CN112884199A - Method and device for predicting faults of hydropower station equipment, computer equipment and storage medium - Google Patents
Method and device for predicting faults of hydropower station equipment, computer equipment and storage medium Download PDFInfo
- Publication number
- CN112884199A CN112884199A CN202110053179.7A CN202110053179A CN112884199A CN 112884199 A CN112884199 A CN 112884199A CN 202110053179 A CN202110053179 A CN 202110053179A CN 112884199 A CN112884199 A CN 112884199A
- Authority
- CN
- China
- Prior art keywords
- fault
- data
- real
- hydropower station
- station 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 58
- 238000003860 storage Methods 0.000 title claims abstract description 16
- 239000013598 vector Substances 0.000 claims abstract description 303
- 238000012544 monitoring process Methods 0.000 claims abstract description 165
- 238000012423 maintenance Methods 0.000 claims abstract description 53
- 238000004458 analytical method Methods 0.000 claims description 42
- 238000012545 processing Methods 0.000 claims description 17
- 238000004364 calculation method Methods 0.000 claims description 14
- 238000004590 computer program Methods 0.000 claims description 13
- 238000013179 statistical model Methods 0.000 claims description 8
- 238000012731 temporal analysis Methods 0.000 claims description 8
- 238000000700 time series analysis Methods 0.000 claims description 8
- 238000007405 data analysis Methods 0.000 claims description 7
- 238000010586 diagram Methods 0.000 description 8
- 230000002159 abnormal effect Effects 0.000 description 5
- 230000015572 biosynthetic process Effects 0.000 description 4
- 238000011156 evaluation Methods 0.000 description 4
- 230000010354 integration Effects 0.000 description 4
- 238000000691 measurement method Methods 0.000 description 4
- 238000012821 model calculation Methods 0.000 description 4
- 238000003786 synthesis reaction Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 3
- 238000009826 distribution Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000013210 evaluation model Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000012546 transfer Methods 0.000 description 2
- 230000001960 triggered effect Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- Development Economics (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Marketing (AREA)
- Educational Administration (AREA)
- Game Theory and Decision Science (AREA)
- Health & Medical Sciences (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- General Engineering & Computer Science (AREA)
- Primary Health Care (AREA)
- General Health & Medical Sciences (AREA)
- Water Supply & Treatment (AREA)
- Public Health (AREA)
- Life Sciences & Earth Sciences (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- Computational Linguistics (AREA)
- Animal Behavior & Ethology (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
The application relates to a method and a device for predicting faults of hydropower station equipment, computer equipment and a storage medium. The method comprises the following steps: acquiring real-time monitoring data of the current running state of the hydropower station equipment, and generating a real-time state vector corresponding to the real-time monitoring data; determining a target fault characteristic vector corresponding to the real-time state vector according to the corresponding relation between the state vector and the fault characteristic vector, wherein the corresponding relation between the state vector and the fault characteristic vector is obtained by analyzing a preset hydropower station equipment fault knowledge map; calculating the offset of the real-time state vector and the target fault feature vector; acquiring maintenance state data of hydropower station equipment, and acquiring fault occurrence probability according to the offset and the maintenance state data; and predicting the fault according to the fault occurrence probability. By adopting the method, the faults are accurately predicted in advance based on the preset hydropower station equipment fault knowledge map, and the faults of the hydropower station equipment can be accurately predicted in time.
Description
Technical Field
The application relates to the technical field of power monitoring, in particular to a method and a device for predicting faults of hydropower station equipment, computer equipment and a storage medium.
Background
With the development of the field of power monitoring, an online monitoring technology for hydropower station equipment appears, a corresponding online monitoring system is established in a hydropower station based on the online monitoring technology, the working state of the hydropower station equipment is monitored in real time, and when an abnormal state is detected, an alarm is given to prevent serious faults or accidents.
The current online monitoring technology adopts a threshold value alarming method, and an alarm is sent out when a monitoring value exceeds a threshold value, however, because the threshold value is set to be high in order to prevent excessive alarm information, when the alarm information is sent out, accidents can occur due to the fact that the alarm cannot be timely handled, and the current alarm information is too simple, only the state parameter exceeds a normal range can be stated, and the reason of which fault can not be judged, so that the problem that the accident occurs due to the fact that the fault reason can not be timely known exists.
Disclosure of Invention
In view of the above, it is necessary to provide a method, an apparatus, a computer device and a storage medium for predicting a failure of a hydropower station device, which can accurately predict the failure in time.
A method of hydropower device fault prediction, the method comprising:
acquiring real-time monitoring data of the current running state of the hydropower station equipment, and generating a real-time state vector corresponding to the real-time monitoring data;
determining a target fault characteristic vector corresponding to the real-time state vector according to the corresponding relation between the state vector and the fault characteristic vector, wherein the corresponding relation between the state vector and the fault characteristic vector is obtained by analyzing a preset hydropower station equipment fault knowledge map;
calculating the offset of the real-time state vector and the target fault feature vector;
acquiring maintenance state data of hydropower station equipment, and acquiring fault occurrence probability according to the offset and the maintenance state data;
and predicting the fault according to the fault occurrence probability.
In one embodiment, the method further comprises the following steps:
acquiring fault related data of hydropower station equipment, wherein the fault related data comprises hydropower station equipment data, state information data, historical fault data and historical processing measure data;
and carrying out data modeling according to the logic relation among the fault related data, and constructing to obtain a preset hydropower station equipment fault knowledge map.
In one embodiment, before obtaining the target fault feature vector corresponding to the real-time state vector from the corresponding relationship according to the corresponding relationship between the state vector and the fault feature vector, the method further includes:
acquiring fault data of different dimensions of hydropower station equipment;
forming a state vector according to fault data of different dimensions;
performing multi-degree relation analysis on the state vector through a preset hydropower station equipment fault knowledge map to generate a fault feature vector corresponding to the state vector;
and establishing a corresponding relation between the state vector and the fault feature vector.
In one embodiment, performing a multi-degree relationship analysis on the state vector through a preset knowledge graph of the faults of the hydropower station equipment, and generating a fault feature vector corresponding to the state vector includes:
performing multi-degree relation analysis on the state vector through a preset hydropower station equipment fault knowledge graph to obtain the association degree of the nodes in the hydropower station equipment fault knowledge graph and the fault, wherein the multi-degree relation analysis is the relation weight analysis of different nodes, and the nodes in the hydropower station equipment fault knowledge graph represent the state vector;
and generating a fault feature vector corresponding to the state vector according to the relevance.
In one embodiment, the obtaining real-time monitoring data of the current operating state of the hydropower station device, and the generating a real-time state vector corresponding to the real-time monitoring data includes:
acquiring real-time monitoring data of the current running state of hydropower station equipment;
establishing a relevant model of the real-time monitoring data according to the real-time monitoring data, wherein the relevant model comprises any one of a comparison model, a calculation model based on a physical principle, a time series analysis model and a statistical model;
and performing data analysis on the real-time monitoring data according to the relevant model to generate a real-time state vector.
In one embodiment, predicting the fault according to the fault occurrence probability comprises:
according to the predicted fault determined by predicting the fault, obtaining a fault reason, a fault risk, a fault related phenomenon and different fault solving measures corresponding to the predicted fault from a preset hydropower station equipment knowledge map;
and determining the optimal fault solving measures from different fault solving measures according to the fault reasons, the fault risks and the fault related phenomena.
In one embodiment, obtaining maintenance state data of the hydropower station device, and obtaining the fault occurrence probability according to the offset and the maintenance state data further includes:
and when the fault occurrence probability exceeds a preset probability threshold, sending alarm information.
A hydropower device fault prediction apparatus, the apparatus comprising:
the real-time data acquisition module is used for acquiring real-time monitoring data of the current running state of the hydropower station equipment and generating a real-time state vector corresponding to the real-time monitoring data;
the corresponding vector generation module is used for determining a target fault feature vector corresponding to the real-time state vector according to the corresponding relation between the state vector and the fault feature vector, and the corresponding relation between the state vector and the fault feature vector is obtained through analysis of a preset hydropower station equipment fault knowledge map;
the offset calculation module is used for calculating the offset of the real-time state vector and the target fault characteristic vector;
the fault occurrence probability determining module is used for acquiring maintenance state data of the hydropower station equipment and obtaining fault occurrence probability according to the offset and the maintenance state data;
and the fault prediction module is used for predicting the fault according to the fault occurrence probability.
A computer device comprising a memory and a processor, the memory storing a computer program, the processor implementing the following steps when executing the computer program:
acquiring real-time monitoring data of the current running state of the hydropower station equipment, and generating a real-time state vector corresponding to the real-time monitoring data;
determining a target fault characteristic vector corresponding to the real-time state vector according to the corresponding relation between the state vector and the fault characteristic vector, wherein the corresponding relation between the state vector and the fault characteristic vector is obtained by analyzing a preset hydropower station equipment fault knowledge map;
calculating the offset of the real-time state vector and the target fault feature vector;
acquiring maintenance state data of hydropower station equipment, and acquiring fault occurrence probability according to the offset and the maintenance state data;
and predicting the fault according to the fault occurrence probability.
A computer-readable storage medium, on which a computer program is stored which, when executed by a processor, carries out the steps of:
acquiring real-time monitoring data of the current running state of the hydropower station equipment, and generating a real-time state vector corresponding to the real-time monitoring data;
determining a target fault characteristic vector corresponding to the real-time state vector according to the corresponding relation between the state vector and the fault characteristic vector, wherein the corresponding relation between the state vector and the fault characteristic vector is obtained by analyzing a preset hydropower station equipment fault knowledge map;
calculating the offset of the real-time state vector and the target fault feature vector;
acquiring maintenance state data of hydropower station equipment, and acquiring fault occurrence probability according to the offset and the maintenance state data;
and predicting the fault according to the fault occurrence probability.
According to the method, the device, the computer equipment and the storage medium for predicting the faults of the hydropower station equipment, the real-time monitoring data of the current running state of the hydropower station equipment are obtained; generating a real-time state vector corresponding to the real-time monitoring data; the real-time monitoring of the current running state of the hydropower station equipment is realized. And timely analyzing and processing are carried out by acquiring real-time monitoring data, so that a corresponding real-time state vector is accurately obtained. The method comprises the steps of accurately matching a target fault characteristic vector corresponding to a current real-time state vector according to a corresponding relation between a state vector and a fault characteristic vector based on a preset hydropower station equipment fault knowledge map and the corresponding relation, accurately calculating the offset of the real-time state vector and the target fault characteristic vector, further acquiring maintenance state data of hydropower station equipment, and finally obtaining accurate fault occurrence probability by combining the offset and the maintenance state data. The faults are predicted according to the fault occurrence probability, and are accurately predicted in advance through the fault occurrence probability, so that the faults occurring in the hydropower station equipment can be accurately predicted in time.
Drawings
FIG. 1 is a diagram of an environment in which a method for predicting a failure of a piece of equipment in a hydroelectric power plant may be implemented;
FIG. 2 is a schematic flow diagram of a method for predicting a failure of a piece of equipment in a hydroelectric power plant according to an embodiment;
FIG. 3 is a schematic flow chart illustrating the steps of constructing a knowledge graph of a piece of hydropower equipment in the method for predicting the failure of the piece of hydropower equipment in one embodiment;
FIG. 4 is a schematic illustration of a hydropower device knowledge map constructed in a method of predicting a failure of a hydropower device in another embodiment;
FIG. 5 is a schematic flow chart illustrating a step of establishing a correspondence between a state vector and a fault feature vector in the method for predicting a failure of a piece of hydropower equipment according to an embodiment;
fig. 6 is a schematic flowchart illustrating a step of establishing a correspondence between a state vector and a fault feature vector in a method for predicting a fault of a piece of hydropower equipment according to another embodiment;
FIG. 7 is a schematic flow chart of a method for predicting a failure of a piece of equipment in a hydroelectric power plant according to another embodiment;
FIG. 8 is a schematic flow chart diagram of a method for predicting a failure of a hydroelectric power plant installation according to yet another embodiment;
FIG. 9 is a schematic flow chart of a method for predicting equipment failure in a hydroelectric power plant according to yet another embodiment;
FIG. 10 is a schematic flow chart diagram of a method for predicting equipment failure in a hydroelectric power plant according to one embodiment;
fig. 11 is a block diagram of a configuration of a device for predicting a failure of a hydroelectric power plant according to an embodiment;
FIG. 12 is a diagram illustrating an internal structure of a computer device according to an embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
The hydropower station equipment fault prediction method provided by the application can be applied to the application environment shown in fig. 1. The online monitoring system 102 of the hydropower station communicates with the hydropower station device 104 through a network, and the online monitoring system 102 generates a real-time state vector corresponding to real-time monitoring data by acquiring the real-time monitoring data of the current operating state of the hydropower station device 104, and then calculates an offset between the real-time state vector and a target fault feature vector. After the online monitoring system 102 calculates the offset, the online monitoring system 102 obtains the fault occurrence probability by obtaining the maintenance state data of the hydropower station device 104 according to the offset and the maintenance state data, and predicts the fault occurring in the hydropower station device 104 according to the fault occurrence probability. The online monitoring system 102 may be a system including a terminal and a server, where the terminal may be, but is not limited to, various personal computers, notebook computers, smart phones, tablet computers, and portable wearable devices, and the server may be implemented by an independent server or a server cluster formed by a plurality of servers.
In one embodiment, as shown in fig. 2, a method for predicting a failure of a hydropower device is provided, which is illustrated by taking the method as an example for being applied to the online monitoring system in fig. 1, and comprises the following steps:
The current operation state of the hydropower station equipment refers to the working state of the hydropower station equipment which is currently operating. The real-time monitoring data is data obtained by monitoring hydropower station equipment in real time by an online monitoring system. For example, the data obtained by real-time monitoring may be a phenomenon occurring when the hydropower station device is currently running, which is monitored in real time, and the phenomenon is fault data that can be directly sensed by the monitored system. The real-time state vector is obtained according to the real-time monitoring data, and represents the current running state of the hydropower station equipment.
Specifically, the online monitoring system acquires real-time monitoring data of the current running state of the hydropower station equipment, and performs modeling analysis on the real-time monitoring data to obtain a real-time state vector corresponding to the real-time monitoring data. The adopted modeling model is different for different monitoring data, is selected according to the property of the current real-time monitoring data and is a model related to the real-time monitoring data. The model to be modeled may be any one of a comparison model, a calculation model based on physical principles, a time series analysis model, and a statistical model, specifically selected by currently acquired real-time monitoring data. The real-time monitoring data characterizes a phenomenon of the current hydropower station equipment, and the phenomenon can be a fault which can be directly sensed by an online monitoring system, so that the phenomenon can be one fault and can also be a cause of another fault.
And 204, determining a target fault characteristic vector corresponding to the real-time state vector according to the corresponding relation between the state vector and the fault characteristic vector, wherein the corresponding relation between the state vector and the fault characteristic vector is obtained through analysis of a preset hydropower station equipment fault knowledge map.
The corresponding relation between the state vector and the fault feature vector can be preset, and the state vector and the fault feature vector have a multi-degree corresponding relation. For example, the correspondence relationship of multiple degrees may be expressed that one state vector may correspond to multiple fault feature vectors, or different state vectors may correspond to the same fault feature vector, and the correspondence relationship of multiple degrees may further include a connection of correspondence relationships between intermediate vectors, for example, one state vector may be associated with a fault feature vector corresponding to another state vector through one intermediate state vector. Therefore, the state vector and the fault feature vector can be a vector set formed by a plurality of vectors respectively, the obtained real-time state vector is not less than one vector, and the state vector is subjected to multi-degree analysis through the knowledge graph of the hydropower station equipment based on the knowledge graph of the hydropower station equipment to generate the corresponding associated fault feature vector.
Specifically, the online monitoring system of the hydropower station matches the acquired real-time monitoring data to a target fault feature vector corresponding to the current real-time monitoring data through a preset corresponding relation between a state vector and a fault feature vector, and the number of the determined target fault feature vectors is not less than one.
And step 206, calculating the offset of the real-time state vector and the target fault feature vector.
The offset is calculated by a distance measurement method, a specific distance measurement method is selected according to the real-time state vector, and the offset can represent the offset condition of the current real-time state vector and the normal state or the fault state.
Specifically, the online monitoring system calculates the offset of the real-time state vector and the target fault feature vector by a distance measurement method selected according to the real-time state vector.
And step 208, obtaining maintenance state data of the hydropower station equipment, and obtaining the fault occurrence probability according to the offset and the maintenance state data.
The maintenance state data is data such as equipment maintenance state of the hydropower station equipment obtained by the online monitoring system. The fault occurrence probability is the fault occurrence probability of each fault of each monitoring period and each equipment, the fault occurrence probability can be expressed as a numerical value between 0 and 1, including 0 and 1, and the numerical value closer to 1 indicates that the fault occurrence probability is larger.
Specifically, after the online monitoring system of the hydropower station acquires the state maintenance data of the hydropower station equipment, the fault occurrence probability of each fault of each monitoring period and each equipment is calculated by integrating the offset and the maintenance state data, and the integrated calculation method can be linear weighted integration, exponential weighted integration and the like. Taking linear weighting synthesis as an example, the linear weighting synthesis is to carry out comprehensive evaluation by taking a linear weighting model as a comprehensive evaluation model, and the linear weighting is an evaluation function method which is a method for solving a multi-target programming problem by giving corresponding weight coefficients to each target according to the importance of the target and then carrying out optimization on the linear combination of the weighted coefficients.
And step 210, predicting the fault according to the fault occurrence probability.
Specifically, the online monitoring system may synthesize the fault occurrence probability of each fault of each device in each monitoring period, and predict the faults that may occur, where the predicted number of faults is not less than one.
According to the method, the device, the computer equipment and the storage medium for predicting the faults of the hydropower station equipment, the real-time monitoring data of the current running state of the hydropower station equipment are obtained; generating a real-time state vector corresponding to the real-time monitoring data; the real-time monitoring of the current running state of the hydropower station equipment is realized, the corresponding real-time state vector is accurately obtained by acquiring real-time monitoring data and carrying out timely analysis and processing, and the corresponding relation between the state vector and the fault characteristic vector is realized on the basis of a preset hydropower station equipment fault knowledge map, accurately matching the target fault characteristic vector corresponding to the current real-time state vector according to the corresponding relation, and accurately calculating the offset of the real-time state vector and the target fault characteristic vector, further acquiring maintenance state data of the hydropower station equipment, by combining the offset and the maintenance state data, the accurate fault occurrence probability is finally obtained, the faults are predicted accurately in advance through the fault occurrence probability, and the faults occurring in the hydropower station equipment can be predicted accurately in time.
In one embodiment, as shown in fig. 3, the method for predicting a failure of a hydroelectric power plant further comprises:
Specifically, the online monitoring system acquires fault-related data of the hydropower station equipment, wherein the fault-related data comprises hydropower station equipment data, state information data, historical fault data, historical processing measure data and other historical data. The data related to the fault can be analyzed by acquiring professional book data related to hydropower station equipment or fault research, recorded expert experience data and the like to obtain hydropower station equipment data, state information data, historical fault data and historical treatment measure data. The historical data includes past monitoring data, maintenance records, production activity records, etc. of the hydropower plant equipment. The hydropower station equipment data comprises equipment specifications, equipment operation and maintenance manuals, equipment parameter settings and the like.
And 304, performing data modeling according to the logic relation among the fault related data, and constructing to obtain a preset hydropower station equipment fault knowledge map.
In one embodiment, the online monitoring system models data based on logical relationships between fault-related data. For example, data modeling may be performed by using the hydropower plant equipment data, the state information data, the historical fault data, and the historical treatment measure data and the logical relationship therebetween, and specifically, a constructed hydropower plant equipment fault knowledge map is shown in fig. 4.
In the embodiment, the preset hydropower station equipment fault knowledge map is constructed, the corresponding relation between the state vector and the fault characteristic vector is established, the incidence relation among fault phenomena is considered, and when an abnormal state is found, the accuracy of judgment can be improved by combining the analysis and judgment of the related fault phenomena, so that an alarm is given when the equipment state slightly changes, and more processing time is won. And accurately matching a target fault characteristic vector corresponding to the current real-time state vector according to the corresponding relation based on a preset hydropower station equipment fault knowledge map. Possible fault reasons, risks, related phenomena and disposal measures are analyzed through the hydropower station equipment fault knowledge graph, the faults are quickly positioned, the faults are accurately predicted in advance, and the faults occurring in the hydropower station equipment can be accurately predicted in time.
In one embodiment, as shown in fig. 5, before obtaining the target fault feature vector corresponding to the real-time state vector from the corresponding relationship according to the corresponding relationship between the state vector and the fault feature vector, that is, before step 204, the method further includes:
Specifically, an online monitoring system of hydropower station equipment acquires fault data of the hydropower station equipment in different dimensions, wherein the different dimensions refer to different angles or different aspects, and the fault data in the different dimensions have a multi-degree relationship. The multi-degree relation refers to that one fault data is uniquely corresponding to another fault data, namely, a one-degree relation, when one fault data is not uniquely corresponding to another fault data, the one-degree relation can be corresponding to multiple fault data, or the one-degree relation is a two-degree relation, the one-degree relation is corresponding to another fault data through another fault data, the two-degree relation is a two-degree relation, the two-degree relation is required to be corresponding to another data through data transfer, the transferred data can also be not unique, at the moment, the multi-degree relation is formed, the two-degree relation is also one of the multi-degree relations, and the more the transferred data is, the more the degree number of the relation. The fault data may be a phenomenon generated when a fault occurs, and is a broad concept. For example, mechanical vibration is a fault, a phenomenon, and may be the cause of another fault. A phenomenon is fault data that can be understood as being directly perceived by the monitored system.
Specifically, the online monitoring system forms a state vector according to the acquired fault data of different dimensions. The number of the state vectors is not less than one, the state vectors are composed of a series of states, one state is obtained by carrying out correlation model calculation on fault data, and the state vectors are composed by obtaining a series of states through a plurality of correlation model calculations. The state vector is used to characterize the operational state of the hydropower device. For example, taking the temperature at the temperature measuring point obeying normal distribution as an example, if the expected value is E, the standard deviation is σ, and the measured value is x, the corresponding state can be quantized as:
and step 506, performing multi-degree relation analysis on the state vector through a preset hydropower station equipment fault knowledge map to generate a fault feature vector corresponding to the state vector.
Specifically, the online monitoring system performs multi-degree relation analysis on the state vector through a preset hydropower station equipment fault knowledge graph, and generates a fault feature vector corresponding to the state vector by establishing the association degree of the node in the hydropower station equipment fault knowledge graph and the fault.
Specifically, the online monitoring system is used for monitoring the association degree of the nodes and the faults in the hydropower station equipment fault knowledge graph.
In the embodiment, fault data of different dimensions of the hydropower station equipment are obtained by obtaining the hydropower station equipment; according to fault data of different dimensions, a state vector is formed, and multi-aspect and multi-angle monitoring on hydropower station equipment is achieved. And performing multi-degree relation analysis on the state vector through a preset hydropower station equipment fault knowledge map to generate a fault feature vector corresponding to the state vector. And based on a preset hydropower station equipment fault knowledge map, a corresponding relation between the state vector and the fault characteristic vector is established, and a target fault characteristic vector corresponding to the current real-time state vector can be accurately matched according to the corresponding relation. Through the relevance between the faults and the phenomena, when an abnormal state is found, the accuracy of judgment can be improved by combining the analysis and the judgment of the related faults and phenomena, the offset of the real-time state vector and the target fault characteristic vector is accurately calculated, the maintenance state data of the hydropower station equipment is further obtained, the accurate fault occurrence probability is finally obtained by combining the offset and the maintenance state data, and the faults are predicted according to the fault occurrence probability. The faults are accurately predicted in advance through the fault occurrence probability, and the faults occurring in the hydropower station equipment can be accurately predicted in time.
In one embodiment, as shown in fig. 6, the state vector is subjected to a multi-degree relationship analysis through a preset knowledge map of the faults of the hydropower station equipment, and a fault feature vector corresponding to the state vector is generated, i.e. step 506 includes:
Wherein, the meaning of a node in the hydropower station equipment fault knowledge graph is a phenomenon. And generating a fault characteristic vector corresponding to the state vector by establishing the association degree between the node in the hydropower station equipment fault knowledge graph and the fault. For example, it may be assumed that there are n paths P between the phenomenon S and the fault F1～PnOne of the paths PiFrom m edges Ei1～EimComposition, each edge having a weight of w (E)ij) Then the degree of correlation of the fault F to the phenomenon S can be given by:
in the formula, the fault F may be represented as one of the fault feature vectors, and the phenomenon S may be represented as a node in the knowledge graph of the faults of the hydropower plant equipment and may be represented as one of the state vectors. The weight refers to the probability that one fault leads to another fault, and a phenomenon may also be a fault, a phenomenon may be a fault that may be directly perceived by the monitored system, and a phenomenon may also be the cause of another fault.
And step 604, generating a fault feature vector corresponding to the state vector according to the relevance.
The online monitoring system establishes the corresponding relation between the state vector and the fault characteristic vector through the correlation degree from the phenomenon S to the fault F.
In this embodiment, by establishing the corresponding relationship between the state vector and the fault feature vector, the target fault feature vector corresponding to the current real-time state vector can be accurately matched according to the corresponding relationship. Through the relevance between the faults and the phenomena, when an abnormal state is found, the accuracy of judgment can be improved by combining the analysis and the judgment of the related faults and phenomena, the offset of the real-time state vector and the target fault characteristic vector is accurately calculated, the maintenance state data of the hydropower station equipment is further obtained, and the accurate fault occurrence probability is finally obtained by combining the offset and the maintenance state data. The faults are predicted according to the fault occurrence probability, and are accurately predicted in advance through the fault occurrence probability, so that the faults occurring in the hydropower station equipment can be accurately predicted in time.
In one embodiment, as shown in fig. 7, the step 202 of obtaining real-time monitoring data of the current operating state of the hydropower station device and generating a real-time state vector corresponding to the real-time monitoring data includes:
Specifically, the online monitoring system acquires real-time monitoring data of the current running state of the hydropower station equipment. The current operation state of the hydropower station equipment refers to the working state of the currently operating hydropower station equipment. The real-time monitoring data is data obtained by monitoring the hydropower station equipment in real time by the online monitoring system, and the data obtained by real-time monitoring can be a phenomenon generated when the hydropower station equipment monitored in real time runs at present. Thus, the real-time monitoring data characterizes a phenomenon of the current hydropower station equipment, the phenomenon being fault data that can be directly perceived by the monitored system, and the phenomenon being a fault that can be directly perceived by the on-line monitoring system. Therefore, a phenomenon may be one kind of failure and may also be a cause of another kind of failure.
And the online monitoring system establishes a relevant model related to the real-time monitoring data according to the real-time monitoring data. Different monitoring data are different in models, the model for modeling can be any one of a comparison model, a calculation model based on a physical principle, a time series analysis model and a statistical model, and the modeling is specifically selected through the currently acquired real-time monitoring data.
And 706, performing data analysis on the real-time monitoring data according to the relevant model to generate a real-time state vector.
And performing data analysis on the real-time monitoring data through the selected relevant model to generate a corresponding real-time state vector, wherein the real-time state vector represents the current running state of the hydropower station equipment.
In the embodiment, real-time monitoring data of the current running state of the hydropower station equipment is obtained; generating a real-time state vector corresponding to the real-time monitoring data; the real-time monitoring of the current running state of the hydropower station equipment is realized, the corresponding real-time state vector is accurately obtained by acquiring real-time monitoring data and carrying out timely analysis and processing, and the corresponding relation between the state vector and the fault characteristic vector is realized on the basis of a preset hydropower station equipment fault knowledge map, accurately matching the target fault characteristic vector corresponding to the current real-time state vector according to the corresponding relation, and accurately calculating the offset of the real-time state vector and the target fault characteristic vector, further acquiring maintenance state data of the hydropower station equipment, by combining the offset and the maintenance state data, the accurate fault occurrence probability is finally obtained, the faults are predicted accurately in advance through the fault occurrence probability, and the faults occurring in the hydropower station equipment can be predicted accurately in time.
In one embodiment, as shown in fig. 8, after predicting the fault according to the fault occurrence probability, i.e. after step 210, the method includes:
According to the fault occurrence probability, the online monitoring system analyzes a preset knowledge graph of the hydropower station equipment to obtain a fault reason, a fault risk, a fault related phenomenon and different fault solving measures corresponding to the predicted fault.
And step 804, determining an optimal fault solution from different fault solutions according to the fault reason, the fault risk and the fault related phenomenon.
The online monitoring system determines the optimal fault solution from different fault solutions according to the fault reason, the fault risk and the fault related phenomenon, and pushes and displays the optimal fault solution.
In the embodiment, the fault is predicted according to the fault occurrence probability, possible fault reasons, fault risks and fault related phenomena can be obtained by using the knowledge graph, and the optimal fault solving measures are determined from different fault solving measures according to the fault reasons, the fault risks and the fault related phenomena, so that operation and maintenance personnel can be helped to position and handle the fault more quickly. The faults are accurately predicted in advance through the fault occurrence probability, and the faults occurring in the hydropower station equipment can be accurately predicted in time.
In one embodiment, as shown in fig. 9, after obtaining the maintenance state data of the hydropower station device and obtaining the fault occurrence probability according to the offset and the maintenance state data, step 208 includes:
and step 902, when the fault occurrence probability exceeds a preset probability threshold, sending alarm information.
In one embodiment, the online monitoring system may preset a probability threshold, specifically, the setting of the probability threshold is an effective setting of reserved fault processing time, and an excessively high alarm threshold is set without setting an excessively high value. In this embodiment, when the calculated failure occurrence probability exceeds the probability threshold, an alarm message is sent immediately to remind the staff in the hydropower station, for example, the specific alarm information may be prompted by an online monitoring system, an alarm is sounded, and an APP prompt and a short message prompt are provided on an electronic device such as a mobile phone associated with the online monitoring system. The online monitoring system can predict the fault while sending the alarm information and provide an optimal fault solution, so that the fault can be processed in time and the processing efficiency is high.
In the embodiment, when the fault occurrence probability exceeds a preset probability threshold, the alarm information is sent in time, the reserved time predicts the fault according to the fault occurrence probability while the alarm information is sent, the knowledge graph can be used for simultaneously obtaining possible fault reasons, fault risks and fault related phenomena, and the optimal fault solving measure is determined from different fault solving measures according to the fault reasons, the fault risks and the fault related phenomena, so that operation and maintenance personnel can be helped to position and handle the fault more quickly. The faults are accurately predicted in advance through the fault occurrence probability, and the faults occurring in the hydropower station equipment can be accurately predicted in time.
In one embodiment, as shown in fig. 10, a method for predicting equipment failure of a hydropower device is provided, which includes the following steps 1002 to 1032.
And 1004, performing data modeling according to the logic relation among the fault related data, and constructing to obtain a preset hydropower station equipment fault knowledge map.
and 1010, performing data analysis on the real-time monitoring data according to the relevant model to generate a real-time state vector.
And step 1016, performing multi-degree relation analysis on the state vector through a preset hydropower station equipment fault knowledge graph to obtain the association degree of the nodes in the hydropower station equipment fault knowledge graph and the fault, wherein the multi-degree relation analysis is the relation weight analysis of different nodes, and the nodes in the hydropower station equipment fault knowledge graph represent the state vector.
And step 1018, generating a fault feature vector corresponding to the state vector according to the correlation degree.
And 1022, determining a target fault characteristic vector corresponding to the real-time state vector according to the corresponding relation between the state vector and the fault characteristic vector, wherein the corresponding relation between the state vector and the fault characteristic vector is obtained through analysis of a preset hydropower station equipment fault knowledge map.
And step 1024, calculating the offset of the real-time state vector and the target fault feature vector.
And step 1026, obtaining maintenance state data of the hydropower station equipment, and obtaining the fault occurrence probability according to the offset and the maintenance state data.
And step 1030, predicting the fault according to the fault occurrence probability.
And 1032, obtaining a fault reason, a fault risk, a fault related phenomenon and different fault solving measures corresponding to the predicted fault from a preset hydropower station equipment knowledge map according to the predicted fault determined by predicting the fault.
Step 1034, determine the optimal fault resolution from the different fault resolution measures according to the fault cause, fault risk, and fault-related phenomena.
In an application example, the application also provides an application scenario, as shown in fig. 10, where the method for predicting the equipment fault of the hydropower station is applied to the application scenario. Specifically, the hydropower station equipment fault prediction method is applied to the application scene as follows:
in one embodiment, the online monitoring system obtains fault-related data of the hydropower station equipment, wherein the fault-related data includes hydropower station equipment data, historical data such as hydropower station equipment data, state information data, historical fault data and historical processing measure data, and the fault-related data can be obtained by obtaining professional book data related to the hydropower station equipment or fault research, recorded expert experience data and the like and analyzing the professional book data, the recorded expert experience data and the like, and the hydropower station equipment data, the state information data, the historical fault data and the historical processing measure data. Specifically, the historical data includes past monitoring data, maintenance records, production activity records, etc. of the hydroelectric power plant equipment. The hydropower station equipment data comprises equipment specifications, equipment operation and maintenance manuals, equipment parameter settings and the like. The online monitoring system performs data modeling according to the logical relationship among the fault-related data, for example, the data modeling may be performed through hydropower station equipment data, state information data, historical fault data, historical processing measure data and the logical relationship among the data, and a preset hydropower station equipment fault knowledge graph is constructed.
In one embodiment, the online monitoring system acquires real-time monitoring data of the current operating state of the hydropower station equipment, wherein the current operating state of the hydropower station equipment refers to the working state of the currently operating hydropower station equipment. The real-time monitoring data is data obtained by monitoring the hydropower station equipment in real time by the online monitoring system, and the data obtained by real-time monitoring can be a phenomenon generated when the hydropower station equipment monitored in real time runs at present. Therefore, the real-time monitoring data represents the phenomenon of the current hydropower station equipment, the phenomenon is fault data which can be directly sensed by the monitored system, and the phenomenon can be a fault which can be directly sensed by the online monitoring system, so that the phenomenon can be a fault and can also be a cause of another fault. The on-line monitoring system establishes a relevant model related to the real-time monitoring data according to the real-time monitoring data, different monitoring data are adopted, the adopted models are different, the modeled model can be any one of a comparison model, a calculation model based on a physical principle, a time series analysis model and a statistical model, and the modeling is specifically selected through the currently acquired real-time monitoring data. And performing data analysis on the real-time monitoring data through the selected relevant model to generate a corresponding real-time state vector, wherein the real-time state vector represents the current running state of the hydropower station equipment.
In one embodiment, the online monitoring system of the hydropower station equipment acquires fault data of different dimensions of the hydropower station equipment, the different dimensions refer to different angles or different aspects, the fault data of the different dimensions have a multi-degree relationship, the multi-degree relationship refers to that one fault data is uniquely corresponding to another fault data, namely, the one-degree relationship, when one fault data is not uniquely corresponding to another fault data, the one-degree relationship can correspond to multiple fault data, or the other fault data is corresponding to another fault data through another fault data, namely, the two-degree relationship is a two-degree relationship, the data needing to be transferred is corresponding to other data through data transfer, the transferred data can also be non-unique, at this moment, the multi-degree relationship is one of the multi-degree relationships, the more the data transferred, the more the degree of the relationship, and the fault data can be a phenomenon generated when a fault occurs, fault data is a broad concept, for example, mechanical vibration is a fault, a phenomenon, and may be the cause of another fault. A phenomenon is fault data that can be understood as being directly perceived by the monitored system. The online monitoring system forms a state vector according to the acquired fault data with different dimensions, the number of the state vectors is not less than one, the state vector is composed of a series of states, one state is obtained by performing relevant model calculation on the fault data, and the state vector is formed by obtaining a series of states through a plurality of relevant model calculations. The state vector is used to characterize the operational state of the hydropower device. For example, taking the temperature at the temperature measuring point obeying normal distribution as an example, if the expected value is E, the standard deviation is σ, and the measured value is x, the corresponding state can be quantized as:
the online monitoring system carries out multi-degree relation analysis on the state vector through a preset hydropower station equipment fault knowledge graph, and generates a fault characteristic vector corresponding to the state vector by establishing the association degree of the nodes in the hydropower station equipment fault knowledge graph and the fault. In this embodiment, a preset hydropower station equipment fault knowledge graph is used to perform multi-degree relation analysis on the state vector to obtain the association degree between the node in the hydropower station equipment fault knowledge graph and the fault, the multi-degree relation analysis is the relation weight analysis of different nodes, and the node in the hydropower station equipment fault knowledge graph represents the state vector. Specifically, the meaning of a node in the knowledge-graph of hydropower station equipment faults is a phenomenon. Generating fault characteristic vectors corresponding to the state vectors by establishing the association degree of the nodes and the faults in the hydropower station equipment fault knowledge graph, for example, setting n paths P between a phenomenon S and a fault F1～PnOne of the paths PiFrom m edges Ei1～EimComposition, each edge having a weight of w (E)ij) Then the degree of correlation of the fault F to the phenomenon S can be given by:
in the formula, the fault F may be represented as one of the fault feature vectors, and the phenomenon S may be represented as a node in the knowledge graph of the faults of the hydropower plant equipment and may be represented as one of the state vectors. The weight refers to the probability that one fault leads to another fault, and a phenomenon may also be a fault, a phenomenon may be a fault that may be directly perceived by the monitored system, and a phenomenon may also be the cause of another fault. The online monitoring system establishes the corresponding relation between the state vector and the fault characteristic vector through the relevance degree from the phenomenon S to the fault F, and establishes the corresponding relation between the state vector and the fault characteristic vector.
In one embodiment, the online monitoring system of the hydropower station matches the acquired real-time monitoring data to a target fault feature vector corresponding to the current real-time monitoring data through a preset corresponding relationship between a state vector and a fault feature vector, and the number of the determined target fault feature vectors is not less than one. And the online monitoring system calculates the offset of the real-time state vector and the target fault characteristic vector by a distance measurement method selected according to the real-time state vector. After the online monitoring system of the hydropower station acquires the state maintenance data of the hydropower station equipment, the fault occurrence probability of each fault of each monitoring period and each equipment is calculated by integrating the offset and the maintenance state data, and the integrated calculation method can be linear weighted integration, exponential weighted integration and the like. Taking linear weighting synthesis as an example, the linear weighting synthesis is to carry out comprehensive evaluation by taking a linear weighting model as a comprehensive evaluation model, and the linear weighting is an evaluation function method which is a method for solving a multi-target programming problem by giving corresponding weight coefficients to each target according to the importance of the target and then carrying out optimization on the linear combination of the weighted coefficients. The online monitoring system can synthesize the fault occurrence probability of each fault of each monitoring period and each device, and predict the possible faults, wherein the predicted faults are not less than one.
In one embodiment, according to the fault occurrence probability, the online monitoring system analyzes a preset knowledge graph of the hydropower station equipment to obtain a fault reason, a fault risk, a fault-related phenomenon and different fault solving measures corresponding to the predicted fault. The online monitoring system determines the optimal fault solution from different fault solutions according to the fault reason, the fault risk and the fault related phenomenon, and pushes and displays the optimal fault solution. In one embodiment, the online monitoring system may preset a probability threshold, specifically, the setting of the probability threshold is an effective setting of the reserved fault handling time, and is not set too high, for example, the online monitoring system sets a probability threshold by analyzing specific data and considering the severity of the fault, the probability threshold may be represented by a value between 0 and 1, including 0 and 1, for example, the probability threshold is set to 0.8, and when the probability threshold exceeds 0.8, an alarm is triggered. An excessively high alarm threshold is set, and when a fault develops to a certain degree, an alarm can be triggered, so that the fault possibly cannot be handled in time and an accident occurs. In the embodiment, when the calculated fault occurrence probability exceeds the probability threshold, the alarm message is sent immediately to remind the hydropower station staff, and the online monitoring system can predict the fault while sending the alarm message and provide an optimal fault solution, so that the fault can be processed in time, and the processing efficiency is high.
In the embodiment, real-time monitoring data of the current running state of the hydropower station equipment is obtained; generating a real-time state vector corresponding to the real-time monitoring data; the method realizes real-time monitoring of the current running state of the hydropower station equipment, timely analysis and processing are carried out by acquiring real-time monitoring data, a corresponding real-time state vector is accurately obtained, the relation between faults and phenomena is considered through the relevance based on a preset hydropower station equipment fault knowledge map, when an abnormal state is found, the accuracy of judgment can be improved by combining the analysis and judgment of the related fault phenomena, the target fault characteristic vector corresponding to the current real-time state vector is accurately matched according to the corresponding relation through the corresponding relation between the state vector and the fault characteristic vector, the offset of the real-time state vector and the target fault characteristic vector is accurately calculated, the maintenance state data of the hydropower station equipment is further acquired, and the accurate fault occurrence probability is finally obtained by combining the offset and the maintenance state data, the faults are predicted according to the fault occurrence probability, an alarm is given out when the state of the equipment slightly changes according to the fault occurrence probability, more handling time is won, the faults are accurately predicted in advance, and the faults occurring in the hydropower station equipment can be accurately predicted in time. When warning information is given, the knowledge graph can be used for reasoning out possible fault reasons, fault risks, fault related phenomena and fault disposal measures, and hydropower station operation and maintenance personnel are helped to locate and dispose faults more quickly.
It should be understood that, although the steps in the flowcharts in the above embodiments are shown in sequence as indicated by the arrows, the steps are not necessarily performed in sequence as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least a part of the steps in each flowchart may include a plurality of steps or a plurality of stages, which are not necessarily performed at the same time, but may be performed at different times, and the order of performing the steps or stages is not necessarily sequential, but may be performed alternately or alternately with other steps or at least a part of the steps or stages in other steps.
In one embodiment, as shown in fig. 11, there is provided a hydropower device failure prediction apparatus including: a real-time data acquisition module 1102, a corresponding vector generation module 1104, an offset calculation module 1106, a failure occurrence probability determination module 1108, and a failure prediction module 1110, wherein:
a real-time data obtaining module 1102, configured to obtain real-time monitoring data of a current operating state of the hydropower station device, and generate a real-time state vector corresponding to the real-time monitoring data;
a corresponding vector generation module 1104, configured to determine a target fault feature vector corresponding to the real-time state vector according to a corresponding relationship between the state vector and the fault feature vector, where the corresponding relationship between the state vector and the fault feature vector is obtained through analysis of a preset hydropower station equipment fault knowledge map;
an offset calculation module 1106, configured to calculate an offset between the real-time status vector and the target fault feature vector;
a fault occurrence probability determining module 1108, configured to obtain maintenance state data of the hydropower station device, and obtain a fault occurrence probability according to the offset and the maintenance state data;
and a failure prediction module 1110, configured to predict a failure according to the failure occurrence probability.
In one embodiment, the hydropower station equipment fault prediction device further comprises a hydropower station equipment fault knowledge map module, wherein the hydropower station equipment fault knowledge map module is used for acquiring fault related data of the hydropower station equipment, and the fault related data comprises hydropower station equipment data, state information data, historical fault data and historical processing measure data; and carrying out data modeling according to the logic relation among the fault related data, and constructing to obtain a preset hydropower station equipment fault knowledge map.
In one embodiment, the hydropower station equipment fault prediction device further comprises a corresponding relation establishing module, wherein the corresponding relation establishing module is used for acquiring fault data of different dimensions of hydropower station equipment; forming a state vector according to fault data of different dimensions; performing multi-degree relation analysis on the state vector through a preset hydropower station equipment fault knowledge map to generate a fault feature vector corresponding to the state vector; and establishing a corresponding relation between the state vector and the fault feature vector.
In one embodiment, the corresponding relation establishing module is further configured to perform multi-degree relation analysis on the state vector through a preset hydropower station equipment fault knowledge graph to obtain association degrees between nodes and faults in the hydropower station equipment fault knowledge graph, the multi-degree relation analysis is relation weight analysis of different nodes, and the nodes in the hydropower station equipment fault knowledge graph represent the state vector; and generating a fault feature vector corresponding to the state vector according to the relevance.
In one embodiment, the real-time data obtaining module 1102 is further configured to obtain real-time monitoring data of the current operating state of the hydropower station device; establishing a relevant model of the real-time monitoring data according to the real-time monitoring data, wherein the relevant model comprises any one of a comparison model, a calculation model based on a physical principle, a time series analysis model and a statistical model; and performing data analysis on the real-time monitoring data according to the relevant model to generate a real-time state vector.
In one embodiment, the hydropower station equipment fault prediction device further comprises an optimal fault solution determination module, wherein the optimal fault solution determination module is used for obtaining fault reasons, fault risks, fault related phenomena and different fault solution measures corresponding to the predicted faults from a preset hydropower station equipment knowledge graph according to the predicted faults determined by predicting the faults; and determining the optimal fault solving measures from different fault solving measures according to the fault reasons, the fault risks and the fault related phenomena.
In one embodiment, the hydropower station equipment fault prediction device further comprises an alarm information sending module, and the alarm information sending module is used for sending alarm information when the fault occurrence probability exceeds a preset probability threshold.
For specific limitations of the device for predicting the failure of the hydropower station equipment, reference may be made to the above limitations of the method for predicting the failure of the hydropower station equipment, which are not described herein again. The modules in the hydropower station equipment failure prediction device can be wholly or partially realized by software, hardware and a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as shown in fig. 12. The computer device includes a processor, a memory, and a network interface connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The database of the computer device is used for storing the knowledge map and monitoring data in real time. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a method of hydropower device failure prediction.
Those skilled in the art will appreciate that the architecture shown in fig. 12 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
In one embodiment, a computer device is further provided, which includes a memory and a processor, the memory stores a computer program, and the processor implements the steps of the above method embodiments when executing the computer program.
In an embodiment, a computer-readable storage medium is provided, on which a computer program is stored which, when being executed by a processor, carries out the steps of the above-mentioned method embodiments.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database or other medium used in the embodiments provided herein can include at least one of non-volatile and volatile memory. Non-volatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical storage, or the like. Volatile Memory can include Random Access Memory (RAM) or external cache Memory. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM), among others.
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (10)
1. A method of predicting a failure of a hydroelectric power plant, the method comprising:
acquiring real-time monitoring data of the current running state of hydropower station equipment, and generating a real-time state vector corresponding to the real-time monitoring data;
determining a target fault characteristic vector corresponding to the real-time state vector according to the corresponding relation between the state vector and the fault characteristic vector, wherein the corresponding relation between the state vector and the fault characteristic vector is obtained by analyzing a preset hydropower station equipment fault knowledge map;
calculating the offset of the real-time state vector and the target fault feature vector;
obtaining maintenance state data of hydropower station equipment, and obtaining fault occurrence probability according to the offset and the maintenance state data;
and predicting the fault according to the fault occurrence probability.
2. The method of claim 1, further comprising:
acquiring fault related data of hydropower station equipment, wherein the fault related data comprises the hydropower station equipment data, state information data, historical fault data and historical processing measure data;
and performing data modeling according to the logic relation among the fault related data, and constructing to obtain the preset hydropower station equipment fault knowledge map.
3. The method according to claim 1 or 2, wherein before obtaining the target fault feature vector corresponding to the real-time state vector from the corresponding relationship according to the corresponding relationship between the state vector and the fault feature vector, the method further comprises:
acquiring fault data of different dimensions of hydropower station equipment;
forming a state vector according to the fault data of different dimensions;
performing multi-degree relation analysis on the state vector through a preset hydropower station equipment fault knowledge map to generate a fault feature vector corresponding to the state vector;
and establishing a corresponding relation between the state vector and the fault feature vector.
4. The method of claim 3, wherein the performing a multi-degree relationship analysis on the state vector through a preset knowledge graph of the hydropower plant faults and generating fault feature vectors corresponding to the state vector comprises:
performing multi-degree relation analysis on the state vector through a preset hydropower station equipment fault knowledge graph to obtain the association degree of the nodes in the hydropower station equipment fault knowledge graph and the fault, wherein the multi-degree relation analysis is the relation weight analysis of different nodes, and the nodes in the hydropower station equipment fault knowledge graph represent the state vector;
and generating a fault feature vector corresponding to the state vector according to the association degree.
5. The method of claim 1, wherein the obtaining real-time monitoring data of a current operating state of a hydroelectric power plant device, and generating a real-time state vector corresponding to the real-time monitoring data comprises:
acquiring real-time monitoring data of the current running state of hydropower station equipment;
establishing a relevant model of the real-time monitoring data according to the real-time monitoring data, wherein the relevant model comprises any one of a comparison model, a calculation model based on a physical principle, a time series analysis model and a statistical model;
and performing data analysis on the real-time monitoring data according to the relevant model to generate a real-time state vector.
6. The method of claim 1, wherein predicting the fault according to the fault occurrence probability comprises:
according to the predicted fault determined by predicting the fault, obtaining a fault reason, a fault risk, a fault related phenomenon and different fault solving measures corresponding to the predicted fault from the preset hydropower station equipment knowledge map;
determining an optimal fault resolution from the different fault resolutions based on the fault cause, the fault risk, and the fault-related phenomenon.
7. The method of claim 1, wherein obtaining the maintenance status data of the hydroelectric power plant equipment and obtaining the fault occurrence probability according to the offset and the maintenance status data further comprises:
and sending alarm information when the fault occurrence probability exceeds a preset probability threshold.
8. A hydropower device failure prediction apparatus, characterized in that the apparatus comprises:
the real-time data acquisition module is used for acquiring real-time monitoring data of the current running state of the hydropower station equipment and generating a real-time state vector corresponding to the real-time monitoring data;
the corresponding vector generation module is used for determining a target fault feature vector corresponding to the real-time state vector according to the corresponding relation between the state vector and the fault feature vector, and the corresponding relation between the state vector and the fault feature vector is obtained through analysis of a preset hydropower station equipment fault knowledge map;
the offset calculation module is used for calculating the offset of the real-time state vector and the target fault characteristic vector;
the fault occurrence probability determining module is used for acquiring maintenance state data of the hydropower station equipment and obtaining fault occurrence probability according to the offset and the maintenance state data;
and the fault prediction module is used for predicting the fault according to the fault occurrence probability.
9. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor, when executing the computer program, implements the steps of the method of any of claims 1 to 7.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110053179.7A CN112884199B (en) | 2021-01-15 | Hydropower station equipment fault prediction method, hydropower station equipment fault prediction device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110053179.7A CN112884199B (en) | 2021-01-15 | Hydropower station equipment fault prediction method, hydropower station equipment fault prediction device, computer equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112884199A true CN112884199A (en) | 2021-06-01 |
| CN112884199B CN112884199B (en) | 2024-06-25 |
Family
ID=
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113359682A (en) * | 2021-06-30 | 2021-09-07 | 西安力传智能技术有限公司 | Equipment fault prediction method, device, equipment fault prediction platform and medium |
| CN113689042A (en) * | 2021-08-25 | 2021-11-23 | 华自科技股份有限公司 | Fault source prediction method for monitoring node |
| CN115018220A (en) * | 2022-08-10 | 2022-09-06 | 哈尔滨工业大学（威海） | Household appliance fault prediction method and system based on knowledge graph |
| CN115048965A (en) * | 2022-08-15 | 2022-09-13 | 南方医科大学珠江医院 | Method, device, equipment and medium for detecting fault of ultrasonic medical equipment |
Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103901298A (en) * | 2014-03-13 | 2014-07-02 | 广东电网公司电力科学研究院 | Method and system for detecting operating states of substation equipment |
| CN105426665A (en) * | 2015-11-03 | 2016-03-23 | 中国船舶工业系统工程研究院 | Dynamic reliability determination method based on state monitoring |
| CN108319695A (en) * | 2018-02-02 | 2018-07-24 | 华自科技股份有限公司 | Power station fault data processing method, device, computer equipment and storage medium |
| US20180315023A1 (en) * | 2017-04-26 | 2018-11-01 | General Electric Company | Subject matter knowledge mapping |
| CN109460010A (en) * | 2018-12-18 | 2019-03-12 | 彩虹无线（北京）新技术有限公司 | The vehicle fault detection method, apparatus and storage medium of knowledge based map |
| CN110033101A (en) * | 2019-03-07 | 2019-07-19 | 华中科技大学 | The Fault Diagnosis Method of Hydro-generating Unit and system of knowledge mapping based on fusion feature |
| CN110941725A (en) * | 2019-11-29 | 2020-03-31 | 国网湖南省电力有限公司 | Knowledge graph-based hydroelectric generating set fault diagnosis method and system |
| US20200201311A1 (en) * | 2018-12-19 | 2020-06-25 | Shenzhen Jingjiang Yunchuang Technology Co., Ltd. | Equipment maintenance method, equipment maintenance device, and storage medium for the same |
| CN111563606A (en) * | 2020-04-30 | 2020-08-21 | 新智数字科技有限公司 | Equipment predictive maintenance method and device |
| CN111832974A (en) * | 2020-07-28 | 2020-10-27 | 重庆长安新能源汽车科技有限公司 | Vehicle fault early warning method and storage medium |
| CN111860900A (en) * | 2020-08-14 | 2020-10-30 | 中国能源建设集团广东省电力设计研究院有限公司 | BIM-based digital twin intelligent machine room management method, device, equipment and medium |
| CN112100392A (en) * | 2020-07-28 | 2020-12-18 | 浙江大学 | Equipment fault tracing method based on reinforcement learning and knowledge graph |
| CN112101666A (en) * | 2020-09-16 | 2020-12-18 | 珠海格力电器股份有限公司 | Fault prediction method and device, readable storage medium and computer equipment |
| CN112148887A (en) * | 2020-09-16 | 2020-12-29 | 珠海格力电器股份有限公司 | Equipment fault diagnosis method and device, storage medium and electronic equipment |
Patent Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103901298A (en) * | 2014-03-13 | 2014-07-02 | 广东电网公司电力科学研究院 | Method and system for detecting operating states of substation equipment |
| CN105426665A (en) * | 2015-11-03 | 2016-03-23 | 中国船舶工业系统工程研究院 | Dynamic reliability determination method based on state monitoring |
| US20180315023A1 (en) * | 2017-04-26 | 2018-11-01 | General Electric Company | Subject matter knowledge mapping |
| CN108319695A (en) * | 2018-02-02 | 2018-07-24 | 华自科技股份有限公司 | Power station fault data processing method, device, computer equipment and storage medium |
| CN109460010A (en) * | 2018-12-18 | 2019-03-12 | 彩虹无线（北京）新技术有限公司 | The vehicle fault detection method, apparatus and storage medium of knowledge based map |
| US20200201311A1 (en) * | 2018-12-19 | 2020-06-25 | Shenzhen Jingjiang Yunchuang Technology Co., Ltd. | Equipment maintenance method, equipment maintenance device, and storage medium for the same |
| CN110033101A (en) * | 2019-03-07 | 2019-07-19 | 华中科技大学 | The Fault Diagnosis Method of Hydro-generating Unit and system of knowledge mapping based on fusion feature |
| CN110941725A (en) * | 2019-11-29 | 2020-03-31 | 国网湖南省电力有限公司 | Knowledge graph-based hydroelectric generating set fault diagnosis method and system |
| CN111563606A (en) * | 2020-04-30 | 2020-08-21 | 新智数字科技有限公司 | Equipment predictive maintenance method and device |
| CN111832974A (en) * | 2020-07-28 | 2020-10-27 | 重庆长安新能源汽车科技有限公司 | Vehicle fault early warning method and storage medium |
| CN112100392A (en) * | 2020-07-28 | 2020-12-18 | 浙江大学 | Equipment fault tracing method based on reinforcement learning and knowledge graph |
| CN111860900A (en) * | 2020-08-14 | 2020-10-30 | 中国能源建设集团广东省电力设计研究院有限公司 | BIM-based digital twin intelligent machine room management method, device, equipment and medium |
| CN112101666A (en) * | 2020-09-16 | 2020-12-18 | 珠海格力电器股份有限公司 | Fault prediction method and device, readable storage medium and computer equipment |
| CN112148887A (en) * | 2020-09-16 | 2020-12-29 | 珠海格力电器股份有限公司 | Equipment fault diagnosis method and device, storage medium and electronic equipment |
Non-Patent Citations (2)
| Title |
|---|
| 杜林明;刘光涛;: "RCM和PHM混合故障诊断分析方法在机车远程运维的应用", 中国高新科技, no. 07, 1 April 2019 (2019-04-01) * |
| 赵峰;朱声浩;吕宗辉;张劲宇;张文博;初奇;林青峰;陈威;: "基于5G技术的智能车间故障预测与健康管理系统", 电子制作, no. 15 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113359682A (en) * | 2021-06-30 | 2021-09-07 | 西安力传智能技术有限公司 | Equipment fault prediction method, device, equipment fault prediction platform and medium |
| CN113359682B (en) * | 2021-06-30 | 2022-12-02 | 西安力传智能技术有限公司 | Equipment fault prediction method, device, equipment fault prediction platform and medium |
| CN113689042A (en) * | 2021-08-25 | 2021-11-23 | 华自科技股份有限公司 | Fault source prediction method for monitoring node |
| CN115018220A (en) * | 2022-08-10 | 2022-09-06 | 哈尔滨工业大学（威海） | Household appliance fault prediction method and system based on knowledge graph |
| CN115048965A (en) * | 2022-08-15 | 2022-09-13 | 南方医科大学珠江医院 | Method, device, equipment and medium for detecting fault of ultrasonic medical equipment |
| CN115048965B (en) * | 2022-08-15 | 2022-12-13 | 南方医科大学珠江医院 | Method, device, equipment and medium for detecting fault of ultrasonic medical equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111045894B (en) | Database abnormality detection method, database abnormality detection device, computer device and storage medium | |
| US11152126B2 (en) | Abnormality diagnosis system and abnormality diagnosis method | |
| CN110868241B (en) | Underground cable fault early warning method and device based on multiple models | |
| CN108445410A (en) | A kind of method and device of monitoring accumulator group operating status | |
| CN109143094B (en) | Abnormal data detection method and device for power battery | |
| RU2649542C1 (en) | Method and system of remote monitoring of objects | |
| US20130226501A1 (en) | Systems and methods for predicting abnormal temperature of a server room using hidden markov model | |
| US20230118175A1 (en) | Event analysis in an electric power system | |
| CN115562225A (en) | Industrial robot operation and maintenance management method and device, computer equipment and storage medium | |
| CN115237710A (en) | Server temperature prediction method and device, computer equipment and storage medium | |
| CN116187552A (en) | Abnormality detection method, computing device, and computer storage medium | |
| CN116050930A (en) | Monitoring disc system, monitoring disc method, storage medium and electronic equipment | |
| CN113295399B (en) | Converter valve element state evaluation method, device, electronic equipment and storage medium | |
| Vafeiadis et al. | Robust malfunction diagnosis in process industry time series | |
| CN112380073B (en) | Fault position detection method and device and readable storage medium | |
| CN117330963B (en) | Energy storage power station fault detection method, system and equipment | |
| CN116311829B (en) | Remote alarm method and device for data machine room | |
| CN110544031B (en) | Method and device for predicting reliability of electric energy meter, computer equipment and storage medium | |
| CN117169761A (en) | Battery state evaluation method, apparatus, device, storage medium, and program product | |
| CN112884199B (en) | Hydropower station equipment fault prediction method, hydropower station equipment fault prediction device, computer equipment and storage medium | |
| CN112884199A (en) | Method and device for predicting faults of hydropower station equipment, computer equipment and storage medium | |
| Peng et al. | A health monitoring method based on multivariate state estimation technique | |
| CN113808727B (en) | Device monitoring method, device, computer device and readable storage medium | |
| CN113689042B (en) | Fault source prediction method for monitoring node | |
| Azhar et al. | Transient Stability Detection Using CNN-LSTM Considering Time Frame of Observation |
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 |