CN113592179B - Predictive maintenance method, system and storage medium - Google Patents
Predictive maintenance method, system and storage medium Download PDFInfo
- Publication number
- CN113592179B CN113592179B CN202110873949.2A CN202110873949A CN113592179B CN 113592179 B CN113592179 B CN 113592179B CN 202110873949 A CN202110873949 A CN 202110873949A CN 113592179 B CN113592179 B CN 113592179B
- Authority
- CN
- China
- Prior art keywords
- data
- fault
- target monitoring
- information
- user
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000012423 maintenance Methods 0.000 title claims abstract description 69
- 238000000034 method Methods 0.000 title claims abstract description 34
- 238000012544 monitoring process Methods 0.000 claims abstract description 209
- 230000003993 interaction Effects 0.000 claims abstract description 62
- 238000003745 diagnosis Methods 0.000 claims description 65
- 238000012774 diagnostic algorithm Methods 0.000 claims description 34
- 238000010586 diagram Methods 0.000 claims description 26
- 238000004590 computer program Methods 0.000 claims description 13
- 239000003086 colorant Substances 0.000 claims description 10
- 231100000279 safety data Toxicity 0.000 claims description 10
- 230000003068 static effect Effects 0.000 claims description 10
- 238000012549 training Methods 0.000 claims description 9
- 230000003044 adaptive effect Effects 0.000 claims description 6
- 238000013480 data collection Methods 0.000 claims description 4
- 230000005540 biological transmission Effects 0.000 claims 1
- 238000007726 management method Methods 0.000 description 48
- 230000036541 health Effects 0.000 description 7
- 238000010276 construction Methods 0.000 description 6
- 230000006870 function Effects 0.000 description 4
- 230000010354 integration Effects 0.000 description 4
- 238000013024 troubleshooting Methods 0.000 description 4
- 238000004891 communication Methods 0.000 description 3
- 238000004519 manufacturing process Methods 0.000 description 3
- XEEYBQQBJWHFJM-UHFFFAOYSA-N Iron Chemical compound [Fe] XEEYBQQBJWHFJM-UHFFFAOYSA-N 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000012217 deletion Methods 0.000 description 1
- 230000037430 deletion Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 229910052742 iron Inorganic materials 0.000 description 1
- 239000010687 lubricating oil Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000003921 oil Substances 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000012827 research and development Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2465—Query processing support for facilitating data mining operations in structured databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2477—Temporal data queries
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/048—Interaction techniques based on graphical user interfaces [GUI]
- G06F3/0481—Interaction techniques based on graphical user interfaces [GUI] based on specific properties of the displayed interaction object or a metaphor-based environment, e.g. interaction with desktop elements like windows or icons, or assisted by a cursor's changing behaviour or appearance
- G06F3/0482—Interaction with lists of selectable items, e.g. menus
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/20—Administration of product repair or maintenance
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/18—Status alarms
- G08B21/182—Level alarms, e.g. alarms responsive to variables exceeding a threshold
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Databases & Information Systems (AREA)
- Entrepreneurship & Innovation (AREA)
- Probability & Statistics with Applications (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Data Mining & Analysis (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Fuzzy Systems (AREA)
- Mathematical Physics (AREA)
- Tourism & Hospitality (AREA)
- Software Systems (AREA)
- Computational Linguistics (AREA)
- Game Theory and Decision Science (AREA)
- Development Economics (AREA)
- Human Computer Interaction (AREA)
- Emergency Management (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
The embodiment of the invention discloses a predictive maintenance method, a predictive maintenance system and a storage medium. The method comprises the following steps: receiving configuration information of a user on a target monitoring component through a station management man-machine interaction interface, wherein the configuration information comprises: station, component name, data acquisition scheme and protocol, and acquired data characteristic variables; based on the configuration information, respectively acquiring data of the at least one target monitoring component, and uniformly managing the acquired data; when the configuration information further comprises a fault alarm threshold value and a fault code aiming at the data characteristic variable, monitoring the data of the target monitoring component collected in real time based on the fault alarm threshold value, and when the data of one data characteristic variable continuously monitored within a set time reaches the corresponding fault alarm threshold value, sending out a fault alarm and providing corresponding fault information according to the fault code. The technical scheme in the embodiment of the invention can realize predictive maintenance of a low knowledge threshold.
Description
Technical Field
The invention relates to the field of automobile industry, in particular to a predictive maintenance method, a predictive maintenance system and a computer-readable storage medium.
Background
In the automobile industry, because equipment suppliers and types are numerous, production processes and links are various, and the requirements on knowledge of automation equipment and maintenance personnel are higher, the traditional predictive maintenance system cannot rapidly perform predictive maintenance on workshop or factory-level equipment, and a great deal of research, development and experiment costs are required for predictive diagnosis of fault types.
In addition, even though IT and internet of things technology based on the forefront can perform predictive maintenance analysis on equipment, the results are difficult to use in actual automobile factories because the results depend on different equipment mechanical characteristic data and production processes in the field, such as different equipment structures, different flexible production loads, different station processes and the like. These complex problems make the predictive maintenance business highly dependent on specialized data specialists and vibration specialists or domain-specific technical specialists, while the reusability of the core algorithm is limited due to the complexity of the data samples.
In summary, important issues in promoting predictive maintenance throughout the plant include: problem 1: how to understand the data of the different stations and equipment with lower knowledge thresholds. Problem 2: how to advance basic analysis of critical equipment in a whole plant at low cost. Problem 3: how to smoothly transfer the predictive maintenance to the field staff with lower technical threshold.
Disclosure of Invention
In view of this, the embodiments of the present invention propose a predictive maintenance method, and a predictive maintenance system and a computer-readable storage medium for implementing predictive maintenance of a low knowledge threshold in the automotive industry or other industrial fields.
The predictive maintenance method provided by the embodiment of the invention comprises the following steps: receiving configuration information of a user on each target monitoring component in at least one target monitoring component through a station management man-machine interaction interface, wherein the configuration information comprises: station, component name, data acquisition scheme and protocol, and acquired data characteristic variables; based on the configuration information, respectively acquiring data of the at least one target monitoring component, uniformly managing the acquired data, and storing the acquired data into a first database; when the configuration information further comprises a fault alarm threshold value for the data characteristic variable and a fault code representing fault information, monitoring the data of the target monitoring component collected in real time based on the fault alarm threshold value, and when the data of one data characteristic variable continuously monitored within a set time reaches the corresponding fault alarm threshold value, sending out fault alarm and providing corresponding fault information according to the fault code; or when the configuration information further comprises an adaptive threshold identification for a data characteristic variable and the fault code, analyzing the acquired data of the data characteristic variable to obtain a safety data range of the data characteristic variable, determining a fault alarm threshold for the data characteristic variable based on the safety data range, or determining a fault alarm threshold for the data characteristic variable based on the learned historical alarm threshold of the data characteristic variable; monitoring the data of the target monitoring component acquired in real time based on the fault alarm threshold, and sending out fault alarm and providing corresponding fault information according to the fault code when the data of the data characteristic variable continuously monitored within a set time reaches the fault alarm threshold; wherein the fault information includes: at least one or any combination of a fault name, fault description information, and fault resolution advice; and the corresponding relation between the fault codes and the fault information is provided for the user to learn and inquire through a code information man-machine interaction interface.
In one embodiment, the unified management of the collected data includes: and the centralized soft data gateway is utilized to unify the data acquired based on different protocols into one format and then transmit the format into a message queue.
In one embodiment, further comprising: receiving a diagnosis algorithm selected by a user aiming at a target monitoring component through a diagnosis algorithm man-machine interaction interface, training the diagnosis algorithm by using a first number of monitoring samples stored in a second database aiming at the monitoring samples of the target monitoring component, verifying the accuracy of the trained diagnosis algorithm by using a second number of monitoring samples remained in the monitoring samples of the second database aiming at the target monitoring component, and providing the obtained accuracy to the user through the diagnosis algorithm man-machine interaction interface; wherein the first number is greater than the second number; the monitoring samples comprise fault samples, each fault sample comprises history acquisition data and fault codes which are correspondingly arranged, wherein the history acquisition data are input samples, and the fault codes are output samples; after the user selects the diagnosis algorithm aiming at the target monitoring component, the trained diagnosis algorithm is utilized to monitor the data of the target monitoring component, and when the corresponding fault code is output, a fault alarm is sent out and corresponding fault information is provided according to the fault code.
In one embodiment, further comprising: receiving fault report information of a user through a sample management man-machine interaction interface; the fault reporting information comprises: fault code, station, component name, start-stop time of fault; according to the fault reporting information, data of the target monitoring assembly corresponding to the station and the assembly name in the start-stop time are obtained from the first database, the data in the start-stop time are analyzed, static data and motion data in the data are determined, the motion data are used as effective sample data, the effective sample data are used as historical collecting data and correspond to fault codes in the fault reporting information to form a fault sample of the target monitoring assembly, and the fault sample is stored in the second database.
In one embodiment, further comprising: presenting the data in the start-stop time to the user in a scatter diagram form through the sample management man-machine interaction interface in a time sequence; wherein in the scatter plot, the stationary data and the motion data are distinguished in different colors or different sizes or different scatter patterns; and when a corresponding fault alarm threshold exists, the fault alarm threshold is marked in the scatter diagram.
The embodiment of the invention provides a predictive maintenance method, which comprises the following steps: receiving configuration information of a user on each target monitoring component in at least one target monitoring component through a station management man-machine interaction interface, wherein the configuration information comprises: station, component name, data acquisition scheme and protocol, and acquired data characteristic variables; based on the configuration information, respectively acquiring data of the at least one target monitoring component, uniformly managing the acquired data, and storing the acquired data into a first database; receiving a diagnosis algorithm selected by a user aiming at a target monitoring component through a diagnosis algorithm man-machine interaction interface, training the diagnosis algorithm by using a first number of monitoring samples stored in a second database aiming at the monitoring samples of the target monitoring component, verifying the accuracy of the trained diagnosis algorithm by using a second number of monitoring samples remained in the monitoring samples of the second database aiming at the target monitoring component, and providing the obtained accuracy to the user through the diagnosis algorithm man-machine interaction interface; wherein the first number is greater than the second number; the monitoring samples comprise fault samples, each fault sample comprises history acquisition data and fault codes which are correspondingly arranged, wherein the history acquisition data are input samples, and the fault codes are output samples; after the user selects the diagnosis algorithm aiming at the target monitoring component, the trained diagnosis algorithm is utilized to monitor the data of the target monitoring component, and when the corresponding fault code is output, a fault alarm is sent out and corresponding fault information is provided according to the fault code.
In one embodiment, further comprising: receiving fault report information of a user through a sample management man-machine interaction interface; the fault reporting information comprises: fault code, station, component name, start-stop time of fault; according to the fault reporting information, data of the target monitoring assembly corresponding to the station and the assembly name in the start-stop time are obtained from the first database, the data in the start-stop time are analyzed, static data and motion data in the data are determined, the motion data are determined to be effective sample data, the effective sample data are taken as historical collecting data and correspond to fault codes in the fault reporting information to form a fault sample of the target monitoring assembly, and the fault sample is stored in the second database.
In one embodiment, further comprising: presenting the data in the start-stop time to the user in a scatter diagram form through the sample management man-machine interaction interface in a time sequence; wherein in the scatter plot, the stationary data and the motion data are distinguished in different colors or different sizes or different scatter patterns.
The predictive maintenance system provided in the embodiment of the invention comprises: the station management module is used for receiving configuration information of a user on each target monitoring component in the at least one target monitoring component through the station management man-machine interaction interface, and the configuration information comprises: station, component name, data acquisition scheme and protocol, and acquired data characteristic variables; the data acquisition module is used for respectively acquiring the data of the at least one target monitoring component based on the configuration information, uniformly managing the acquired data and storing the acquired data into the first database; the first data monitoring module is used for monitoring the data of the target monitoring component acquired in real time based on the fault alarm threshold when the configuration information further comprises the fault alarm threshold for the data characteristic variable and the fault code representing the fault information, and sending out fault alarm and providing corresponding fault information according to the fault code when the data of one data characteristic variable is continuously monitored to reach the corresponding fault alarm threshold in a set time; or when the configuration information further comprises an adaptive threshold identification for a data characteristic variable and the fault code, analyzing the acquired data of the data characteristic variable to obtain a safety data range of the data characteristic variable, determining a fault alarm threshold for the data characteristic variable based on the safety data range, or determining a fault alarm threshold for the data characteristic variable based on the learned historical alarm threshold of the data characteristic variable; monitoring the data of the target monitoring component acquired in real time based on the fault alarm threshold, and sending out fault alarm and providing corresponding fault information according to the fault code when the data of the data characteristic variable continuously monitored within a set time reaches the fault alarm threshold; wherein the fault information includes: at least one or any combination of a fault name, fault description information, and fault resolution advice; and the fault code storage module is used for storing the corresponding relation between the fault code and the fault information and providing the corresponding relation for the user to learn and inquire through a code information man-machine interaction interface.
In one embodiment, the data acquisition module uses a centralized soft data gateway to unify data acquired based on different protocols into one format and then transmits the format to a message queue to realize unified management.
In one embodiment, further comprising: the diagnosis algorithm configuration module is used for receiving a diagnosis algorithm selected by a user aiming at a target monitoring component through a diagnosis algorithm man-machine interaction interface, training the diagnosis algorithm by utilizing a first number of monitoring samples in monitoring samples aiming at the target monitoring component stored in a second database, verifying the accuracy of the trained diagnosis algorithm by utilizing a second number of monitoring samples remained in monitoring samples aiming at the target monitoring component in the second database, and providing the obtained accuracy to the user through the diagnosis algorithm man-machine interaction interface; wherein the first number is greater than the second number; the monitoring samples comprise fault samples, each fault sample comprises history acquisition data and fault codes which are correspondingly arranged, wherein the history acquisition data are input samples, and the fault codes are output samples; and the second data monitoring module is used for monitoring the data of the target monitoring assembly acquired in real time by utilizing the trained diagnosis algorithm after the user selects the diagnosis algorithm aiming at the target monitoring assembly, sending out fault alarm information when the corresponding fault code is monitored to be output and providing the corresponding fault information according to the fault code.
In one embodiment, further comprising: the sample management module is used for receiving fault report information of a user through a sample management man-machine interaction interface; the fault reporting information comprises: fault code, station, component name, start-stop time of fault; according to the fault reporting information, data of the target monitoring assembly corresponding to the station and the assembly name in the start-stop time are obtained from the first database, the data in the start-stop time are analyzed, static data and motion data in the data are determined, the motion data are used as effective sample data, the effective sample data are used as historical collecting data and correspond to fault codes in the fault reporting information to form a fault sample of the target monitoring assembly, and the fault sample is stored in the second database.
In one embodiment, the sample management module further presents the data within the start-stop time to the user in a scatter plot form through the sample management human-machine interaction interface in a time sequence; wherein in the scatter plot, the stationary data and the motion data are distinguished in different colors or different sizes or different scatter patterns; and when a corresponding fault alarm threshold exists, the fault alarm threshold is marked in the scatter diagram.
The predictive maintenance system provided in the embodiment of the invention comprises: the station management module is used for receiving configuration information of a user on each target monitoring component in the at least one target monitoring component through the station management man-machine interaction interface, and the configuration information comprises: station, component name, data acquisition scheme and protocol, and acquired data characteristic variables; the data acquisition module is used for respectively acquiring the data of the at least one target monitoring component based on the configuration information, uniformly managing the acquired data and storing the acquired data into the first database; the diagnosis algorithm configuration module is used for receiving a diagnosis algorithm selected by a user aiming at a target monitoring component through a diagnosis algorithm man-machine interaction interface, training the diagnosis algorithm by utilizing a first number of monitoring samples in monitoring samples aiming at the target monitoring component stored in a second database, verifying the accuracy of the trained diagnosis algorithm by utilizing a second number of monitoring samples remained in monitoring samples aiming at the target monitoring component in the second database, and providing the obtained accuracy to the user through the diagnosis algorithm man-machine interaction interface; wherein the first number is greater than the second number; the monitoring samples comprise fault samples, each fault sample comprises history acquisition data and fault codes which are correspondingly arranged, wherein the history acquisition data are input samples, and the fault codes are output samples; and the data monitoring module is used for monitoring the data of the target monitoring assembly acquired in real time by utilizing the trained diagnostic algorithm after the user selects the diagnostic algorithm aiming at the target monitoring assembly, sending out fault alarm information when the corresponding fault code is monitored to be output, and providing the corresponding fault information according to the fault code.
In one embodiment, further comprising: the sample management module is used for receiving fault report information of a user through a sample management man-machine interaction interface; the fault reporting information comprises: fault code, station, component name, start-stop time of fault; according to the fault reporting information, data of the target monitoring assembly corresponding to the station and the assembly name in the start-stop time are obtained from the first database, the data in the start-stop time are analyzed, static data and motion data in the data are determined, the motion data are determined to be effective sample data, the effective sample data are taken as historical collecting data and correspond to fault codes in the fault reporting information to form a fault sample of the target monitoring assembly, and the fault sample is stored in the second database.
In one embodiment, the sample management module further presents the data within the start-stop time to the user in a scatter plot form through the sample management human-machine interaction interface in a time sequence; wherein in the scatter plot, the stationary data and the motion data are distinguished in different colors or different sizes or different scatter patterns.
Still another predictive maintenance system provided in an embodiment of the present invention includes: at least one memory and at least one processor, wherein: the at least one memory is used for storing a computer program; the at least one processor is configured to invoke the computer program stored in the at least one memory to perform the predictive maintenance method of any of the embodiments described above.
A computer-readable storage medium according to an embodiment of the present invention has a computer program stored thereon; the computer program is capable of being executed by a processor and implementing the predictive maintenance method of any of the embodiments described above.
According to the scheme, the manual interaction interface capable of guiding a user such as a maintainer or a technical worker to perform data acquisition on the components to be monitored and configuring information such as the alarm threshold value is provided, and the alarm threshold value can be determined by the system in a self-adaptive manner, so that the user can participate in the construction of the predictive maintenance system with a lower knowledge threshold.
In addition, by providing an interface capable of guiding a user to report fault information such as fault components, fault time periods, fault types and the like when faults occur, further, a fault sample is obtained based on the fault information reported by the user, on one hand, the fault sample on the site can be obtained in real time, and on the other hand, the user can participate in the construction of the predictive maintenance system with a lower knowledge threshold.
Further, by providing an interface that can guide the user to set the diagnostic algorithm for predictive maintenance and pushing the diagnostic accuracy of the diagnostic algorithm to the user for the diagnostic algorithm selected by the user, the user with lower knowledge can be assisted in selecting an appropriate diagnostic algorithm, and further the user can participate in the construction of the predictive maintenance system with lower knowledge threshold.
Therefore, in the embodiment of the invention, data configuration and result integration are not required by a data expert, and can be completed only by a user, so that the knowledge threshold is reduced. In addition, in the embodiment, various components can be monitored, and collected data can be managed in a unified manner, so that the complexity and cost of the system can be reduced.
Drawings
The above and other features and advantages of the present invention will become more apparent to those of ordinary skill in the art by describing in detail preferred embodiments thereof with reference to the attached drawings in which:
fig. 1A and 1B are respectively exemplary flowcharts of a predictive maintenance method in an embodiment of the invention.
Fig. 2A and 2B are schematic diagrams illustrating a workstation management human-machine interface in accordance with an example of the present invention.
FIG. 3 is a schematic diagram of a code information man-machine interface according to an example of the present invention.
Fig. 4A-4D are schematic diagrams illustrating a sample management human-machine interface in accordance with an example of the present invention.
FIG. 4E is a schematic diagram of a scatter plot in one example of the invention.
FIG. 5 is a schematic diagram of a human-machine interface for a diagnostic algorithm in accordance with one example of the present invention.
Fig. 6 is a schematic structural diagram of a predictive maintenance system according to an embodiment of the invention.
Fig. 7 is a schematic structural diagram of yet another predictive maintenance system according to an embodiment of the invention.
Wherein, the reference numerals are as follows:
| Reference numerals | Meaning of |
| 101～106 | Step (a) |
| 601 | Station management module |
| 602 | Data acquisition module |
| 603 | First data monitoring module |
| 604 | Fault code storage module |
| 605 | Sample management module |
| 606 | Diagnostic algorithm configuration module |
| 607 | Second data monitoring module |
| 608 | Database for storing data |
| 71 | Memory device |
| 72 | Processor and method for controlling the same |
| 73 | Display device |
| 74 | Bus line |
Detailed Description
In the embodiments of the present invention, considering that research and development departments of some IT companies and automobile companies are currently researching specific devices in the field of predictive maintenance, two types are possible: 1) Data platforms provide algorithm flow engines (libraries) such as IBM and Tangent Works (https:// www.tangent.works /). These data platforms provide advanced artificial intelligence algorithms suitable for use by data specialists. But it is very high for technicians and workers in the automotive industry. If the results are integrated into the field application by data specialists, higher initial investment and later system maintenance costs are required. 2) Predictive maintenance of special equipment, such as ABB motors and generators. If predictive maintenance of critical equipment from a whole plant is desired in the future, such targeted dedicated equipment would make the whole plant's application/service integration more complex and redundant, and system maintenance costs would also increase.
Therefore, in order to provide a predictive maintenance solution with low knowledge threshold and low cost, in the embodiment of the present invention, it is considered to provide a man-machine interaction interface, which can guide a field user, such as a serviceman or a technical worker, to perform data collection and configuration of information such as an alarm threshold on a component to be monitored; when a fault occurs, a field user is guided to report fault information such as a fault component, a fault time period, a fault type and the like, and a fault sample is obtained based on the fault information reported by the user; and guiding the on-site user to set an algorithm for predictive maintenance. Therefore, data configuration and result integration can be carried out without data expert, and the method can be completed only by a user, so that the knowledge threshold is reduced. In addition, in the embodiment, various components can be monitored, and collected data can be managed in a unified manner, so that the complexity and cost of the system can be reduced.
The present invention will be further described in detail with reference to the following examples, in order to make the objects, technical solutions and advantages of the present invention more apparent.
Fig. 1A and 1B are respectively exemplary flowcharts of a predictive maintenance method according to an embodiment of the present invention. As shown in fig. 1A, the method may include the steps of:
Step 101, receiving configuration information of a user on each target monitoring component in at least one target monitoring component through a station management man-machine interaction interface, wherein the configuration information can comprise: station, component name, data acquisition scheme and protocol, acquired data characteristic variables and other information.
Fig. 2A and 2B are schematic diagrams illustrating a workstation management human-machine interface in accordance with an example of the present invention. Wherein fig. 2A is a main display interface, and fig. 2B is a configuration interface. As shown in fig. 2A, the station management man-machine interaction main display interface is provided with settings for stations, component names, data acquisition schemes, data acquisition protocols, hosts, ports, titles (Topic) and other information (only part of the content can be displayed in one row due to limited space). For the completed items, an "edit" button for modifying the items, a "copy" button for copying the items, and a "delete" button for deleting the items are also provided in the interface. In addition, in order to add new items, an "add" button for newly adding items and a "build table" button for database build table storage are also provided in the interface.
For example, when the "add" button or the "edit" button is clicked, a station detail configuration interface as shown in fig. 2B may be popped up. Assuming the case when the first entry is added, for example, the user may output a specific workstation number, such as PA01, in the text box corresponding to "workstation" as shown in fig. 2B. The component to be monitored, such as a chain, may be selected in a drop down box corresponding to "component". The data acquisition scheme to be sampled, such as bosch XDK, is selected in the drop-down box corresponding to the "data acquisition scheme". In this embodiment, data acquisition protocols corresponding to various data acquisition schemes are known by default, for example, after the data acquisition scheme selects the Boadapted XDK, the protocol is known by default as MQTT. Wherein the specific data acquisition scheme may be determined based on the medium from which the data is derived. For example, the data acquisition device of many manufacturers with Siemens and ABB on the market can directly acquire the sensor data. In addition, there are bosch XDK devices, data gateway devices, standard data push interfaces, field control devices such as siemens and ohmmeter, and the like, and some applications are also considered data acquisition devices. In addition, a corresponding host number, such as 47.12.3.23, may be entered in the text box corresponding to "host". A corresponding port number, such as 1883, may be entered in the text box corresponding to "port". A corresponding title, such as svw/PA01, may be entered in the text box corresponding to "title". In addition, a corresponding variable name may be input in a text box corresponding to a "feature" (i.e., a data feature variable, simply referred to as a "feature" in the drawing), an address for collecting the data feature variable may be input in a text box corresponding to an "address", two alarm thresholds, i.e., a "middle level threshold" and a "high level threshold", may be set corresponding to the data feature variable, and a corresponding fault code, i.e., a "middle level fault code" and a "high level fault code", may be further set corresponding to each alarm threshold, respectively. In this embodiment, for the same component, more than one data feature variable may be collected, and some data feature variables have an alarm threshold and a corresponding fault code representing fault information, and some data feature variables have no alarm threshold and a corresponding fault code. For example, in fig. 2B, the data characteristic variables may include: time stamp (timestamp), maximum vibration amount (vibMax), etc., can be added by clicking the "add" button on the right side, and for an already added item, if not required, the "delete" button on the right side can be clicked for deletion. Wherein the timestamp (timestamp) is without an alarm threshold. The maximum vibration quantity (vibMax) can have a corresponding two-stage alarm threshold and a corresponding fault code. The numerical values in the present embodiment are merely illustrative, and do not represent actual numerical values.
In this embodiment, the alarm threshold may be directly input by a user with abundant experience, or when the user does not determine what the appropriate alarm threshold is, the "adaptive threshold" option in fig. 2A may be selected, so that the system automatically learns to obtain the corresponding alarm threshold. For example, the system may analyze the collected data of the data feature variable requiring automatic learning of the alarm threshold, obtain a safe data range of the data feature variable, and determine a fault alarm threshold for the data feature variable based on the safe data range. Or may be determined based on a learned historical fault alert threshold for the data characteristic variable. It is not limited herein.
In order to facilitate the user to understand the specific fault information corresponding to each fault code, in this embodiment, a code information man-machine interaction interface may be further provided, as shown in fig. 3, fig. 3 is a schematic diagram of a code information man-machine interaction interface in an example of the present invention, where the correspondence between each code and its indication information is presented, in this embodiment, the code includes a health code and a fault code, and correspondingly, the indication information also includes health information and fault information, and may specifically include: name and corresponding descriptive information. In addition, the fault resolution advice may be further included in addition to the fault name and the fault description information for the fault information. Wherein the troubleshooting advice may be hidden by folding or unfolded due to limited space. For example, for a fault code of code 1100, the corresponding fault name is: the vibration energy of the equipment is abnormal, and the corresponding description information is as follows: temperature anomaly (abnormal temperature), of course, in other embodiments, the description information may be "too high temperature" or "too low temperature", etc. The corresponding troubleshooting suggestions include: 1. checking if there is additional debris impact, such as scrap iron, oil or debris; 2. checking whether there is a human intervention, such as a carelessness or an accidental collision; 3. checking equipment noise and the lubricating oil state of the bearing; 4. monitoring continues. Of course, in other embodiments, the information for the code may also include only the name, or only the descriptive information, or only the name and troubleshooting advice, or only the descriptive information and troubleshooting advice, and the like.
Step 102, based on the configuration information, respectively collecting data of the at least one target monitoring component, uniformly managing the collected data, and storing the collected data in a first database.
In this embodiment, the centralized soft data gateway may be utilized to unify data collected based on different protocols into a single format and then transmit the unified data to a message queue, for example, the message queue of MQTT (Message Queuing Telemetry Transport, message queue telemetry transport protocol). And the time sequence data writing module can be used for writing into the first database for storage.
Step 103, for the situation that there are fault alarm thresholds corresponding to the data characteristic variables and fault codes representing fault information, the data of the target monitoring component collected in real time can be monitored based on the fault alarm thresholds, and when the data of one data characteristic variable continuously monitored within a set time reaches the corresponding fault alarm threshold, fault alarms are sent out, and corresponding fault information is provided according to the fault codes.
104, Receiving fault report information of a user through a sample management man-machine interaction interface; the fault reporting information comprises: fault code, station, component name, start-stop time of fault, etc.
Fig. 4A-4D are schematic diagrams illustrating a sample management human-machine interface in accordance with an example of the present invention. Fig. 4A is a main display interface, and fig. 4B to 4D are configuration interfaces. As shown in fig. 4A, the sample management man-machine interaction main display interface is provided with settings for information such as codes, names, stations, component names, start time, end time and the like. The code may be a health code or a fault code, that is, the sample management man-machine interaction interface in the embodiment of the invention may report a health sample or a fault sample. Of course, in other examples, only the failure samples may be reported. For the completed items, an "edit" button for modifying the items and a "delete" button for deleting the items are also provided in the interface. In addition, in order to add a new item, an "add" button for the newly added item is also provided in the interface.
For example, when the "add" button is clicked, a sample detail configuration interface as shown in fig. 4B to 4D may be popped up. As shown in fig. 4B to 4D, the user may output a specific station number in the text box corresponding to the "station", and the corresponding component name may be automatically displayed in the gray frame on the right side. In this embodiment, when the mouse click is placed in the text box, all the stations and the corresponding component names are presented to the user for selection in the form of a pop-up drop-down menu (not shown). The corresponding sample level may be selected in a drop down box corresponding to "sample level," such as a health, intermediate level fault, or high level fault as shown in fig. 4B. The corresponding sample code is selected in the drop-down box for the corresponding "sample code", such as the various sample codes and corresponding sample names shown in fig. 4C. After the sample code is selected, the corresponding sample name is selected, as shown in fig. 4D. The corresponding start and stop times (including start time and end time) are entered in the text box corresponding to "sample time". In this embodiment, when the mouse click is placed in the corresponding text box, the calendar interface is presented in the form of a pop-up window. And inputting corresponding description information in a text box corresponding to the description.
In this embodiment, in order to reduce the knowledge threshold of the user, only the corresponding start-stop time is required to be reported by the user when the user reports the health sample or the fault sample. However, considering that the period of time includes a period of time when the target monitoring component is operating, and possibly includes a period of time when the target monitoring component is not operating, in order to remove interference, valid sample data is extracted from the period of time, in this embodiment, the data in the start-stop time may be further analyzed to determine static data and motion data, the motion data is used as valid sample data, the valid sample data is used as historical collection data, and the valid sample data corresponds to a code in the reported information to form a monitoring sample of the target monitoring component, and the monitoring sample is stored in the second database. Wherein the monitoring samples may include health samples and fault samples. Of course, in other examples, the monitoring samples may include only fault samples. The historical acquisition data is an input sample, and the corresponding code is an output sample.
In addition, in order to facilitate the user to confirm whether the sample range is correct, the data in the start and stop time can be further presented to the user in a time sequence in a form of a scatter diagram through the sample management man-machine interaction interface; wherein in the scatter plot, the stationary data and the motion data are distinguished in different colors or different sizes or different scatter patterns; and when a corresponding fault alarm threshold exists, the fault alarm threshold is marked in the scatter diagram. A schematic of a scatter plot in one example of the invention is shown in fig. 4E. In particular, as shown in fig. 4A, a "view" button for viewing a view may be further set for the completed item, and as shown in fig. 4B and 4C, a "preview view and save" button may be further set, and when the "view" button or the "preview view and save" button is clicked, the scatter diagram may be presented for viewing by the user.
If, furthermore, a history monitoring sample has been previously obtained, the obtained history monitoring sample may first be stored in a second database,
Step 105, receiving a diagnostic algorithm selected by a user for a target monitoring component through a diagnostic algorithm man-machine interaction interface, training the diagnostic algorithm by using a first number of monitoring samples in monitoring samples stored in a second database for the target monitoring component, performing accuracy verification on the trained diagnostic algorithm by using a second number of monitoring samples in the second database for the remaining monitoring samples in the target monitoring component, and providing the obtained accuracy to the user through the diagnostic algorithm man-machine interaction interface. Wherein the first number may be substantially greater than the second number.
In various embodiments, the monitoring sample may include both a healthy sample and a failed sample, or may include only a failed sample.
FIG. 5 is a schematic diagram of a human-machine interface for a diagnostic algorithm in accordance with one example of the present invention. As shown in FIG. 5, after a diagnostic algorithm is selected for a target monitoring component, the accuracy for the diagnostic algorithm is presented in the lateral accuracy region. For example, after a naive bayes diagnosis algorithm is selected for the chain of the station PA08, the accuracy area shows 60% of the corresponding accuracy, if the user wants to know other diagnosis algorithms, the user can reselect other types of diagnosis algorithms and click a "recalculate" button, and at this time, the accuracy of the reselected diagnosis algorithm is shown, so that the user can conveniently select the diagnosis algorithm for final use, and the user does not need to know the characteristics of various diagnosis algorithms in detail in advance.
And 106, after the user selects a diagnosis algorithm for a target monitoring component, monitoring the data of the target monitoring component acquired in real time by using the trained diagnosis algorithm, and sending out a fault alarm and providing corresponding fault information according to the fault code when the corresponding fault code is output.
In specific implementation, the corresponding fault information can be presented to the user through one page of the man-machine interaction interface, or can be sent to other pre-configured devices at the same time. It is not particularly limited herein.
It can be seen that in the above-described flowchart shown in fig. 1, two monitoring methods can be employed. One is alarm threshold based monitoring and one is diagnostic algorithm based monitoring. In other embodiments, only one monitoring method may be used, that is, only some of the steps 101 to 106 may be included. For example, as shown in FIG. 1B, only steps 101-103 may be included. Furthermore, in other embodiments, steps 101-102 and 104-106 may be included alone, or 101-102 and 105-106 may be included alone. Wherein, for the case that step 103 is not included, the setting of the alarm threshold may not be included in the configuration information of the target monitoring component. For the case that step 104 is not included, the monitoring sample is stored in the default second database, but the monitoring sample is not necessarily input through the sample management man-machine interface in the embodiment, and may also be input in other manners; or may be input through the sample management human-computer interaction interface in this embodiment, but may not be input in real time, and may be input in advance.
The predictive maintenance method in the embodiment of the invention is described in detail above, and the predictive maintenance system in the embodiment of the invention is described in detail below. The predictive maintenance system in the embodiment of the present invention may be used to implement the predictive maintenance method in the embodiment of the present invention, and details not disclosed in detail in the embodiment of the system of the present invention may be referred to corresponding descriptions in the embodiment of the method of the present invention, which are not described in detail herein.
Fig. 6 is an exemplary block diagram of a predictive maintenance system in an embodiment of the invention. As shown in fig. 6, the system may include: a workstation management module 601, a data acquisition module 602, a first data monitoring module 603, a fault code storage module 604, a sample management module 605, a diagnostic algorithm configuration module 606, and a second data monitoring module 607.
The station management module 601 is configured to receive configuration information of a user on each of at least one target monitoring component through a station management man-machine interface, where the configuration information includes: station, component name, data acquisition scheme and protocol, acquired data characteristic variables and the like.
The data collection module 602 is configured to collect data of the at least one target monitoring component based on the configuration information, perform unified management on the collected data, and store the collected data in the first database. For example, in one embodiment, the data collection module 602 may utilize a centralized soft data gateway to unify data collected based on different protocols into a single format and then transmit the unified data to a message queue for unified management.
The first data monitoring module 603 is configured to monitor, when the configuration information further includes a fault alarm threshold value for a data feature variable and a fault code representing fault information, data of the target monitoring component collected in real time based on the fault alarm threshold value, and continuously monitor that the data of a data feature variable reaches a corresponding fault alarm threshold value within a set time, send out a fault alarm and provide corresponding fault information according to the fault code; or when the configuration information further comprises an adaptive threshold identification for a data characteristic variable and the fault code, analyzing the acquired data of the data characteristic variable to obtain a safety data range of the data characteristic variable, determining a fault alarm threshold for the data characteristic variable based on the safety data range, or determining a fault alarm threshold for the data characteristic variable based on the learned historical alarm threshold of the data characteristic variable; monitoring the data of the target monitoring component acquired in real time based on the fault alarm threshold, and sending out fault alarm and providing corresponding fault information according to the fault code when the data of the data characteristic variable continuously monitored within a set time reaches the fault alarm threshold; wherein the fault information includes: at least one of, or any combination of, a fault name, fault description information, and a fault resolution suggestion.
The fault code storage module 604 is configured to store a correspondence between the fault code and the fault information, and provide the correspondence to the user for learning and querying through a code information man-machine interaction interface.
The sample management module 605 is configured to receive fault report information of a user through a sample management man-machine interaction interface; the fault reporting information comprises: fault code, station, component name, start-stop time of fault; according to the fault reporting information, data of the target monitoring assembly corresponding to the station and the assembly name in the start-stop time are obtained from the first database, the data in the start-stop time are analyzed, static data and motion data in the data are determined, the motion data are used as effective sample data, the effective sample data are used as historical collecting data and correspond to fault codes in the fault reporting information to form a fault sample of the target monitoring assembly, and the fault sample is stored in the second database. In particular, the first database and the second database may be different databases or may be combined together to collectively form a large database 608.
In one embodiment, the sample management module 605 may further present the data within the start-stop time in a time series to the user in the form of a scatter plot through the sample management human-machine interaction interface; wherein in the scatter plot, the stationary data and the motion data are distinguished in different colors or different sizes or different scatter patterns; and when a corresponding fault alarm threshold exists, the fault alarm threshold is marked in the scatter diagram.
The diagnostic algorithm configuration module 606 is configured to receive, through a diagnostic algorithm man-machine interface, a diagnostic algorithm selected by a user for a target monitoring component, train the diagnostic algorithm with a first number of monitoring samples stored in a second database for the monitoring samples of the target monitoring component, verify an accuracy of the trained diagnostic algorithm with a second number of monitoring samples remaining in the monitoring samples stored in the second database for the target monitoring component, and provide the obtained accuracy to the user through the diagnostic algorithm man-machine interface; wherein the first number is greater than the second number; the monitoring samples comprise fault samples, each fault sample comprises history acquisition data and fault codes which are correspondingly arranged, wherein the history acquisition data are input samples, and the fault codes are output samples.
The second data monitoring module 607 is configured to monitor, after the user selects a diagnostic algorithm for the target monitoring component, data of the target monitoring component acquired in real time by using the trained diagnostic algorithm, and send out fault alarm information and provide corresponding fault information according to the fault code when the user monitors to output the corresponding fault code.
In some embodiments, only some of the modules in the system shown in FIG. 6 may be included. For example, only the station management module 601, the data acquisition module 602, the first data monitoring module 603, and the fault code storage module 604 in fig. 6 may be included. Or include only the workstation management module 601, the data acquisition module 602, the fault code storage module 604, the diagnostic algorithm configuration module 606, and the second data monitoring module 607 of fig. 6. Or include only the workstation management module 601, the data acquisition module 602, the fault code storage module 604, the sample management module 605, the diagnostic algorithm configuration module 606, and the second data monitoring module 607 of fig. 6.
FIG. 7 is a schematic diagram of a further predictive maintenance system in accordance with an embodiment of the application, which may be used to implement the method shown in FIG. 1 or to implement the system shown in FIG. 6. As shown in fig. 7, the system may include: at least one memory 71, at least one processor 72, and at least one display 73. In addition, some other components may be included, such as communication ports and the like. These components communicate via a bus 74.
Wherein the at least one memory 71 is used for storing a computer program. In one embodiment, the computer program may be understood to include the various modules of the predictive maintenance system shown in FIG. 6. In addition, the at least one memory 71 may also store an operating system or the like. Operating systems include, but are not limited to: android operating system, symbian operating system, windows operating system, linux operating system, etc.
The at least one processor 72 is configured to invoke the computer program stored in the at least one memory 71 to perform the predictive maintenance method described in embodiments of the application. The processor 72 may be a CPU, processing unit/module, ASIC, logic module, or programmable gate array, among others. Which can receive and transmit data through the communication port.
At least one display 73 is used to display various human-machine interaction interfaces.
It should be noted that not all the steps and modules in the above processes and the structure diagrams are necessary, and some steps or modules may be omitted according to actual needs. The execution sequence of the steps is not fixed and can be adjusted as required. The division of the modules is merely for convenience of description and the division of functions adopted in the embodiments, and in actual implementation, one module may be implemented by a plurality of modules, and functions of a plurality of modules may be implemented by the same module, and the modules may be located in the same device or different devices.
It will be appreciated that the hardware modules in the embodiments described above may be implemented mechanically or electronically. For example, a hardware module may include specially designed permanent circuits or logic devices (e.g., special purpose processors such as FPGAs or ASICs) for performing certain operations. A hardware module may also include programmable logic devices or circuits (e.g., including a general purpose processor or other programmable processor) temporarily configured by software for performing particular operations. As regards implementation of the hardware modules in a mechanical manner, either by dedicated permanent circuits or by circuits that are temporarily configured (e.g. by software), this may be determined by cost and time considerations.
In addition, in an embodiment of the present application, a computer readable storage medium is provided, on which a computer program is stored, where the computer program can be executed by a processor and implement the predictive maintenance method described in the embodiment of the present application. Specifically, a system or apparatus provided with a storage medium on which a software program code realizing the functions of any of the above embodiments is stored, and a computer (or CPU or MPU) of the system or apparatus may be caused to read out and execute the program code stored in the storage medium. Further, some or all of the actual operations may be performed by an operating system or the like operating on a computer based on instructions of the program code. The program code read out from the storage medium may also be written into a memory provided in an expansion board inserted into a computer or into a memory provided in an expansion unit connected to the computer, and then, based on instructions of the program code, a CPU or the like mounted on the expansion board or the expansion unit may be caused to perform part or all of actual operations, thereby realizing the functions of any of the above embodiments. Storage medium implementations for providing program code include floppy disks, hard disks, magneto-optical disks, optical disks (e.g., CD-ROMs, CD-R, CD-RWs, DVD-ROMs, DVD-RAMs, DVD-RWs, DVD+RWs), magnetic tapes, non-volatile memory cards, and ROMs. Alternatively, the program code may be downloaded from a server computer by a communication network.
According to the scheme, the manual interaction interface capable of guiding a user such as a maintainer or a technical worker to perform data acquisition on the components to be monitored and configuring information such as the alarm threshold value is provided, and the alarm threshold value can be determined by the system in a self-adaptive manner, so that the user can participate in the construction of the predictive maintenance system with a lower knowledge threshold.
In addition, by providing an interface capable of guiding a user to report fault information such as fault components, fault time periods, fault types and the like when faults occur, further, a fault sample is obtained based on the fault information reported by the user, on one hand, the fault sample on the site can be obtained in real time, and on the other hand, the user can participate in the construction of the predictive maintenance system with a lower knowledge threshold.
Further, by providing an interface that can guide the user to set the diagnostic algorithm for predictive maintenance and pushing the diagnostic accuracy of the diagnostic algorithm to the user for the diagnostic algorithm selected by the user, the user with lower knowledge can be assisted in selecting an appropriate diagnostic algorithm, and further the user can participate in the construction of the predictive maintenance system with lower knowledge threshold.
Therefore, in the embodiment of the invention, data configuration and result integration are not required by a data expert, and can be completed only by a user, so that the knowledge threshold is reduced. In addition, in the embodiment, various components can be monitored, and collected data can be managed in a unified manner, so that the complexity and cost of the system can be reduced.
The foregoing description of the preferred embodiments of the invention is not intended to be limiting, but rather is intended to cover all modifications, equivalents, alternatives, and improvements that fall within the spirit and scope of the invention.
Claims (16)
1. A predictive maintenance method, comprising:
receiving configuration information of a user on each target monitoring component in at least one target monitoring component through a station management man-machine interaction interface, wherein the configuration information comprises: station, component name, data acquisition scheme and protocol, and acquired data characteristic variables;
Based on the configuration information, respectively acquiring data of the at least one target monitoring component, uniformly managing the acquired data, and storing the acquired data into a first database;
When the configuration information further comprises a fault alarm threshold value for the data characteristic variable and a fault code representing fault information, monitoring the data of the target monitoring component collected in real time based on the fault alarm threshold value, and when the data of one data characteristic variable continuously monitored within a set time reaches the corresponding fault alarm threshold value, sending out fault alarm and providing corresponding fault information according to the fault code; or alternatively
When the configuration information further comprises an adaptive threshold identification for a data characteristic variable and the fault code, analyzing the acquired data of the data characteristic variable to obtain a safety data range of the data characteristic variable, determining a fault alarm threshold for the data characteristic variable based on the safety data range, or determining a fault alarm threshold for the data characteristic variable based on the learned historical alarm threshold of the data characteristic variable; monitoring the data of the target monitoring component acquired in real time based on the fault alarm threshold, and sending out fault alarm and providing corresponding fault information according to the fault code when the data of the data characteristic variable continuously monitored within a set time reaches the fault alarm threshold;
Wherein the fault information includes: at least one or any combination of a fault name, fault description information, and fault resolution advice; and the corresponding relation between the fault codes and the fault information is provided for the user to learn and inquire through a code information man-machine interaction interface.
2. The predictive maintenance method as recited in claim 1, wherein said unified management of the collected data includes: and the centralized soft data gateway is utilized to unify the data acquired based on different protocols into one format and then transmit the format into a message queue.
3. The predictive maintenance method as recited in claim 1, further comprising:
Receiving a diagnosis algorithm selected by a user aiming at a target monitoring component through a diagnosis algorithm man-machine interaction interface, training the diagnosis algorithm by using a first number of monitoring samples stored in a second database aiming at the monitoring samples of the target monitoring component, verifying the accuracy of the trained diagnosis algorithm by using a second number of monitoring samples remained in the monitoring samples of the second database aiming at the target monitoring component, and providing the obtained accuracy to the user through the diagnosis algorithm man-machine interaction interface; wherein the first number is greater than the second number; the monitoring samples comprise fault samples, each fault sample comprises history acquisition data and fault codes which are correspondingly arranged, wherein the history acquisition data are input samples, and the fault codes are output samples;
After the user selects the diagnosis algorithm aiming at the target monitoring component, the trained diagnosis algorithm is utilized to monitor the data of the target monitoring component, and when the corresponding fault code is output, a fault alarm is sent out and corresponding fault information is provided according to the fault code.
4. A predictive maintenance method as claimed in claim 3, further comprising:
Receiving fault report information of a user through a sample management man-machine interaction interface; the fault reporting information comprises: fault code, station, component name, start-stop time of fault;
according to the fault reporting information, data of the target monitoring assembly corresponding to the station and the assembly name in the start-stop time are obtained from the first database, the data in the start-stop time are analyzed, static data and motion data in the data are determined, the motion data are used as effective sample data, the effective sample data are used as historical collecting data and correspond to fault codes in the fault reporting information to form a fault sample of the target monitoring assembly, and the fault sample is stored in the second database.
5. The predictive maintenance method of claim 4, further comprising: presenting the data in the start-stop time to the user in a scatter diagram form through the sample management man-machine interaction interface in a time sequence; wherein in the scatter plot, the stationary data and the motion data are distinguished in different colors or different sizes or different scatter patterns; and when a corresponding fault alarm threshold exists, the fault alarm threshold is marked in the scatter diagram.
6. A predictive maintenance method, comprising:
receiving configuration information of a user on each target monitoring component in at least one target monitoring component through a station management man-machine interaction interface, wherein the configuration information comprises: station, component name, data acquisition scheme and protocol, and acquired data characteristic variables;
Based on the configuration information, respectively acquiring data of the at least one target monitoring component, uniformly managing the acquired data, and storing the acquired data into a first database;
Receiving a diagnosis algorithm selected by a user aiming at a target monitoring component through a diagnosis algorithm man-machine interaction interface, training the diagnosis algorithm by using a first number of monitoring samples stored in a second database aiming at the monitoring samples of the target monitoring component, verifying the accuracy of the trained diagnosis algorithm by using a second number of monitoring samples remained in the monitoring samples of the second database aiming at the target monitoring component, and providing the obtained accuracy to the user through the diagnosis algorithm man-machine interaction interface; wherein the first number is greater than the second number; the monitoring samples comprise fault samples, each fault sample comprises history acquisition data and fault codes which are correspondingly arranged, wherein the history acquisition data are input samples, and the fault codes are output samples;
After the user selects the diagnosis algorithm aiming at the target monitoring component, the trained diagnosis algorithm is utilized to monitor the data of the target monitoring component, and when the corresponding fault code is output, a fault alarm is sent out and corresponding fault information is provided according to the fault code;
Receiving fault report information of a user through a sample management man-machine interaction interface; the fault reporting information comprises: fault code, station, component name, start-stop time of fault;
According to the fault reporting information, data of the target monitoring assembly corresponding to the station and the assembly name in the start-stop time are obtained from the first database, the data in the start-stop time are analyzed, static data and motion data in the data are determined, the motion data are determined to be effective sample data, the effective sample data are taken as historical collecting data and correspond to fault codes in the fault reporting information to form a fault sample of the target monitoring assembly, and the fault sample is stored in the second database.
7. The predictive maintenance method of claim 6, further comprising: presenting the data in the start-stop time to the user in a scatter diagram form through the sample management man-machine interaction interface in a time sequence; wherein in the scatter plot, the stationary data and the motion data are distinguished in different colors or different sizes or different scatter patterns.
8. A predictive maintenance system, comprising:
The station management module is used for receiving configuration information of a user on each target monitoring component in the at least one target monitoring component through the station management man-machine interaction interface, and the configuration information comprises: station, component name, data acquisition scheme and protocol, and acquired data characteristic variables;
the data acquisition module is used for respectively acquiring the data of the at least one target monitoring component based on the configuration information, uniformly managing the acquired data and storing the acquired data into the first database;
The first data monitoring module is used for monitoring the data of the target monitoring component acquired in real time based on the fault alarm threshold when the configuration information further comprises the fault alarm threshold for the data characteristic variable and the fault code representing the fault information, and sending out fault alarm and providing corresponding fault information according to the fault code when the data of one data characteristic variable is continuously monitored to reach the corresponding fault alarm threshold in a set time; or when the configuration information further comprises an adaptive threshold identification for a data characteristic variable and the fault code, analyzing the acquired data of the data characteristic variable to obtain a safety data range of the data characteristic variable, determining a fault alarm threshold for the data characteristic variable based on the safety data range, or determining a fault alarm threshold for the data characteristic variable based on the learned historical alarm threshold of the data characteristic variable; monitoring the data of the target monitoring component acquired in real time based on the fault alarm threshold, and sending out fault alarm and providing corresponding fault information according to the fault code when the data of the data characteristic variable continuously monitored within a set time reaches the fault alarm threshold; wherein the fault information includes: at least one or any combination of a fault name, fault description information, and fault resolution advice;
And the fault code storage module is used for storing the corresponding relation between the fault code and the fault information and providing the corresponding relation for the user to learn and inquire through a code information man-machine interaction interface.
9. The predictive maintenance system of claim 8, wherein the data collection module utilizes a centralized soft data gateway to unify data collected based on different protocols into a single format for transmission to a message queue for unified management.
10. The predictive maintenance system of claim 8, further comprising:
The diagnosis algorithm configuration module is used for receiving a diagnosis algorithm selected by a user aiming at a target monitoring component through a diagnosis algorithm man-machine interaction interface, training the diagnosis algorithm by utilizing a first number of monitoring samples in monitoring samples aiming at the target monitoring component stored in a second database, verifying the accuracy of the trained diagnosis algorithm by utilizing a second number of monitoring samples remained in monitoring samples aiming at the target monitoring component in the second database, and providing the obtained accuracy to the user through the diagnosis algorithm man-machine interaction interface; wherein the first number is greater than the second number; the monitoring samples comprise fault samples, each fault sample comprises history acquisition data and fault codes which are correspondingly arranged, wherein the history acquisition data are input samples, and the fault codes are output samples;
And the second data monitoring module is used for monitoring the data of the target monitoring assembly acquired in real time by utilizing the trained diagnosis algorithm after the user selects the diagnosis algorithm aiming at the target monitoring assembly, sending out fault alarm information when the corresponding fault code is monitored to be output and providing the corresponding fault information according to the fault code.
11. The predictive maintenance system of claim 10, further comprising:
the sample management module is used for receiving fault report information of a user through a sample management man-machine interaction interface; the fault reporting information comprises: fault code, station, component name, start-stop time of fault; according to the fault reporting information, data of the target monitoring assembly corresponding to the station and the assembly name in the start-stop time are obtained from the first database, the data in the start-stop time are analyzed, static data and motion data in the data are determined, the motion data are used as effective sample data, the effective sample data are used as historical collecting data and correspond to fault codes in the fault reporting information to form a fault sample of the target monitoring assembly, and the fault sample is stored in the second database.
12. The predictive maintenance system of claim 11, wherein the sample management module further presents data within the start-stop time in a time series to the user in a scatter plot through the sample management human-machine interface; wherein in the scatter plot, the stationary data and the motion data are distinguished in different colors or different sizes or different scatter patterns; and when a corresponding fault alarm threshold exists, the fault alarm threshold is marked in the scatter diagram.
13. A predictive maintenance system, comprising:
The station management module is used for receiving configuration information of a user on each target monitoring component in the at least one target monitoring component through the station management man-machine interaction interface, and the configuration information comprises: station, component name, data acquisition scheme and protocol, and acquired data characteristic variables;
the data acquisition module is used for respectively acquiring the data of the at least one target monitoring component based on the configuration information, uniformly managing the acquired data and storing the acquired data into the first database;
The diagnosis algorithm configuration module is used for receiving a diagnosis algorithm selected by a user aiming at a target monitoring component through a diagnosis algorithm man-machine interaction interface, training the diagnosis algorithm by utilizing a first number of monitoring samples in monitoring samples aiming at the target monitoring component stored in a second database, verifying the accuracy of the trained diagnosis algorithm by utilizing a second number of monitoring samples remained in monitoring samples aiming at the target monitoring component in the second database, and providing the obtained accuracy to the user through the diagnosis algorithm man-machine interaction interface; wherein the first number is greater than the second number; the monitoring samples comprise fault samples, each fault sample comprises history acquisition data and fault codes which are correspondingly arranged, wherein the history acquisition data are input samples, and the fault codes are output samples;
The data monitoring module is used for monitoring the data of the target monitoring assembly acquired in real time by utilizing the trained diagnostic algorithm after the user selects the diagnostic algorithm aiming at the target monitoring assembly, sending out fault alarm information and providing corresponding fault information according to the fault code when the user monitors to output the corresponding fault code;
The sample management module is used for receiving fault report information of a user through a sample management man-machine interaction interface; the fault reporting information comprises: fault code, station, component name, start-stop time of fault; according to the fault reporting information, data of the target monitoring assembly corresponding to the station and the assembly name in the start-stop time are obtained from the first database, the data in the start-stop time are analyzed, static data and motion data in the data are determined, the motion data are determined to be effective sample data, the effective sample data are taken as historical collecting data and correspond to fault codes in the fault reporting information to form a fault sample of the target monitoring assembly, and the fault sample is stored in the second database.
14. The predictive maintenance system of claim 13, wherein the sample management module further presents data within the start-stop time in a time series to the user in a scatter plot through the sample management human-machine interface; wherein in the scatter plot, the stationary data and the motion data are distinguished in different colors or different sizes or different scatter patterns.
15. A predictive maintenance system, comprising: at least one memory and at least one processor, wherein:
The at least one memory is used for storing a computer program;
The at least one processor is configured to invoke a computer program stored in the at least one memory to perform the predictive maintenance method of any of claims 1-7.
16. A computer readable storage medium having a computer program stored thereon; computer program, characterized in that it is executable by a processor and implements the predictive maintenance method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110873949.2A CN113592179B (en) | 2021-07-30 | 2021-07-30 | Predictive maintenance method, system and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110873949.2A CN113592179B (en) | 2021-07-30 | 2021-07-30 | Predictive maintenance method, system and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113592179A CN113592179A (en) | 2021-11-02 |
| CN113592179B true CN113592179B (en) | 2024-10-29 |
Family
ID=78252866
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110873949.2A Active CN113592179B (en) | 2021-07-30 | 2021-07-30 | Predictive maintenance method, system and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113592179B (en) |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101833324A (en) * | 2010-05-14 | 2010-09-15 | 武汉理工大学 | Intelligent fault diagnosis system in tread extrusion process and diagnosis method thereof |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8498776B2 (en) * | 2009-11-17 | 2013-07-30 | GM Global Technology Operations LLC | Fault diagnosis and prognosis using diagnostic trouble code markov chains |
| CN110414774A (en) * | 2019-06-11 | 2019-11-05 | 华迪计算机集团有限公司 | A kind of O&M monitoring system and method |
| CN112631204A (en) * | 2020-12-14 | 2021-04-09 | 成都航天科工大数据研究院有限公司 | Health management platform, terminal, system and method for numerical control machine tool |
| CN112965871A (en) * | 2021-02-05 | 2021-06-15 | 深圳市道通科技股份有限公司 | Vehicle fault prompt information acquisition method and device and storage medium |
-
2021
- 2021-07-30 CN CN202110873949.2A patent/CN113592179B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101833324A (en) * | 2010-05-14 | 2010-09-15 | 武汉理工大学 | Intelligent fault diagnosis system in tread extrusion process and diagnosis method thereof |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113592179A (en) | 2021-11-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP3300005B1 (en) | Augmented reality presentation of an industrial environment | |
| CN1854706B (en) | Methods and systems for diagnosing machinery | |
| US8126679B2 (en) | Automatic remote monitoring and diagnostics system | |
| RU2636095C2 (en) | Method and system for monitoring status of plant group | |
| CN100555136C (en) | Unusual condition prevention method and system in the processing factory | |
| US7249284B2 (en) | Complex system serviceability design evaluation method and apparatus | |
| US11321616B2 (en) | Computer-based extraction of complex building operation rules for products and services | |
| CN102032115A (en) | System and method for analyzing reporting data | |
| CN102520717A (en) | Data presentation system for abnormal situation prevention in a process plant | |
| CN107850893B (en) | Generating events on an intelligent programmable logic controller using context information | |
| WO2018148029A1 (en) | System for analyzing machine data | |
| CN117055502A (en) | Intelligent control system based on Internet of things and big data analysis | |
| CN117289085A (en) | Multi-line fault analysis and diagnosis method and system | |
| Devaney et al. | Case-Based Reasoning for Gas Turbine Diagnostics. | |
| CN113592179B (en) | Predictive maintenance method, system and storage medium | |
| CN117367807A (en) | Method, system, equipment and medium for diagnosing faults of aero-engine | |
| CN109885978B (en) | Remote sensing ground station fault diagnosis system and method | |
| CN117395176A (en) | Network fault identification method, device, equipment and storage medium | |
| CN111212093A (en) | Data processing system and control device | |
| CN115146942B (en) | Electronic operation ticket system and operation method for hydropower plant | |
| CN112147974B (en) | Alarm root cause diagnosis method based on chemical process knowledge automation | |
| KR102306430B1 (en) | Industrial Process Equipment System Management Method using Cloud-based Intergrated Context-Aware Processing Engine | |
| CN114265891A (en) | Intelligent workshop system and method based on multi-source data fusion and storage medium | |
| CN111200315B (en) | Transformer substation monitoring background fault diagnosis system and method | |
| JP6898280B2 (en) | Knowledge creation system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant |