[go: up one dir, main page]
More Web Proxy on the site http://driver.im/

CN112810772B - Ship equipment fault diagnosis method and equipment based on multi-dimensional feature knowledge extraction - Google Patents

Ship equipment fault diagnosis method and equipment based on multi-dimensional feature knowledge extraction Download PDF

Info

Publication number
CN112810772B
CN112810772B CN202110139145.XA CN202110139145A CN112810772B CN 112810772 B CN112810772 B CN 112810772B CN 202110139145 A CN202110139145 A CN 202110139145A CN 112810772 B CN112810772 B CN 112810772B
Authority
CN
China
Prior art keywords
fault
ship
fault diagnosis
data
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
Application number
CN202110139145.XA
Other languages
Chinese (zh)
Other versions
CN112810772A (en
Inventor
程鲲鹏
吉承成
刘新辉
戴林
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Jiangsu Yuanwang Instrument Group Co ltd
Original Assignee
Jiangsu Yuanwang Instrument Group Co ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Jiangsu Yuanwang Instrument Group Co ltd filed Critical Jiangsu Yuanwang Instrument Group Co ltd
Priority to CN202110139145.XA priority Critical patent/CN112810772B/en
Publication of CN112810772A publication Critical patent/CN112810772A/en
Application granted granted Critical
Publication of CN112810772B publication Critical patent/CN112810772B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • BPERFORMING OPERATIONS; TRANSPORTING
    • B63SHIPS OR OTHER WATERBORNE VESSELS; RELATED EQUIPMENT
    • B63BSHIPS OR OTHER WATERBORNE VESSELS; EQUIPMENT FOR SHIPPING 
    • B63B79/00Monitoring properties or operating parameters of vessels in operation
    • B63B79/10Monitoring properties or operating parameters of vessels in operation using sensors, e.g. pressure sensors, strain gauges or accelerometers
    • BPERFORMING OPERATIONS; TRANSPORTING
    • B63SHIPS OR OTHER WATERBORNE VESSELS; RELATED EQUIPMENT
    • B63BSHIPS OR OTHER WATERBORNE VESSELS; EQUIPMENT FOR SHIPPING 
    • B63B79/00Monitoring properties or operating parameters of vessels in operation
    • B63B79/20Monitoring properties or operating parameters of vessels in operation using models or simulation, e.g. statistical models or stochastic models
    • BPERFORMING OPERATIONS; TRANSPORTING
    • B63SHIPS OR OTHER WATERBORNE VESSELS; RELATED EQUIPMENT
    • B63BSHIPS OR OTHER WATERBORNE VESSELS; EQUIPMENT FOR SHIPPING 
    • B63B79/00Monitoring properties or operating parameters of vessels in operation
    • B63B79/30Monitoring properties or operating parameters of vessels in operation for diagnosing, testing or predicting the integrity or performance of vessels

Landscapes

  • Chemical & Material Sciences (AREA)
  • Engineering & Computer Science (AREA)
  • Combustion & Propulsion (AREA)
  • Mechanical Engineering (AREA)
  • Ocean & Marine Engineering (AREA)
  • Physics & Mathematics (AREA)
  • Probability & Statistics with Applications (AREA)
  • Testing And Monitoring For Control Systems (AREA)

Abstract

The application provides a ship equipment fault diagnosis method and equipment based on multi-dimensional feature knowledge extraction, and relates to the technical field of ship equipment. The method comprises the steps of obtaining monitoring data of target ship equipment; acquiring a fault diagnosis result of the target ship equipment according to the monitoring data of the target ship equipment and the ship fault diagnosis knowledge map, wherein the fault diagnosis result comprises the following steps: the method and the device have the advantages that the fault equipment identification, the initial fault reason and the fault processing suggestion are carried out, the ship fault diagnosis knowledge graph takes the ship equipment as the top point, the relation among the ship equipment is established at the same side, and by applying the method and the device, the automatic diagnosis of the fault of the ship equipment can be realized, the labor intensity of ship equipment detection personnel is reduced, the fault diagnosis result is not limited by the detection level of the detection personnel, and the accuracy of the fault diagnosis result can be improved.

Description

Ship equipment fault diagnosis method and equipment based on multi-dimensional feature knowledge extraction
Technical Field
The application relates to the technical field of ships, in particular to a ship equipment fault diagnosis method and equipment based on multi-dimensional feature knowledge extraction.
Background
As an artificial transportation tool running in geographic water, the ship industry develops rapidly, and the ship has profound significance in aspects of accelerating ocean development pace, maintaining national ocean rights and interests, guaranteeing water transportation safety, maintaining national economic growth, guaranteeing national defense safety and the like.
At present, when fault detection and diagnosis are carried out on ship equipment, detection personnel mainly carry out fault detection based on the current state by adopting a traditional method of after-fault maintenance or regular maintenance based on manual troubleshooting.
However, the existing fault detection method completely depends on the detection level of detection personnel, and has the problem of low accuracy.
Disclosure of Invention
The present application aims to provide a ship equipment fault diagnosis method and equipment based on multidimensional feature knowledge extraction, which can improve the accuracy of fault diagnosis results, aiming at the defects in the prior art.
In order to achieve the above purpose, the technical solutions adopted in the embodiments of the present application are as follows:
in a first aspect, the invention provides a ship equipment fault diagnosis method based on multi-dimensional feature knowledge extraction, which comprises the following steps:
acquiring monitoring data of target ship equipment;
acquiring a fault diagnosis result of the target ship equipment according to the monitoring data of the target ship equipment and a ship fault diagnosis knowledge map, wherein the fault diagnosis result comprises the following steps: the ship fault diagnosis knowledge graph is constructed by taking a plurality of ship equipment as vertexes and taking the relation between the ship equipment as an edge.
In an alternative embodiment, the method further comprises:
obtaining historical monitoring data of a plurality of the ship devices, wherein the historical monitoring data comprises: ship equipment identification, fault reason and fault processing suggestion;
obtaining the relation among a plurality of ship devices according to the historical monitoring data;
and constructing the ship fault diagnosis knowledge graph according to the relationship among the plurality of ship equipment.
In an optional embodiment, the obtaining a relationship between a plurality of pieces of marine equipment according to the historical monitoring data includes:
according to the historical monitoring data, at least one of the following characteristic data is extracted: structured data, semi-structured data, unstructured data;
constructing a triple according to the characteristic data, wherein the triple comprises: the method comprises the following steps of (1) identifying ship equipment, belonging membership values of fault reasons, fault reasons and fault processing suggestions, wherein the membership values are used for indicating the probability that characteristic data belong to the fault reasons;
and obtaining the relationship among the plurality of ship devices according to the triples.
In an alternative embodiment, the method further comprises:
and acquiring a membership value of each fault reason to which the characteristic data belongs according to a preset fuzzy algorithm.
In an optional embodiment, the obtaining a fault diagnosis result of the target ship equipment according to the monitoring data of the target ship equipment and the ship fault diagnosis knowledge graph includes:
extracting target characteristic data of the monitoring data of the target ship equipment, wherein the target characteristic data comprises at least one of the following data: structured data, semi-structured data, unstructured data;
according to the target characteristic data and all membership values in the ship fault diagnosis knowledge map, carrying out optimal path search on the ship fault diagnosis knowledge map based on an optimal path search algorithm to obtain an optimal path search result;
and obtaining a fault diagnosis result according to the optimal path search result.
In an optional embodiment, after obtaining the fault diagnosis result of the target ship equipment according to the monitoring data of the target ship equipment and the ship fault diagnosis knowledge graph, the method further includes:
and carrying out co-occurrence analysis on the fault diagnosis result according to a co-occurrence matrix to obtain a fault accompanying conclusion, wherein the fault accompanying conclusion is used for indicating the probability of the co-occurrence of other fault reasons when the initial fault reason occurs, and the co-occurrence matrix is used for indicating the probability of the co-occurrence of all fault reasons.
In an optional embodiment, before the performing the co-occurrence analysis on the fault diagnosis result according to the co-occurrence matrix and obtaining the fault accompanying conclusion, the method further includes:
constructing a citation network according to the historical monitoring data of the ship equipment, wherein the citation network comprises fault reasons and fault times corresponding to the historical monitoring data of the ship equipment;
and acquiring the co-occurrence matrix according to the citation network.
In a second aspect, the present invention provides a ship equipment fault diagnosis apparatus based on multidimensional feature knowledge extraction, including:
the acquisition module is used for acquiring monitoring data of the target ship equipment;
the diagnosis module is used for acquiring a fault diagnosis result of the target ship equipment according to the monitoring data of the target ship equipment and the ship fault diagnosis knowledge map, and the fault diagnosis result comprises: the method comprises the steps of fault equipment identification, initial fault reasons and fault processing suggestions, wherein the ship fault diagnosis knowledge graph is constructed by taking a plurality of ship equipment as vertexes and taking the relation among the ship equipment as an edge.
In an alternative embodiment, the failure diagnosis apparatus further includes: a building module, configured to obtain historical monitoring data of a plurality of pieces of marine equipment, where the historical monitoring data includes: ship equipment identification, fault reason and fault processing suggestion;
obtaining the relation among a plurality of ship devices according to the historical monitoring data;
and constructing the ship fault diagnosis knowledge graph according to the relationship among the plurality of ship equipment.
In an optional embodiment, the building module is specifically configured to extract, according to the historical monitoring data, at least one of the following feature data: structured data, semi-structured data, unstructured data;
constructing a triple according to the characteristic data, wherein the triple comprises: the method comprises the following steps of (1) identifying ship equipment, belonging membership values of fault reasons, fault reasons and fault processing suggestions, wherein the membership values are used for indicating the probability that characteristic data belong to the fault reasons;
and acquiring the relationship among the plurality of ship devices according to the triples.
In an optional embodiment, the building module is further configured to obtain a membership value of each fault cause to which the feature data belongs according to a preset fuzzy algorithm.
In an optional embodiment, the diagnostic module is specifically configured to extract target feature data of the monitoring data of the target ship device, where the target feature data includes at least one of: structured data, semi-structured data, unstructured data;
according to the target characteristic data and all membership values in the ship fault diagnosis knowledge map, carrying out optimal path search on the ship fault diagnosis knowledge map based on an optimal path search algorithm to obtain an optimal path search result;
and obtaining a fault diagnosis result according to the optimal path search result.
In an optional embodiment, the diagnosis module is further configured to perform co-occurrence analysis on the fault diagnosis result according to a co-occurrence matrix, and obtain a fault co-occurrence conclusion, where the fault co-occurrence conclusion is used to indicate probabilities that other fault causes occur concomitantly when an initial fault cause occurs, and the co-occurrence matrix is used to indicate a probability that each fault cause occurs together.
In an optional embodiment, the diagnostic module is further configured to construct a citation network according to historical monitoring data of the ship equipment, where the citation network includes fault reasons and fault times corresponding to the historical monitoring data of the ship equipment; and acquiring the co-occurrence matrix according to the citation network.
In a third aspect, the present invention provides an electronic device comprising: the system comprises a processor, a storage medium and a bus, wherein the storage medium stores machine-readable instructions executable by the processor, when an electronic device runs, the processor and the storage medium communicate through the bus, and the processor executes the machine-readable instructions to execute the steps of the ship equipment fault diagnosis method based on multi-dimensional feature knowledge extraction according to any one of the preceding embodiments.
In a fourth aspect, the present invention provides a storage medium, wherein the storage medium stores a computer program, and the computer program is executed by a processor to execute the steps of the ship equipment fault diagnosis method based on multi-dimensional feature knowledge extraction according to any one of the foregoing embodiments.
The beneficial effect of this application is:
in the ship equipment fault diagnosis method and equipment based on multi-dimensional feature knowledge extraction, monitoring data of target ship equipment are acquired; acquiring a fault diagnosis result of the target ship equipment according to the monitoring data of the target ship equipment and the ship fault diagnosis knowledge map, wherein the fault diagnosis result comprises the following steps: the ship fault diagnosis knowledge graph takes a plurality of ship equipment as vertexes, and the relation among the ship equipment is established at the same time.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are required to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present application and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained from the drawings without inventive effort.
Fig. 1 is a schematic flowchart of a ship equipment fault diagnosis method based on multi-dimensional feature knowledge extraction according to an embodiment of the present application;
fig. 2 is a schematic flowchart of another ship equipment fault diagnosis method based on multi-dimensional feature knowledge extraction according to an embodiment of the present application;
fig. 3 is a schematic flowchart of a further ship equipment fault diagnosis method based on multi-dimensional feature knowledge extraction according to an embodiment of the present application;
fig. 4 is a schematic flowchart of another ship equipment fault diagnosis method based on multi-dimensional feature knowledge extraction according to an embodiment of the present application;
FIG. 5 is a schematic diagram of a ship fault diagnosis knowledge graph provided by an embodiment of the present application;
fig. 6 is a schematic flowchart of a further ship equipment fault diagnosis method based on multi-dimensional feature knowledge extraction according to an embodiment of the present application;
fig. 7 is a schematic flowchart of another ship equipment fault diagnosis method based on multidimensional feature knowledge extraction according to the embodiment of the present application;
FIG. 8 is a schematic diagram of a citation network provided by an embodiment of the present application;
fig. 9 is a functional module schematic diagram of a ship equipment fault diagnosis device based on multi-dimensional feature knowledge extraction according to an embodiment of the present application;
fig. 10 is a functional module schematic diagram of another ship equipment fault diagnosis device based on multi-dimensional feature knowledge extraction according to an embodiment of the present application;
fig. 11 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some embodiments of the present application, but not all embodiments. The components of the embodiments of the present application, as generally described and illustrated in the figures herein, could be arranged and designed in a wide variety of different configurations.
Thus, the following detailed description of the embodiments of the present application, as presented in the figures, is not intended to limit the scope of the claimed application, but is merely representative of selected embodiments of the application. 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 application.
It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, it need not be further defined and explained in subsequent figures.
Fig. 1 is a schematic flowchart of a ship equipment fault diagnosis method based on multidimensional feature knowledge extraction according to an embodiment of the present application, where an execution subject of the method may be an electronic device that can perform data processing, such as a computer, a server, and a processor, and as shown in fig. 1, the method may include:
s101, acquiring monitoring data of target ship equipment.
The target ship equipment may include, but is not limited to, rudder equipment, anchor equipment, mooring equipment, towing equipment, cargo handling equipment, life saving equipment, closing equipment, piping, outfitting, fire fighting equipment, ventilation and air conditioning equipment, and the like, and may be different according to the type of the ship equipment, and is not limited herein.
Optionally, the monitoring data of the target ship device may be obtained based on a monitoring system of the ship device, the monitoring system may include multiple monitoring devices, the obtained monitoring data may be multi-dimensional feature data, the multi-dimensional feature data may be data acquired from multiple dimensions, optionally, the multiple dimensions may be understood as different monitoring locations of the target ship device, or may be understood as different types of monitoring data (for example, structured data, semi-structured data, unstructured data, and the like) of the same monitoring location, which is not limited herein. For example, the monitoring data may include, but is not limited to, multidimensional characteristic data such as temperature (deg.c), pressure (MPa), current (mA), vibration acceleration (Hz), vibration displacement (mm), noise, oil particle size, and the like, and the monitoring data may be collected by the corresponding sensor unit according to different monitoring locations, which is not limited herein. In some embodiments, the acquired monitoring data may be imported into the electronic device by way of file import.
S102, acquiring a fault diagnosis result of the target ship equipment according to the monitoring data of the target ship equipment and the ship fault diagnosis knowledge graph.
Wherein, the fault diagnosis result comprises: the method comprises the following steps that fault equipment identification, initial fault reasons and fault processing suggestions are carried out, a ship fault diagnosis knowledge graph takes a plurality of ship equipment as vertexes, and the relation among the ship equipment is established at the same side, so that the ship fault diagnosis knowledge graph can integrate corresponding fault diagnosis results under various historical working conditions, further, the fault diagnosis result of the target ship equipment can be determined based on monitoring data of the target ship equipment and the ship fault diagnosis knowledge graph, and the fault diagnosis result can include but is not limited to: the automatic diagnosis is realized by the fault equipment identification, the initial fault reason and the fault processing suggestion, so that the labor intensity of detection personnel can be reduced for the detection personnel of the ship equipment, the fault diagnosis result is not limited by the detection level of the detection personnel, and the accuracy of the fault diagnosis result can be improved.
In summary, the ship equipment fault diagnosis method based on multi-dimensional feature knowledge extraction provided by the embodiment of the application obtains monitoring data of target ship equipment; acquiring a fault diagnosis result of the target ship equipment according to the monitoring data of the target ship equipment and the ship fault diagnosis knowledge map, wherein the fault diagnosis result comprises the following steps: the ship fault diagnosis knowledge graph takes a plurality of ship equipment as vertexes, and the relation among the ship equipment is established at the same time.
Fig. 2 is a schematic flowchart of another ship equipment fault diagnosis method based on multi-dimensional feature knowledge extraction according to an embodiment of the present application. Optionally, as shown in fig. 2, the method further includes:
s201, obtaining historical monitoring data of a plurality of ship devices, wherein the historical monitoring data comprises: ship equipment identification, fault reason and fault handling suggestion.
S202, obtaining the relation among a plurality of ship devices according to historical monitoring data.
In some embodiments, a ship failure diagnosis knowledge map may be constructed based on historical monitoring data of a plurality of ship equipment, and it is understood that the historical monitoring data may also be multi-dimensional feature data. The ship equipment identification can be used for uniquely identifying each ship equipment, and can comprise letters, numbers, symbols and the like; the failure reason can be used for indicating the failure reason of the ship equipment under different monitoring data; the fault handling proposal can be used to indicate corresponding fault handling measures for different fault reasons. After the historical monitoring data of the multiple pieces of ship equipment is obtained, the relationships among the multiple pieces of ship equipment may be obtained according to the historical monitoring data, where the relationships among the multiple pieces of ship equipment may represent association relationships among the multiple pieces of ship equipment, and may include, but are not limited to, interaction relationships, affiliations among parts, and the like, which is not limited herein.
S203, constructing a ship fault diagnosis knowledge graph according to the relation among the plurality of ship devices.
After the relationship among the ship devices is obtained, the ship fault diagnosis knowledge graph can be constructed by taking the ship devices as vertexes, namely as entity nodes, and the relationship among the ship devices is an edge.
It should be noted that, for the ship failure diagnosis knowledge graph, it may be composed of a concept layer relationship graph and an entity layer relationship graph, where the relationship between concepts and entities may be represented by a multiple relationship attribute tree graph, and the multiple relationship attribute tree graph may be constructed based on an ontology, and the ontology may be understood as a professional knowledge system refined based on knowledge content of ship equipment management, maintenance, use, etc., and is a knowledge representation method, and it is to re-express the concept structure, the association relationship between concepts, etc. in the professional field, and the ontology may be composed of a parent concept layer, a child concept layer, and an instance layer, and the concept layer relationship graph in the ship failure diagnosis knowledge graph may correspond to the parent concept layer and the child concept layer in the ontology, and the entity layer relationship graph in the ship failure diagnosis knowledge graph may be obtained based on the instance layer in the ontology, and the instance layer may include a plurality of entity nodes, in the present application, the physical nodes may be understood as different ship devices, that is, corresponding to the aforementioned vertices.
For example, for a ship ballast water plant, its corresponding parent concept layer may include, but is not limited to, mechanical design, flow design, vibration design, electrical design, etc.; the corresponding sub-concept layer can include but is not limited to motor design, pipeline design, base design, sensor model selection design and the like; the corresponding example layer may include, but is not limited to, rotor centering design, pipeline sealing, twisted pair stagnation cables with shielding layers, and the like, and when the fault diagnosis map of the ship ballast water equipment is constructed based on the method, the fault diagnosis map may be mapped correspondingly, that is, the concept layer of the body is mapped into the fault diagnosis map of the ship ballast water equipment to form the concept layer of the fault diagnosis map, the triplets corresponding to the examples of the body are mapped into the example layer of the fault diagnosis map, entities in the triplets are used as vertexes of the fault diagnosis map, and the membership values are used as edges of the fault diagnosis map, so that semantic relationships and examples of the body can be completely mapped into the fault diagnosis map, and of course, the specific mapping manner is not limited thereto, and the constructed fault diagnosis map is not limited thereto.
By applying the method and the device for ship fault diagnosis, the constructed ship fault diagnosis knowledge graph has high reusability, and the problems of difficult fusion of multi-dimensional feature information, low comprehensiveness of prediction results and low accuracy of the existing ship equipment fault diagnosis method based on multi-dimensional feature knowledge extraction can be solved.
Fig. 3 is a schematic flowchart of another ship equipment fault diagnosis method based on multi-dimensional feature knowledge extraction according to an embodiment of the present application. Optionally, as shown in fig. 3, the obtaining a relationship between a plurality of ship devices according to the historical monitoring data includes:
s301, extracting at least one of the following characteristic data according to the historical monitoring data: structured data, semi-structured data, unstructured data.
For the structured data, the structured data may be acquired based on a monitoring system of the marine equipment, and the acquired structured data may include physical quantities such as temperature, pressure, current, vibration acceleration, vibration displacement, and the like, but is not limited thereto; the unstructured data may be extracted by a natural language processing technique based on texts such as a device maintenance report of a ship device, a user use note, and a device engineer maintenance record report, but is not limited thereto. For example, the unstructured data obtained based on the text may be: "the current of the sensor No. 1 exceeds the normal range, and it may be that the circuit board drifts greatly, and may also be in a place with large electromagnetic interference, and it is necessary to transfer the sensor to a position with low interference, or add a shielding device, or recalibrate the circuit board according to the field working condition, of course, it should be noted that, according to the actual application scenario, the semi-structured data may also include semi-structured data, and the semi-structured data may be obtained through a monitoring system of the marine equipment, or may be obtained through the above text, and the application is not limited herein.
Optionally, when extracting feature data in the unstructured data based on the natural language processing technology, the following steps may be included, but are not limited to: carrying out entity naming identification on the unstructured data, namely extracting entities from the unstructured data and classifying or labeling the entities, wherein the entities can indicate names of ship equipment, and entity unification and reference cancellation can be carried out after entity naming identification is carried out, wherein the entity unification is that a plurality of entities with different surface meanings but essentially pointing to the same entity are unified, so that the entity types are reduced; the term "cancel" refers to the replacement of a term, such as "the" or "the" appearing in the unstructured data, with a corresponding entity; based on the above processing, relationships between entities can be further identified.
Of course, it can be understood that the acquired historical monitoring data can be preprocessed according to an actual application scenario, so that when the ship fault diagnosis knowledge graph is constructed based on the preprocessed historical monitoring data, the constructed ship fault diagnosis knowledge graph is used for fault diagnosis of ship equipment, and the accuracy of fault diagnosis can be improved. Optionally, the preprocessing operations may include, but are not limited to: data completion, outlier processing, dirty data cleaning, etc., may be different according to the actual application scenario.
S302, constructing a triple according to the characteristic data, wherein the triple comprises: the method comprises the steps of ship equipment identification, membership values of all fault reasons, fault reasons and fault processing suggestions, wherein the membership values are used for indicating the probability that characteristic data belong to all fault reasons.
After the feature data is obtained, a triple may be constructed according to the feature data, optionally, feature data corresponding to each ship device may construct a triple, where the triple may include: the method comprises the steps of ship equipment identification, fault reason and fault processing suggestions and membership values of the fault reasons, wherein the membership values can be used for indicating the probability that the characteristic data belong to the fault reasons.
For example, in the extracted feature data, the structured data is: the concentration value of the combustible gas at the upper part of the pump chamber is 23.5LEL, and the threshold values of the first-level alarm, the second-level alarm, the third-level alarm and the limit alarm of the combustible gas in the pump chamber are respectively as follows: the concentration value of the combustible gas obtained by calculation belongs to membership values of primary alarm, secondary alarm, tertiary alarm and limit alarm, wherein the membership values are respectively as follows: 0. 0.65, 0.35, 0, optionally the triples constructed based on the structured data may be: the concentration value of the combustible gas at the upper part of the pump chamber is 23.5LEL-0, the first-level alarm of the combustible gas of the pump chamber is carried out, no suggestion is made, the concentration value of the combustible gas at the upper part of the pump chamber is 23.5LEL-0.65, the second-level alarm of the combustible gas of the pump chamber is carried out, the exhaust fan is started, the concentration value of the combustible gas at the upper part of the pump chamber is 23.5LEL-0.35, the third-level alarm of the combustible gas of the pump chamber is carried out, some valves are suggested to be cut off, the concentration value of the combustible gas at the upper part of the pump chamber is 23.5LEL-0, the limit alarm of the combustible gas of the pump chamber is carried out, and no suggestion is carried out, and the way of actually constructing triples is not limited by the above.
As another alternative, the unstructured data obtained based on the above text further illustrates that, optionally, the triplets constructed based on the unstructured data may be represented by device state description-membership value-fault cause and fault handling suggestion, such as: the current of the sensor No. 1 exceeds the standard by-0.6, the circuit board drifts, the circuit board is recommended to be recalibrated, the current of the sensor No. 1 exceeds the standard by-0.5, the electromagnetic interference is large, and the sensor No. 1 is recommended to be shifted to a low-interference position or a shielding device is additionally arranged, but the sensor No. 1 is not limited.
Of course, it should be noted that the constructed triples are not limited to the above contents, and in some embodiments, the contents in the triples may also be replaced by other contents, for example, the ship device identifier may further include a device state description, the membership value may be replaced by a device value, and the like, but not limited thereto, and may be different according to an actual application scenario.
And S303, acquiring the relationship among the plurality of ship devices according to the triples.
Based on the obtained triples, the relationship between the ship devices may be represented according to the membership value of each fault cause in each triplet, and it should be noted that, of course, the relationship between the ship devices is not limited to the membership value, and according to the content included in the triplets, the relationship between the ship devices may also be described by the device value, but is not limited thereto.
Optionally, the method further includes:
and acquiring the membership value of each fault reason to which the characteristic data belongs according to a preset fuzzy algorithm.
The preset fuzzy algorithm may include a membership function, and then a membership value of each fault cause to which the feature data belongs may be calculated and obtained through the membership function.
Alternatively, the membership function may be expressed as:
Figure BDA0002926644520000141
Figure BDA0002926644520000142
the PSS, the PS, the PM, and the PB are preset membership parameters, and may be used to indicate fault thresholds under different fault causes, the PSS (positive small) represents a minimum parameter, the PS (positive small) represents a positive small parameter, the PM (positive middle) represents a positive middle parameter, the PB (positive big) represents a positive large parameter, and the x represents characteristic data, where optionally, if the value of x is greater than zero, it may be understood that the characteristic data x should belong to any one of the following characteristic ranges: x is more than or equal to 0<PSS、PSS≤x<PS、PS≤x<PM、PM≤x<PB, PB ≦ x, then L p1 (x) A membership value, L, representing the threshold value of the first characteristic under the characteristic range to which x belongs p2 (x) The method includes that x belongs to a membership value of a second feature threshold in a feature range to which x belongs, a first feature threshold and the second feature threshold are two adjacent feature thresholds, and the first feature threshold is smaller than the second feature threshold.
For example, for the structured data described above: the concentration value of the combustible gas at the upper part of the pump chamber is 23.5LEL, and the threshold values of the first-level alarm, the second-level alarm, the third-level alarm and the limit alarm of the combustible gas in the pump chamber are respectively as follows: the threshold value is divided into threshold value ranges of 0-10, 10-20, 20-30 and 30-40, and corresponding threshold value division points are respectively as follows: 10. 20, 30 and 40, optionally, wherein values of PSS, PS, PM and PB may be 10, 20, 30 and 40, respectively, and then the concentration value of combustible gas at the upper part of the pump chamber 23.5LEL belonging to the first alarm, the second alarm, the third alarm and the limit alarm may be calculated as the membership values: 0. 0.65, 0.35 and 0, and it can be understood that the concentration value of the combustible gas at the upper part of the pump chamber belongs to the membership value of the secondary alarm
Figure BDA0002926644520000151
The concentration value of the combustible gas at the upper part of the pump chamber belongs to a membership value of three-level alarm through calculation
Figure BDA0002926644520000152
Of course, the actual calculation method is not limited to this, and different preset model algorithms may be used according to different ship equipment.
Of course, it should be noted that the obtaining of the membership value of each fault cause to which the characteristic data belongs is not limited to the preset fuzzy algorithm, and the membership value may also be obtained by an expert with related professional experience knowledge through comprehensive evaluation according to engineering experience, an expert database, historical data, and the like, and is not limited herein.
Fig. 4 is a schematic flowchart of another ship equipment fault diagnosis method based on multi-dimensional feature knowledge extraction according to an embodiment of the present application, and fig. 5 is a schematic diagram of a ship fault diagnosis knowledge-graph according to an embodiment of the present application. Optionally, as shown in fig. 4, the obtaining of the fault diagnosis result of the target ship device according to the monitoring data of the target ship device and the ship fault diagnosis knowledge graph includes:
s401, extracting target characteristic data of monitoring data of target ship equipment, wherein the target characteristic data comprises at least one of the following data: structured data, semi-structured data, unstructured data.
When performing fault diagnosis, for the monitoring data of the target ship device, target feature data of the monitoring data of the target ship device may be extracted, where the target feature data may include: for a specific extraction manner, reference may be made to the aforementioned extraction manner of the historical monitoring data, and the application is not limited herein.
S402, according to the target characteristic data and all membership values in the ship fault diagnosis knowledge graph, carrying out optimal path searching on the ship fault diagnosis knowledge graph based on an optimal path searching algorithm to obtain an optimal path searching result.
In some embodiments, the optimal path finding Algorithm may be implemented based on Dijkstra's Algorithm, froude Algorithm (Floyd), and the like, which is not limited herein. The dijkstra algorithm is taken as an example for explanation here, and when the optimal path search is performed on the ship fault diagnosis knowledge graph based on the optimal path search algorithm, the ship equipment corresponding to the target feature data can be taken as a starting point, and in the ship fault diagnosis knowledge graph, a path with the maximum product of the membership values is searched as an optimal path, so that an optimal path search result is obtained.
And S403, obtaining a fault diagnosis result according to the optimal path searching result.
Based on the optimal path search result, a fault diagnosis result can be determined according to the indication content in the optimal path, and the fault diagnosis result can include a fault equipment identifier, an initial fault reason and a fault processing suggestion.
As shown in fig. 5, for example, the target characteristic data is that the output current of the sensor is 21.05mA, and the ship fault diagnosis knowledge graph can know that the membership degree to the channel fault of the acquisition module is 0.5, the membership degree to the cable fault is 0.3, and the membership degree to the cable drift is 0.8; the membership degree of the acquisition module channel fault and the power supply voltage abnormity is 0.6, and the specific contents can be seen in relevant parts in the figure. It can be understood that the membership degree product of the path "sensor 21.05mA → acquisition module channel failure → power supply voltage abnormality → checking whether the amplitude of the power supply voltage is within the specified value" can be calculated to be 0.5 x 0.6 x 0.8 x 0.24 based on the ship failure diagnosis knowledge map. By analogy, the membership product of other paths can be calculated. It can be calculated that the maximum membership product is "sensor 21.05mA → circuit board drift → installation near water pump → adjustment of installation position", which is 0.8 × 0.7 × 0.6 ═ 0.336. From this, it can be inferred that when "sensor 21.05 mA", the causes of the failure are "circuit board drift" and "mounting near the water pump", and the processing advice is "adjust mounting position".
It can be understood that when the target feature data includes multidimensional feature data such as structured data, semi-structured data, unstructured data, and the like, when fault diagnosis is performed based on the multidimensional target feature data, the fault diagnosis result can be more accurate.
Fig. 6 is a schematic flowchart of another ship equipment fault diagnosis method based on multi-dimensional feature knowledge extraction according to an embodiment of the present application. Optionally, as shown in fig. 6, after obtaining the fault diagnosis result of the target ship device according to the monitoring data of the target ship device and the ship fault diagnosis knowledge map, the method further includes:
s501, carrying out co-occurrence analysis on the fault diagnosis result according to a co-occurrence matrix to obtain a fault accompanying conclusion, wherein the fault accompanying conclusion is used for indicating the probability of the co-occurrence of other fault reasons when the initial fault reason occurs, and the co-occurrence matrix is used for indicating the probability of the co-occurrence of all fault reasons.
Optionally, the co-occurrence matrix may be obtained according to historical monitoring data of a plurality of ship devices, and the corresponding co-occurrence matrix may be obtained by performing statistical analysis on the historical monitoring data of the plurality of ship devices. Based on the co-occurrence matrix, the fault diagnosis result of the target ship equipment can be subjected to co-occurrence analysis, so that a fault accompanying conclusion corresponding to the monitoring data of the target ship equipment can be obtained through the co-occurrence analysis, that is, when the initial fault reason appears, the probability that other fault reasons appear concomitantly can be obtained, and it can be understood that when a certain fault reason appears concomitantly is higher, the probability that the initial fault reason appears is higher, and the fault reason appears most easily.
By applying the embodiment of the application, other possible fault reasons can be found in time, the fault reasons can be prevented in advance, and the working efficiency of ship equipment is guaranteed.
Fig. 7 is a schematic flowchart of another ship equipment fault diagnosis method based on multidimensional feature knowledge extraction according to the embodiment of the present application, and fig. 8 is a schematic diagram of a citation network according to the embodiment of the present application. Optionally, as shown in fig. 7, before performing a co-occurrence analysis on the fault diagnosis result according to the co-occurrence matrix and obtaining a fault accompanying conclusion, the method further includes:
s601, establishing a citation network according to historical monitoring data of the plurality of ship devices, wherein the citation network comprises fault reasons and fault times corresponding to the historical monitoring data of the ship devices.
S602, acquiring a co-occurrence matrix according to the citation network.
In some embodiments, the citation network may be represented by a citation matrix, where each row in the citation matrix may represent different historical monitoring data, each column may represent a fault cause corresponding to the historical monitoring data, and a value of each element in the citation matrix may be determined according to the number of faults corresponding to the historical monitoring data, and of course, an actual representation manner is not limited thereto.
After the citation matrix is determined according to the citation network, a co-occurrence matrix may be further determined according to the citation matrix, and optionally, the co-occurrence matrix may be calculated according to the citation matrix and a corresponding transpose matrix thereof.
For example, X1, X2, X3 may represent three historical monitoring data indicating a sensor current of 21.5mA, a sensor current of 3.5mA, a sensor current of 20.5mA, respectively; y1, Y2 and Y3 may represent three fault causes, which respectively indicate that the fault causes are circuit board drift, electromagnetic interference around the circuit board drift and cable connection fault, and the constructed citation network may be shown in fig. 8, where the citation matrix determined according to the citation network is
Figure BDA0002926644520000191
And the co-occurrence matrix determined from the quote matrix may be
Figure BDA0002926644520000192
As can be seen from the co-occurrence matrix D, the element values corresponding to Y1 and Y2 are the largest, and it can be understood that the strength of the association between Y1 and Y2 is the largest, so it can be determined that a concomitant conclusion of "electromagnetic interference exists around" may occur when "circuit board drift" is inferred, and the actual determination method is not limited to this.
Fig. 9 is a functional module schematic diagram of a ship equipment fault diagnosis device based on multi-dimensional feature knowledge extraction according to an embodiment of the present application, the basic principle and the generated technical effect of the device are the same as those of the corresponding method embodiment, and for brief description, the corresponding contents in the method embodiment may be referred to for parts not mentioned in this embodiment. As shown in fig. 9, the failure diagnosis apparatus 100 includes:
an obtaining module 110, configured to obtain monitoring data of a target ship device;
a diagnosis module 120, configured to obtain a fault diagnosis result of the target ship device according to the monitoring data of the target ship device and a ship fault diagnosis knowledge graph, where the fault diagnosis result includes: the ship fault diagnosis knowledge graph is constructed by taking a plurality of ship equipment as vertexes and taking the relation between the ship equipment as an edge.
Fig. 10 is a functional module schematic diagram of another ship equipment fault diagnosis device based on multi-dimensional feature knowledge extraction according to an embodiment of the present application. In an alternative embodiment, as shown in fig. 10, the fault diagnosis apparatus further includes: a building module 130, configured to obtain historical monitoring data of a plurality of the ship devices, where the historical monitoring data includes: ship equipment identification, fault reason and fault processing suggestion; obtaining the relation among a plurality of ship devices according to the historical monitoring data; and constructing the ship fault diagnosis knowledge graph according to the relationship among the plurality of ship equipment.
In an optional embodiment, the building module 130 is specifically configured to extract, according to the historical monitoring data, at least one of the following feature data: structured data, semi-structured data, unstructured data; constructing a triple according to the characteristic data, wherein the triple comprises: the method comprises the following steps of (1) identifying ship equipment, belonging membership values of fault reasons, fault reasons and fault processing suggestions, wherein the membership values are used for indicating the probability that characteristic data belong to the fault reasons; and obtaining the relationship among the plurality of ship devices according to the triples.
In an optional embodiment, the building module 130 is further configured to obtain a membership value of each fault cause to which the feature data belongs according to a preset fuzzy algorithm.
In an optional embodiment, the diagnostic module 120 is specifically configured to extract target feature data of the monitoring data of the target ship device, where the target feature data includes at least one of: structured data, semi-structured data, unstructured data; according to the target characteristic data and all membership values in the ship fault diagnosis knowledge map, carrying out optimal path search on the ship fault diagnosis knowledge map based on an optimal path search algorithm to obtain an optimal path search result; and obtaining a fault diagnosis result according to the optimal path search result.
In an optional embodiment, the diagnosis module 120 is further configured to perform co-occurrence analysis on the fault diagnosis result according to a co-occurrence matrix, and obtain a fault co-occurrence conclusion, where the fault co-occurrence conclusion is used to indicate probabilities that other fault causes occur concomitantly when an initial fault cause occurs, and the co-occurrence matrix is used to indicate the probability that each fault cause occurs together.
In an optional embodiment, the diagnostic module 120 is further configured to construct a citation network according to the historical monitoring data of the ship equipment, where the citation network includes a fault reason and a fault frequency corresponding to the historical monitoring data of the ship equipment; and acquiring the co-occurrence matrix according to the citation network.
The above-mentioned apparatus is used for executing the method provided by the foregoing embodiment, and the implementation principle and technical effect are similar, which are not described herein again.
These above modules may be one or more integrated circuits configured to implement the above methods, such as: one or more Application Specific Integrated Circuits (ASICs), or one or more microprocessors (DSPs), or one or more Field Programmable Gate Arrays (FPGAs), among others. For another example, when one of the above modules is implemented in the form of a Processing element scheduler code, the Processing element may be a general-purpose processor, such as a Central Processing Unit (CPU) or other processor capable of calling program code. For another example, these modules may be integrated together and implemented in the form of a system-on-a-chip (SOC).
Fig. 11 is a schematic structural diagram of an electronic device according to an embodiment of the present application. As shown in fig. 11, the electronic device may include: a processor 210, a storage medium 220 and a bus 230, wherein the storage medium 220 stores machine-readable instructions executable by the processor 210, when the electronic device is running, the processor 210 communicates with the storage medium 220 via the bus 230, and the processor 210 executes the machine-readable instructions to perform the steps of the above-mentioned method embodiments. The specific implementation and technical effects are similar, and are not described herein again.
Optionally, the present application further provides a storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the above method embodiments are performed. The specific implementation and technical effects are similar, and are not described herein again.
In the several embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, a division of a unit is merely a logical division, and an actual implementation may have another division, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.
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 units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, or in a form of hardware plus a software functional unit.
The integrated unit implemented in the form of a software functional unit may be stored in a computer readable storage medium. The software functional unit is stored in a storage medium and includes several instructions to enable a computer device (which may be a personal computer, a server, or a network device) or a processor (processor) to execute some steps of the methods according to the embodiments of the present application. And the aforementioned storage medium includes: a U disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
It is noted that, in this document, relational terms such as "first" and "second," and the like, may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
The above description is only a preferred embodiment of the present application and is not intended to limit the present application, and various modifications and changes may be made to the present application by those skilled in the art. Any modification, equivalent replacement, improvement and the like made within the spirit and principle of the present application shall be included in the protection scope of the present application. It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, it need not be further defined and explained in subsequent figures. The above description is only a preferred embodiment of the present application and is not intended to limit the present application, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, improvement and the like made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims (4)

1. A ship equipment fault diagnosis method based on multi-dimensional feature knowledge extraction is characterized by comprising the following steps:
acquiring monitoring data of target ship equipment;
acquiring a fault diagnosis result of the target ship equipment according to the monitoring data of the target ship equipment and a ship fault diagnosis knowledge map, wherein the fault diagnosis result comprises the following steps: the ship fault diagnosis knowledge graph is constructed by taking a plurality of ship equipment as vertexes and constructing a relation among the ship equipment as an edge;
the acquiring a fault diagnosis result of the target ship equipment according to the monitoring data of the target ship equipment and the ship fault diagnosis knowledge graph comprises the following steps:
extracting target characteristic data of the monitoring data of the target ship equipment, wherein the target characteristic data comprises at least one of the following data: structured data, semi-structured data, unstructured data;
according to the target characteristic data and all membership values in the ship fault diagnosis knowledge map, carrying out optimal path search on the ship fault diagnosis knowledge map based on an optimal path search algorithm to obtain an optimal path search result;
obtaining a fault diagnosis result according to the optimal path searching result;
the method further comprises the following steps:
obtaining historical monitoring data of a plurality of the ship devices, wherein the historical monitoring data comprises: ship equipment identification, fault reason and fault processing suggestion;
obtaining the relation among a plurality of ship devices according to the historical monitoring data;
constructing the ship fault diagnosis knowledge graph according to the relationship among the plurality of ship devices;
the obtaining of the relationship between the plurality of ship devices according to the historical monitoring data includes:
according to the historical monitoring data, at least one of the following characteristic data is extracted: structured data, semi-structured data, unstructured data;
constructing a triple according to the characteristic data, wherein the triple comprises: the method comprises the following steps of (1) identifying ship equipment, belonging membership values of fault reasons, fault reasons and fault processing suggestions, wherein the membership values are used for indicating the probability that characteristic data belong to the fault reasons;
obtaining the relation among a plurality of ship devices according to the triples;
acquiring a membership value of each fault reason to which the characteristic data belongs according to a preset fuzzy algorithm;
after the fault diagnosis result of the target ship equipment is obtained according to the monitoring data of the target ship equipment and the ship fault diagnosis knowledge graph, the method further comprises the following steps:
performing co-occurrence analysis on the fault diagnosis result according to a co-occurrence matrix to obtain a fault accompanying conclusion, wherein the fault accompanying conclusion is used for indicating the probability of the co-occurrence of other fault reasons when the initial fault reason occurs, and the co-occurrence matrix is used for indicating the probability of the co-occurrence of each fault reason;
before the co-occurrence analysis is performed on the fault diagnosis result according to the co-occurrence matrix and a fault accompanying conclusion is obtained, the method further includes:
constructing a citation network according to the historical monitoring data of the ship equipment, wherein the citation network comprises fault reasons and fault times corresponding to the historical monitoring data of the ship equipment;
and acquiring the co-occurrence matrix according to the citation network.
2. A ship equipment fault diagnosis device based on multi-dimensional feature knowledge extraction is characterized by comprising:
the acquisition module is used for acquiring monitoring data of the target ship equipment;
the diagnosis module is used for acquiring a fault diagnosis result of the target ship equipment according to the monitoring data of the target ship equipment and the ship fault diagnosis knowledge map, and the fault diagnosis result comprises: the ship fault diagnosis knowledge graph is constructed by taking a plurality of ship equipment as vertexes and constructing a relation among the ship equipment as an edge;
the diagnostic module is specifically further configured to extract target feature data of the monitoring data of the target ship device, where the target feature data includes at least one of: structured data, semi-structured data, unstructured data; according to the target characteristic data and all membership values in the ship fault diagnosis knowledge map, carrying out optimal path search on the ship fault diagnosis knowledge map based on an optimal path search algorithm to obtain an optimal path search result; obtaining a fault diagnosis result according to the optimal path searching result;
a building module, configured to obtain historical monitoring data of a plurality of pieces of marine equipment, where the historical monitoring data includes: ship equipment identification, fault reason and fault processing suggestion; obtaining the relation among a plurality of ship devices according to the historical monitoring data; constructing the ship fault diagnosis knowledge graph according to the relationship among the plurality of ship equipment;
the building module is specifically further configured to extract at least one of the following feature data according to the historical monitoring data: structured data, semi-structured data, unstructured data; constructing a triple according to the characteristic data, wherein the triple comprises: the method comprises the following steps of (1) identifying ship equipment, belonging membership values of fault reasons, fault reasons and fault processing suggestions, wherein the membership values are used for indicating the probability that characteristic data belong to the fault reasons; obtaining the relation among a plurality of ship devices according to the triples;
the construction module is also used for acquiring the membership value of each fault reason to which the characteristic data belongs according to a preset fuzzy algorithm;
the diagnosis module is specifically configured to perform co-occurrence analysis on the fault diagnosis result according to a co-occurrence matrix to obtain a fault accompanying conclusion, where the fault accompanying conclusion is used to indicate probabilities that other fault causes appear concomitantly when an initial fault cause appears, and the co-occurrence matrix is used to indicate probabilities that the fault causes appear together;
the diagnosis module is specifically used for constructing a citation network according to the historical monitoring data of the ship equipment, and the citation network comprises fault reasons and fault times corresponding to the historical monitoring data of the ship equipment; and acquiring the co-occurrence matrix according to the citation network.
3. An electronic device, comprising: a processor, a storage medium and a bus, wherein the storage medium stores machine-readable instructions executable by the processor, when the electronic device runs, the processor and the storage medium communicate through the bus, and the processor executes the machine-readable instructions to execute the steps of the ship equipment fault diagnosis method based on multi-dimensional feature knowledge extraction according to claim 1.
4. A storage medium having stored thereon a computer program for executing the steps of the method for diagnosing a malfunction of a ship equipment based on multi-dimensional feature knowledge extraction according to claim 1 when the computer program is executed by a processor.
CN202110139145.XA 2021-02-01 2021-02-01 Ship equipment fault diagnosis method and equipment based on multi-dimensional feature knowledge extraction Active CN112810772B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110139145.XA CN112810772B (en) 2021-02-01 2021-02-01 Ship equipment fault diagnosis method and equipment based on multi-dimensional feature knowledge extraction

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110139145.XA CN112810772B (en) 2021-02-01 2021-02-01 Ship equipment fault diagnosis method and equipment based on multi-dimensional feature knowledge extraction

Publications (2)

Publication Number Publication Date
CN112810772A CN112810772A (en) 2021-05-18
CN112810772B true CN112810772B (en) 2022-08-26

Family

ID=75861314

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110139145.XA Active CN112810772B (en) 2021-02-01 2021-02-01 Ship equipment fault diagnosis method and equipment based on multi-dimensional feature knowledge extraction

Country Status (1)

Country Link
CN (1) CN112810772B (en)

Families Citing this family (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113359664B (en) * 2021-05-31 2023-07-07 海南文鳐科技有限公司 Fault diagnosis and maintenance system, method, equipment and storage medium
CN113553662A (en) * 2021-07-20 2021-10-26 广船国际有限公司 Ship fault prediction method, system, equipment and storage medium
CN114818994B (en) * 2022-06-24 2022-09-09 国网浙江省电力有限公司信息通信分公司 Cross-business map fusion method based on multi-source heterogeneous power data
CN118298526A (en) * 2024-04-02 2024-07-05 南京盛航海运股份有限公司 Ship equipment running state monitoring and fault diagnosis method and system

Family Cites Families (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109240258A (en) * 2018-07-09 2019-01-18 上海万行信息科技有限公司 Vehicle failure intelligent auxiliary diagnosis method and system based on term vector
CN111435366A (en) * 2019-01-14 2020-07-21 阿里巴巴集团控股有限公司 Equipment fault diagnosis method and device and electronic equipment
CN110705812A (en) * 2019-04-15 2020-01-17 中国石油大学(华东) Industrial fault analysis system based on fuzzy neural network
CN110705710A (en) * 2019-04-17 2020-01-17 中国石油大学(华东) Knowledge graph-based industrial fault analysis expert system
CN110110809B (en) * 2019-05-16 2021-03-16 郑州轻工业学院 Fuzzy automaton construction method based on machine fault diagnosis
CN110854839A (en) * 2019-10-12 2020-02-28 江苏远望仪器集团有限公司 Power supply system for monitoring system and asymmetric load fault diagnosis method
CN111126603A (en) * 2019-12-25 2020-05-08 江苏远望仪器集团有限公司 Equipment fault prediction method, device and equipment based on neural network model

Also Published As

Publication number Publication date
CN112810772A (en) 2021-05-18

Similar Documents

Publication Publication Date Title
CN112810772B (en) Ship equipment fault diagnosis method and equipment based on multi-dimensional feature knowledge extraction
CN110033101B (en) Hydroelectric generating set fault diagnosis method and system based on knowledge graph of fusion features
CN110705710A (en) Knowledge graph-based industrial fault analysis expert system
CN114138759B (en) Secondary equipment fault processing pushing method and system based on knowledge graph reasoning
Yan et al. Big-data-driven based intelligent prognostics scheme in industry 4.0 environment
Gao et al. A novel framework for the reliability modelling of repairable multistate complex mechanical systems considering propagation relationships
CN108830335A (en) Photovoltaic plant fault early warning method and system
Kim et al. Development of an interpretable maritime accident prediction system using machine learning techniques
Gao et al. Decision fusion method for fault diagnosis based on closeness and Dempster-Shafer theory
US10318364B2 (en) Methods and systems for problem-alert aggregation
Loughney et al. Utilizing the evidential reasoning approach to determine a suitable wireless sensor network orientation for asset integrity monitoring of an offshore gas turbine driven generator
Su et al. A maintenance and troubleshooting method based on integrated information and system principles
CN116611523B (en) Method and system for predicting interpretable faults of turbofan engine
CN116467493B (en) Mine disaster tracing method based on knowledge graph
CN117540900A (en) Safety multidimensional risk identification method for water resource system
CN117313845A (en) Power grid fault detection auxiliary method and system based on knowledge graph
Zhang et al. Identification of key factors and mining of association relations in complex product assembly process
Ebrahimipour et al. Ontology-based knowledge platform to support equipment health in plant operations
Wang et al. Risk Assessment Method for Ship Based on Improved Fuzzy Multicriteria Decision‐Making
Kim et al. A hybrid failure diagnosis and prediction using natural language-based process map and rule-based expert system
Peng et al. Equipment fault propagation path identification based on unstable points detection
Huang et al. Research on the uncertainty problem of SDG fault diagnosis based on information flow
Yin et al. Research on ontology modeling of uncertain environment cognition for unmanned maritime systems
CN117634869B (en) Safe operation early warning method and system for thermal power plant
Zhang et al. Analysis on Intelligent Fault Diagnosis Technology of Industrial Control Network

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
GR01 Patent grant