CN111255674B - System and method for detecting state of rotating mechanical equipment - Google Patents
System and method for detecting state of rotating mechanical equipment Download PDFInfo
- Publication number
- CN111255674B CN111255674B CN202010072399.XA CN202010072399A CN111255674B CN 111255674 B CN111255674 B CN 111255674B CN 202010072399 A CN202010072399 A CN 202010072399A CN 111255674 B CN111255674 B CN 111255674B
- Authority
- CN
- China
- Prior art keywords
- state
- vibration
- equipment
- data
- mechanical equipment
- 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
Images
Classifications
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F04—POSITIVE - DISPLACEMENT MACHINES FOR LIQUIDS; PUMPS FOR LIQUIDS OR ELASTIC FLUIDS
- F04B—POSITIVE-DISPLACEMENT MACHINES FOR LIQUIDS; PUMPS
- F04B51/00—Testing machines, pumps, or pumping installations
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E30/00—Energy generation of nuclear origin
Landscapes
- Engineering & Computer Science (AREA)
- Mechanical Engineering (AREA)
- General Engineering & Computer Science (AREA)
- Testing Of Devices, Machine Parts, Or Other Structures Thereof (AREA)
Abstract
The embodiment of the invention provides a system and a method for detecting the state of rotating mechanical equipment. The system comprises: system hardware and system software; wherein: the system hardware comprises a signal acquisition terminal, a signal transmission device and a data processing terminal; the signal acquisition terminal is used for acquiring state data of rotary mechanical equipment, the signal transmission equipment is used for transmitting the state data to the data processing terminal, and the data processing terminal is used for analyzing the state data to obtain a state result of the rotary mechanical equipment; the system software comprises a database, a background intelligent diagnosis model, a data analysis function, a software interface and a software interface module. The embodiment of the invention can complete modeling of the system and further fault diagnosis and early warning by separating from the physical structure of mechanical equipment and depending on the acquired vibration information.
Description
Technical Field
The invention relates to the technical field of fault detection, in particular to a system and a method for detecting the state of rotary mechanical equipment.
Background
In a nuclear power plant, a pump is a main rotating mechanical device of the nuclear power plant and is a heart device of the nuclear power plant, the nuclear power plant requires a main pump with long service life, can continuously and safely operate for a long time, has good sealing performance, and does not allow nuclear leakage, and because the strength of vibration and noise and main frequency components contained in the vibration and noise are closely related to the type, degree, position, reason and the like of a fault, effective fault diagnosis and early warning provided according to vibration information of the pump become inevitable development trends of the industry.
Generally, the equipment state is early-warned according to the vibration signal, and the fault reason is judged according to the monitoring information, so that technical personnel are often required to have higher professional level and field diagnosis experience, which causes the application of the fault diagnosis technology to be limited, and the following problems exist: the fault diagnosis is difficult, only aiming at a fault body, the expert experience and the theoretical model are relied on, the early warning capability of the novel fault is insufficient, the fault diagnosis rule is single, and the threshold value early warning is solely relied on.
Disclosure of Invention
The embodiment of the invention provides a system and a method for detecting the state of rotary mechanical equipment, which are used for solving the defects that the diagnosis form is single and the diagnosis is too dependent on the experience level of technicians in the prior art.
In a first aspect, an embodiment of the present invention provides a system for detecting a state of a rotating mechanical device, including:
system hardware and system software; wherein:
the system hardware comprises a signal acquisition terminal, a signal transmission device and a data processing terminal;
the signal acquisition terminal is used for acquiring state data of rotary mechanical equipment, the signal transmission equipment is used for transmitting the state data to the data processing terminal, and the data processing terminal is used for analyzing the state data to obtain a state result of the rotary mechanical equipment;
the system software comprises a database, a background intelligent diagnosis model, a data analysis function, a software interface and a software interface.
Preferably, the system software adopts a three-layer architecture, which specifically includes: a data layer, an intermediate layer and an application layer; wherein:
the data layer comprises equipment acquisition information, system basic information data and a system model algorithm, the equipment acquisition information is used for inputting the equipment acquisition data into the software system and reading in the off-line data, the system basic information data comprises equipment information, personnel information, parameter information and file information, and the system model algorithm is used for compiling and packaging the equipment acquisition data by adopting a preset programming language;
the middle layer is used for packaging a back-end method provided by the application server into a Web method, transmitting data through an HTTP (hyper text transport protocol), and providing a uniform interface for the client;
the application layer is used for providing a human-computer interaction interface, and is responsible for providing a plurality of types of software use authorization for other users through an administrator.
In a second aspect, an embodiment of the present invention provides a detection method for detecting a state of a rotating mechanical device, including:
acquiring real-time acquisition data of the rotary mechanical equipment;
calling a pre-trained equipment state monitoring model parameter to obtain an equipment state expected value and an equipment state index output by the equipment state monitoring model;
and inputting the equipment state expected value and the equipment state index into an equipment state early warning processing and fault diagnosis process to obtain fault early warning information or fault diagnosis information of the rotary mechanical equipment.
Preferably, the acquiring real-time acquisition data of the rotating mechanical device further includes: and constructing a fault diagnosis knowledge base.
Preferably, the constructing a fault diagnosis knowledge base specifically includes:
acquiring historical data;
digging data with a preset correlation degree from the historical data by combining a fuzzy correlation analysis method and a grey correlation analysis method to obtain vibration state correlation process parameters;
outputting a vibration abnormal definition based on a vibration abnormal fluctuation condition and a normal fluctuation condition according to expert knowledge, obtaining a vibration abnormal fluctuation reason through correlation analysis, and outputting a correlation relation between the vibration state correlation process parameters and the vibration abnormal definition;
training to obtain a system health state quantitative hierarchical model by adopting an artificial intelligence algorithm based on data drive based on the state information of the key nodes in the historical data and the incidence relation;
and obtaining the fault diagnosis knowledge base based on the incidence relation and the hierarchical model.
Preferably, the device state early warning processing and fault diagnosis process specifically includes:
analyzing the vibration state of the rotating mechanical equipment from a plurality of preset domains to obtain a primary selection vibration parameter set;
based on the primarily selected vibration parameter set, a preset optimization algorithm is adopted to obtain a carefully selected characteristic parameter set;
obtaining a vibration signal and a process parameter variation trend of the rotary mechanical equipment by adopting a qualitative trend analysis method according to the selected characteristic parameter set;
and predicting the fault trend of the rotary mechanical equipment by the hierarchical model based on the vibration signal and the process parameter variation trend and combining the fault diagnosis knowledge base.
Preferably, the device state early warning processing and fault diagnosis process further includes:
collecting technological parameters and current vibration parameters of the rotating mechanical equipment;
and obtaining fault information of the rotating mechanical equipment based on the process parameters and the current vibration parameters through the layered model.
Preferably, the rotating mechanical device comprises a pump.
According to the system and the method for detecting the state of the rotary mechanical equipment, provided by the embodiment of the invention, the modeling of the system and further fault diagnosis and early warning can be completed by separating from the physical structure of the mechanical equipment and depending on the collected vibration information.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.
Fig. 1 is an overall structure diagram of a system according to an embodiment of the present invention;
FIG. 2 is a diagram of a system software architecture provided by an embodiment of the present invention;
FIG. 3 is a flowchart of a method for detecting a status of a rotating machine according to an embodiment of the present invention;
FIG. 4 is a flowchart of the system operation provided by an embodiment of the present invention;
FIG. 5 is a flow chart of the construction of the data-driven-based artificial intelligence fault diagnosis knowledge base according to the embodiment of the present invention;
fig. 6 is a flowchart of a method for warning a vibration state of a rotating mechanical device according to an embodiment of the present invention;
fig. 7 is a flowchart of a fault diagnosis method for a rotating mechanical device according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
In order to solve the problems in the prior art, embodiments of the present invention provide a vibration state information management and intelligent diagnosis system and method for a rotating machine device, so as to know an operation state of the rotating machine in time and ensure safe and reliable operation of the rotating machine. Early warning, analysis and diagnosis of equipment deterioration or abnormal accidents are realized, and the safety, reliability and economy of equipment operation are improved.
Fig. 1 is an overall structure diagram of a system according to an embodiment of the present invention, as shown in fig. 1, including:
system hardware and system software; wherein:
the system hardware comprises a signal acquisition terminal, a signal transmission device and a data processing terminal;
the signal acquisition terminal is used for acquiring state data of rotary mechanical equipment, the signal transmission equipment is used for transmitting the state data to the data processing terminal, and the data processing terminal is used for analyzing the state data to obtain a state result of the rotary mechanical equipment;
the system software comprises a database, a background intelligent diagnosis model, a data analysis function, a software interface and a software interface.
Specifically, the early warning and intelligent diagnosis system for diagnosing the vibration state of the rotating mechanical equipment comprises two parts, namely system hardware and system software. The system hardware comprises a signal acquisition terminal (sensor), signal transmission equipment and a data processing terminal, wherein the signal acquisition terminal is used for acquiring state data of the rotary mechanical equipment, the signal transmission equipment is used for transmitting the state data to the data processing terminal, and the data processing terminal is used for analyzing the state data to obtain a state result of the rotary mechanical equipment; the system software mainly comprises a database, a background intelligent diagnosis model, a data analysis function, a software interface and other modules.
The embodiment of the invention can complete modeling of the system and further fault diagnosis and early warning by separating from the physical structure of mechanical equipment and depending on the acquired vibration information.
Based on the above embodiment, the system software adopts a three-layer architecture, which specifically includes: a data layer, an intermediate layer and an application layer; wherein:
the data layer comprises equipment acquisition information, system basic information data and a system model algorithm, the equipment acquisition information is used for inputting the equipment acquisition data into the software system and reading in the off-line data, the system basic information data comprises equipment information, personnel information, parameter information and file information, and the system model algorithm is used for compiling and packaging the equipment acquisition data by adopting a preset programming language;
the middle layer is used for packaging a back-end method provided by the application server into a Web method, transmitting data through an HTTP (hyper text transport protocol), and providing a uniform interface for the client;
the application layer is used for providing a human-computer interaction interface, and is responsible for providing a plurality of types of software use authorization for other users through an administrator.
Specifically, as shown in fig. 2, the software system adopts a three-layer structure of a data layer, a middle layer and an application layer to improve the stability, security, extensibility and adaptability of the system, wherein:
1) data layer
The data layer comprises equipment acquisition information, system basic information data and a system model algorithm. The method comprises the steps that firstly, data collected by equipment are directly input into a software system from the equipment, and secondly, offline data are read in; the system basic information data comprises information such as equipment information, personnel information, parameters, files and the like, and is imported and maintained by an administrator; and the software reserves a background algorithm interface which supports Python and MATLAB packages, and the specifically reserved interface is modified according to the user requirement. The background intelligent diagnosis model determines whether to rewrite and package in C + + language according to the running speed; the data can be stored in a system database server or directly provided for an application layer to use as required;
2) intermediate layer
The middle layer packages the back-end method provided by the application server into a Web method, transmits data through an HTTP protocol, and provides a uniform interface for the client. And the interface service layer schedules the function provided by the middle layer according to the response of the front-end interface. The layer is responsible for realizing intermediate functions and calculating intermediate data, and realizes intermediate functions such as data input and output, intelligent diagnosis model algorithm, data mining, database management, data visualization and the like;
3) application layer
The application layer is an interface for human-computer interaction between a user and the system, the system is provided with an administrator and is responsible for providing different types of software use authorization for other users, different role authorities are given to different user groups, the web-side software interface adopts regional and hierarchical display, the running state of equipment is visualized, a good human-computer interaction interface is provided, and the operation is simple.
Most of the operations provided by the embodiment of the invention can be directly completed on the software interface, and the method has the advantages of simple operation, good human-computer interaction and small workload.
Fig. 3 is a flowchart of a detection method for detecting a state of a rotating mechanical device according to an embodiment of the present invention, as shown in fig. 3, including:
s1, acquiring real-time acquisition data of the rotating mechanical equipment;
s2, calling pre-trained equipment state monitoring model parameters to obtain an equipment state expected value and an equipment state index output by the equipment state monitoring model;
and S3, inputting the equipment state expected value and the equipment state index into an equipment state early warning processing and fault diagnosis process to obtain fault early warning information or fault diagnosis information of the rotary mechanical equipment.
Specifically, the overall working flow of the system is as shown in fig. 4, the system firstly performs real-time data input (acquisition) of equipment monitoring parameters, displays vibration real-time monitoring and running states, then enters a data accuracy discrimination link, performs reconstruction and alarm if abnormal measurement data is detected, then calls equipment state monitoring model parameters after successful training to perform equipment state expected value calculation and equipment state index calculation, and finally enters an equipment state early warning processing flow. The equipment state early warning processing flow specifically comprises equipment state monitoring and early warning, parameter trend analysis, and calling a fault mode library to automatically generate a fault diagnosis list and an equipment state monitoring report so as to realize closed-loop management of equipment state monitoring. And the related information of the fault diagnosis list is completed and recorded by equipment diagnosis specialists, equipment point inspection or equipment maintenance personnel. The equipment state monitoring report is convenient for production managers, equipment spot inspection or maintainers to inquire the overall condition of the health state of the equipment, and potential hidden dangers or potential faults exist. After the equipment generates early warning, equipment maintenance personnel, special workers and the like perform further analysis and diagnosis according to suspected fault information of the system and report leaders to generate a fault diagnosis list, the fault diagnosis list explains fault names, components, possible reasons and processing modes of faults, information such as deviated parameters and related attributes and the like, the equipment maintenance personnel perform defect elimination or fault processing according to the fault diagnosis list, equipment accountants perform maintenance quality inspection and fill in fault processing result feedback, and meanwhile, the diagnosis process records can be quickly added into a fault mode library to form standard diagnosis experience. And if the problem which is not solved exists, the fault diagnosis method can be used for filling in a diagnosis list to arrange a maintenance plan or transferring to the next fault diagnosis cycle.
The embodiment of the invention adopts the artificial intelligence fault diagnosis method based on data driving, can carry out fault analysis and diagnosis only according to the data acquired by the sensor, overcomes the limitation of the traditional fault diagnosis method based on an analysis model and a qualitative model, and does not need to consider the physical structure of mechanical equipment any more.
Based on any of the above embodiments, fig. 5 is a flow chart for constructing a data-driven-based artificial intelligence fault diagnosis knowledge base according to an embodiment of the present invention, as shown in fig. 5, including:
101, acquiring historical data;
102, mining data with a preset correlation degree from the historical data by combining a fuzzy correlation analysis method and a grey correlation analysis method to obtain vibration state correlation process parameters;
103, outputting a vibration abnormal definition based on a vibration abnormal fluctuation condition and a normal fluctuation condition according to expert knowledge, obtaining a vibration abnormal fluctuation reason through relevance analysis, and outputting a relevance relation between the vibration state relevant process parameters and the vibration abnormal definition;
104, training to obtain a system health state quantitative hierarchical model by adopting an artificial intelligence algorithm based on data drive based on the state information of the key nodes in the historical data and the incidence relation;
and 105, obtaining the fault diagnosis knowledge base based on the incidence relation and the hierarchical model.
Specifically, the fault diagnosis knowledge base is the basis of vibration state early warning and fault diagnosis of the rotating mechanical equipment. After the real-time data collected by the sensor is subjected to processing such as interference prevention and preliminary calculation, the real-time data is compared with data in a knowledge base, and vibration state early warning and fault diagnosis of the department can be realized after analysis.
In step 101, firstly, a large amount of historical data is obtained;
in step 102, a fuzzy association analysis method (FRA method) and a gray association analysis method (GRA method) are combined to mine data with a high association degree from the multi-source data, and process parameters (the process parameters include voltage, current, pressure, temperature, motor current, motor coil temperature, bearing temperature, vibration value, inlet and outlet medium temperature and flow rate of equipment) closely related to the vibration state are obtained. Processing fuzzy information through an FRA method to obtain objective interval values from multi-source data; processing whitening information through a GRA method to obtain grey correlation degree sequencing among multiple factors;
in step 103, according to expert knowledge, a reasonable vibration abnormal definition is given for the abnormal vibration fluctuation condition and the normal vibration condition, the reason causing the abnormal vibration fluctuation is found out through correlation analysis, and the relation between the process parameter change and the vibration state is summarized;
in step 104, according to the state information of key nodes in the system historical data and the result of step 103, fusing a multi-source information fusion technology and a Bayesian network, providing an improved dynamic Bayesian network method, solving the problem that the information provided by the system has ambiguity and incompleteness, obtaining the fault occurrence probability of different nodes of the system based on the improved dynamic Bayesian network, specifically combining the multi-source information fusion technology and the Bayesian network to form the improved dynamic Bayesian network method, specifically regarding a plurality of fault characteristics of the extracted vibration signal as multi-source information from a plurality of different sensors, regarding each fault characteristic as coming from one sensor, and performing denoising and fusion on the plurality of fault characteristics by adopting the multi-element fusion technology to obtain clearer and more accurate fault characteristics; then, aiming at different nodes of the system, a dynamic Bayesian network is adopted for fault analysis, and the probability of fault characteristic occurrence is counted; the method comprises the following steps of splitting components of a pump and an auxiliary system related to the pump, and training a hierarchical model with quantified system health state, namely a fault diagnosis model;
in step 105, a failure diagnosis knowledge base is formed based on the results of steps 103 and 104, and the history data is dynamically updated based on the newly stored data.
The embodiment of the invention integrates a multi-source information fusion technology and a Bayesian network, provides an improved dynamic Bayesian network method, solves the problems that information provided by a system has ambiguity and incompleteness, effectively solves the problem of dependence of a fusion algorithm on prior information, can analyze and select a proper robust and accurate algorithm according to prior data of a pump vibration state system, adopts a data mining technology, combines a fuzzy association analysis method and a gray association analysis method, finds out the existing deficiency and improves the deficiency by systematically comparing an actual result of data mining with a predicted value, and enables the model to be more perfect.
Based on any of the above embodiments, fig. 6 is a flowchart of a method for warning a vibration state of a rotating mechanical device according to an embodiment of the present invention, and as shown in fig. 6, the process of warning a vibration state of a device and diagnosing a fault specifically includes:
201, analyzing the vibration state of the rotating mechanical equipment from a plurality of preset domains to obtain a primary selection vibration parameter set;
202, obtaining a selected characteristic parameter set by adopting a preset optimization algorithm based on the initially selected vibration parameter set;
203, obtaining a vibration signal and a process parameter variation trend of the rotary mechanical equipment by adopting a qualitative trend analysis method according to the selected characteristic parameter set;
and 204, predicting the fault trend of the rotary mechanical equipment by the hierarchical model based on the vibration signal and the process parameter variation trend and combining the fault diagnosis knowledge base.
Specifically, in step 201, a characteristic parameter set of the pump is extracted according to the vibration data of the pump, which is the first step of state warning and fault diagnosis. The performance of the pump can be confirmed by judging whether the characteristic parameter deviates from the normal value range. The design analyzes the vibration state of the rotating machine from a plurality of angles of time domain, frequency domain and time-frequency domain to obtain a primary selection vibration parameter set. Through time domain analysis, characteristic parameters such as signal mean value, mean square deviation, kurtosis value and peak value and the characteristics of related calculated values at different moments are revealed. Mechanical equipment failure can not only be reflected in the time domain characteristics, but also cause frequency domain characteristics to change. When the vibration signal is subjected to time domain analysis, the time domain characteristics of some signals are similar, but the signals cannot belong to the same working condition, and the vibration signal is only suitable for a linear system and also needs to be subjected to frequency domain analysis. Through Fourier transform, the dynamic signal is transformed from a time domain to a frequency domain, and the complex vibration signal is decomposed into a known sine wave signal for analysis, so that the relation between the signal structure and the frequency signal amplitude in the frequency domain is reflected. However, the vibration signal of the mechanical equipment is often a non-stationary signal, the working condition state of the mechanical equipment can change at any time, the fourier transform is directed to the whole signal, so that some local features of the vibration signal can be lost, and meanwhile, the frequency domain analysis based on the fourier transform is lack of self-adaptive capacity for different vibration signal faults. Therefore, the advantages of time domain analysis and frequency domain analysis need to be combined, a proper wavelet transform function is selected, and meanwhile, vibration signal characteristics are extracted from the time domain and the frequency domain, so that the signal characteristics are extracted more comprehensively. However, wavelet analysis needs to select a proper wavelet basis function in advance, wavelets cannot be transformed adaptively according to the characteristics of vibration signals, different wavelets have different sensitivity degrees to noise, and some wavelet basis functions have no good anti-noise capability. Therefore, the vibration state of the rotating machine needs to be extracted and analyzed from multiple angles of time domain, frequency domain and time-frequency domain so as to more comprehensively know the equipment state;
in step 202, since the sensitivity evaluation of the characteristic parameters is used for improving the sensitivity of the characteristic parameters in the to-be-selected fault characteristic set to the fault, a characteristic parameter set with high sensitivity is selected from the characteristic parameter set extracted in step 201, and a genetic algorithm is adopted as an optimization algorithm to select the characteristic parameters to obtain a selected characteristic parameter set;
in step 203, according to the selected characteristic parameter set, referring to the variation characteristic trend of the historical data of the characteristic parameters, carrying out qualitative trend analysis on the selected characteristic parameters to obtain the vibration signal and the process parameter variation trend of the pump, obtaining the future running state of the pump, comparing the future running state of the pump with the fault state in the fault diagnosis knowledge base, and judging whether the pump has a fault trend;
in step 204, according to the current operating state and the future operating state of the pump, a system hierarchical model is combined, reverse derivation is performed, and the fault occurrence probability of different nodes of the system is predicted.
The embodiment of the invention can judge whether the potential fault exists or not by diagnosing the existing fault and comparing the actual signal with the ideal signal, and can analyze and process the vibration information of the pump in an all-around and multi-level manner by adopting a data analysis method combining time domain analysis, frequency domain analysis and time frequency analysis, thereby further enhancing the fault diagnosis capability; the method has certain self-learning capability of the machine, namely for given new vibration abnormity and fault types, the accuracy of the model is over 95 percent through self-learning of original data in one month, vibration state early warning and intelligent diagnosis.
Based on any of the above embodiments, fig. 7 is a flowchart of a fault diagnosis method for a rotating mechanical device according to an embodiment of the present invention, and as shown in fig. 7, the device state early warning processing and fault diagnosis process further includes:
301, collecting technological parameters and current vibration parameters of the rotating mechanical equipment;
302, obtaining fault information of the rotating mechanical equipment based on the process parameters and the current vibration parameters through the layered model.
Specifically, in step 301, when an actual fault is determined, unlike the fault early warning process, the process parameters and the current vibration parameters of the pump are collected;
in step 302, fault information of the pump is obtained based on the process parameters and the current vibration parameters obtained in step 301, or through a layered model.
The embodiment of the invention has stronger adaptability to novel faults by means of the self-learning function of the machine, provides powerful guarantee for correct fault diagnosis and has strong adaptability to the novel faults.
The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (3)
1. A method for detecting a condition of a rotating machine, comprising:
acquiring real-time acquisition data of the rotary mechanical equipment;
calling pre-trained equipment state monitoring model parameters to obtain equipment state expected values and equipment state indexes output by the equipment state monitoring model;
inputting the equipment state expected value and the equipment state index into an equipment state early warning processing and fault diagnosis process to obtain fault early warning information or fault diagnosis information of the rotary mechanical equipment;
the acquiring real-time acquisition data of the rotating mechanical equipment comprises the following steps: constructing a fault diagnosis knowledge base;
the constructing of the fault diagnosis knowledge base specifically comprises the following steps:
acquiring historical data;
combining a fuzzy correlation analysis method and a grey correlation analysis method, and excavating data with a preset correlation degree from the historical data to obtain vibration state correlation process parameters;
outputting a vibration abnormal definition based on a vibration abnormal fluctuation condition and a normal fluctuation condition according to expert knowledge, obtaining a vibration abnormal fluctuation reason through correlation analysis, and outputting a correlation relation between the vibration state correlation process parameters and the vibration abnormal definition;
training to obtain a system health state quantitative hierarchical model by adopting an artificial intelligence algorithm based on data drive based on the state information of the key nodes in the historical data and the incidence relation;
obtaining the fault diagnosis knowledge base based on the incidence relation and the hierarchical model;
the device state early warning processing and fault diagnosis process specifically comprises the following steps:
analyzing the vibration state of the rotating mechanical equipment from a plurality of preset domains to obtain a primary selection vibration parameter set;
based on the primarily selected vibration parameter set, a preset optimization algorithm is adopted to obtain a carefully selected characteristic parameter set;
obtaining a vibration signal and a process parameter variation trend of the rotary mechanical equipment by adopting a qualitative trend analysis method according to the selected characteristic parameter set;
and predicting the fault trend of the rotary mechanical equipment by the hierarchical model based on the vibration signal and the process parameter variation trend and combining the fault diagnosis knowledge base.
2. A detection method for detecting a state of a rotary machine according to claim 1, wherein the device state warning process and fault diagnosis process further includes:
collecting technological parameters and current vibration parameters of the rotating mechanical equipment;
and obtaining fault information of the rotating mechanical equipment based on the process parameters and the current vibration parameters through the layered model.
3. A detection method for detecting a state of a rotating machine according to any one of claims 1 to 2, wherein said rotating machine comprises a pump.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010072399.XA CN111255674B (en) | 2020-01-21 | 2020-01-21 | System and method for detecting state of rotating mechanical equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010072399.XA CN111255674B (en) | 2020-01-21 | 2020-01-21 | System and method for detecting state of rotating mechanical equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111255674A CN111255674A (en) | 2020-06-09 |
| CN111255674B true CN111255674B (en) | 2022-08-09 |
Family
ID=70945609
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010072399.XA Active CN111255674B (en) | 2020-01-21 | 2020-01-21 | System and method for detecting state of rotating mechanical equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111255674B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118839597A (en) * | 2020-08-11 | 2024-10-25 | 成都一通密封股份有限公司 | Data processing module and method of sealing device for pump |
| CN113159088B (en) * | 2021-01-07 | 2022-07-15 | 中国地质大学（武汉） | Fault monitoring and diagnosis method based on multi-feature fusion and width learning |
| CN114201848A (en) * | 2021-06-23 | 2022-03-18 | 核动力运行研究所 | Correlation analysis method for main pump vibration data and process parameters |
| CN113988173A (en) * | 2021-10-26 | 2022-01-28 | 中国华能集团清洁能源技术研究院有限公司 | Fault diagnosis method, system, equipment and storage medium based on qualitative trend analysis and five-state Bayesian network |
| CN115469643A (en) * | 2022-09-15 | 2022-12-13 | 中国核动力研究设计院 | Nuclear power station rotating machinery health management method, system and medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101135601A (en) * | 2007-10-18 | 2008-03-05 | 北京英华达电力电子工程科技有限公司 | Rotating machinery vibrating failure diagnosis device and method |
| CN101799320A (en) * | 2010-01-27 | 2010-08-11 | 北京信息科技大学 | Fault prediction method and device thereof for rotation equipment |
| KR101281897B1 (en) * | 2012-05-29 | 2013-07-03 | 주식회사 현대케피코 | Performance tester on actual vehicle condition for multi purpose actuator |
| KR20180033844A (en) * | 2016-09-26 | 2018-04-04 | 현대로보틱스주식회사 | Fault Diagnosis System of Industrial Robot |
| CN108731923A (en) * | 2018-03-28 | 2018-11-02 | 中控技术（西安）有限公司 | A kind of fault detection method and device of rotating machinery |
-
2020
- 2020-01-21 CN CN202010072399.XA patent/CN111255674B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101135601A (en) * | 2007-10-18 | 2008-03-05 | 北京英华达电力电子工程科技有限公司 | Rotating machinery vibrating failure diagnosis device and method |
| CN101799320A (en) * | 2010-01-27 | 2010-08-11 | 北京信息科技大学 | Fault prediction method and device thereof for rotation equipment |
| KR101281897B1 (en) * | 2012-05-29 | 2013-07-03 | 주식회사 현대케피코 | Performance tester on actual vehicle condition for multi purpose actuator |
| KR20180033844A (en) * | 2016-09-26 | 2018-04-04 | 현대로보틱스주식회사 | Fault Diagnosis System of Industrial Robot |
| CN108731923A (en) * | 2018-03-28 | 2018-11-02 | 中控技术（西安）有限公司 | A kind of fault detection method and device of rotating machinery |
Non-Patent Citations (1)
| Title |
|---|
| 基于虚拟仪器的远程监测与诊断系统研究及开发;肖高权;《中国优秀硕士学位论文全文数据库 信息科技辑》;20120315(第03期);正文第1-80页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111255674A (en) | 2020-06-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111255674B (en) | System and method for detecting state of rotating mechanical equipment | |
| CN110647133B (en) | Rail transit equipment state detection maintenance method and system | |
| CN113077172A (en) | Equipment state trend analysis and fault diagnosis method | |
| CN110766277B (en) | Health assessment and diagnosis system and mobile terminal for nuclear industry field | |
| Galar et al. | Context awareness for maintenance decision making: A diagnosis and prognosis approach | |
| JP5179086B2 (en) | Industrial process monitoring method and monitoring system | |
| CN116862442A (en) | Intelligent equipment management method and system based on big data analysis | |
| US10963797B2 (en) | System for analyzing machine data | |
| CN110081927A (en) | Ship machine equipment failure prediction method, device, system and storage medium | |
| CN104615121A (en) | Method and system for train fault diagnosis | |
| CN116670608A (en) | Hybrid ensemble method for predictive modeling of Internet of things | |
| CN118092242A (en) | Industrial robot state monitoring method and system of distributed intelligent network | |
| Wang | Key techniques in intelligent predictive maintenance (IPdM)–a framework of intelligent faults diagnosis and prognosis system (IFDaPS) | |
| CN111753603A (en) | EDG fault diagnosis system of emergency generator set | |
| CN110765633A (en) | Intelligent management method and device for power device | |
| CN118408583B (en) | Encoder fault diagnosis method and system | |
| Galar | Context-driven Maintenance: an eMaintenance approach | |
| CN118192370A (en) | Special equipment safety monitoring management system | |
| CN117435883A (en) | Method and system for predicting equipment faults based on digital twinning | |
| Liu et al. | Machine health monitoring and prognostication via vibration information | |
| Kumar et al. | An expert system for predictive maintenance of mining excavators and its various forms in open cast mining | |
| WO2022175767A1 (en) | Equipment fault detection system using artificial intelligence(icms) | |
| CN117287640B (en) | Early warning method, device, equipment and storage medium for water supply risk | |
| CN117589444B (en) | Wind driven generator gear box fault diagnosis method based on federal learning | |
| CN118641942A (en) | Visual motor life online monitoring method and 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 | ||
| CB02 | Change of applicant information |
Address after: 430223 room 11, 15 / F, R & D building, No. 13-1, University Park, Donghu New Technology Development Zone, Wuhan, Hubei Province Applicant after: Wuhan ruilaibao Technology Co.,Ltd. Address before: Floor 15, block B, building 1, modern service industry base, Huagong science and Technology Park, No.13-1, daxueyuan Road, Donghu New Technology Development Zone, Wuhan City, Hubei Province, 430000 Applicant before: WUHAN RELABO ENERGY TECHNOLOGY Co.,Ltd. |
|
| CB02 | Change of applicant information | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20230227 Address after: 430075 No.11, 15th floor, R & D building, No.1 modern service industry base, Science Park, Huazhong University of science and technology, No.13-1 University Park, Donghu New Technology Development Zone, Wuhan City, Hubei Province Patentee after: Wuhan ruilaibao Technology Co.,Ltd. Patentee after: WUHAN University Address before: 430223 room 11, 15 / F, R & D building, No. 13-1, University Park, Donghu New Technology Development Zone, Wuhan, Hubei Province Patentee before: Wuhan ruilaibao Technology Co.,Ltd. |
|
| TR01 | Transfer of patent right |