CN112286088A - Method and application system for online application of power equipment fault prediction model - Google Patents
Method and application system for online application of power equipment fault prediction model Download PDFInfo
- Publication number
- CN112286088A CN112286088A CN202011024022.3A CN202011024022A CN112286088A CN 112286088 A CN112286088 A CN 112286088A CN 202011024022 A CN202011024022 A CN 202011024022A CN 112286088 A CN112286088 A CN 112286088A
- Authority
- CN
- China
- Prior art keywords
- fault
- prediction model
- equipment
- library
- fault prediction
- 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.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B19/00—Programme-control systems
- G05B19/02—Programme-control systems electric
- G05B19/04—Programme control other than numerical control, i.e. in sequence controllers or logic controllers
- G05B19/042—Programme control other than numerical control, i.e. in sequence controllers or logic controllers using digital processors
- G05B19/0428—Safety, monitoring
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B2219/00—Program-control systems
- G05B2219/20—Pc systems
- G05B2219/24—Pc safety
- G05B2219/24024—Safety, surveillance
Abstract
The invention belongs to the technical field of information, and discloses a method and an application system for online application of a power equipment fault prediction model, wherein the power equipment fault prediction models generated by different prediction methods are classified according to the faults of different equipment, and an equipment fault prediction model library is generated offline; deploying a fault prediction model library into an existing network operation system, performing equipment fault prediction on the current system, and generating a maintenance plan on line; and (4) retraining the prediction model of the partial fault type, and updating the equipment fault prediction model library on line or off line. The invention applies the offline generated fault prediction model to the online system, can know the possible faults of the equipment in real time, provides a maintenance plan of the equipment for a decision maker, and achieves advanced maintenance, thereby avoiding the shutdown hidden trouble caused by the equipment fault to the communication equipment.
Description
Technical Field
The invention belongs to the technical field of information, and particularly relates to a method and an application system for online application of a power equipment fault prediction model.
Background
At present, a dynamic loop monitoring system is mainly used for monitoring the running state of power equipment, the power equipment comprises a switching power supply, an air conditioner, an oil engine, a storage battery, a high-low voltage power distribution and the like, the system mainly comprises an acquisition unit, a central platform server and a display client, each composition module corresponds to one or more physical equipment entities, and the central platform server can be deployed at the cloud. The system is used for remotely monitoring the operation parameters of the power and environmental equipment of the communication bureau station on line. When the power equipment breaks down, the system can realize quick presentation, quick response and quick order dispatching, and can effectively eliminate the faults in time. However, sometimes, the failure is not processed in time, which may affect the normal operation of the communication master device.
The predictive maintenance technology can predict the time of possible occurrence of the fault in advance, make a maintenance or maintenance plan in advance, and prevent the fault in the bud, and the predictive maintenance requires a large amount of equipment data to be modeled, and a large amount of historical data exists in the actual operation environment of the dynamic loop monitoring system, so that a good experiment material can be provided for the establishment of a power equipment fault prediction model.
The modeling of the predictive maintenance of the current power equipment is mainly simulated by using historical data in a laboratory, an effective prediction model base which can be deployed in a dynamic loop monitoring system is not formed, and the model base is not used in a monitoring system which operates in real time, so that a proper method needs to be adopted, the model established by the experiment is effectively applied to an actual operating environment, the advance prediction of the fault is met, and the equipment is overhauled in advance.
Through the above analysis, the problems and defects of the prior art are as follows:
(1) in the prior art, because the power equipment is processed after the fault occurs, the hidden trouble that the normal operation of the communication main equipment is influenced due to the fact that the fault is not processed in time exists.
(2) The prior art does not form an effective power equipment fault prediction model library which can be deployed in a dynamic loop monitoring system, and is not used in a monitoring system which operates in real time.
(3) In the prior art, a method for dynamically updating a power equipment fault prediction model base does not exist.
The difficulty in solving the above problems and defects is:
one of the key difficulties in solving the problems in the prior art is the generation of a fault prediction model base, which allows different prediction methods to be used for generating different prediction models for different fault types, and the fault prediction model base can be used online, so that different fault types can be guaranteed to use effective prediction models to meet the best prediction effect; and secondly, dynamic updating of a fault prediction model base is carried out, so that the generated fault prediction model is prevented from being inaccurate, online or offline dynamic updating of the prediction model is allowed, and the fault prediction can be more satisfied with the actual field real condition.
The significance of solving the problems and the defects is as follows:
(1) the mode of fault processing after the fault occurs is changed, and the prediction is realized before the fault occurs, so that more sufficient time is provided for processing the fault, and the hidden trouble of shutdown caused by untimely equipment fault processing is avoided;
(2) the main purpose of power plant fault prediction is to predict faults before they occur, so an offline generated power plant prediction model must be deployed into an actual operating system to be functional.
(3) The more accurate the fault prediction is, the more the fault prediction plays a role in practical application, so the fault prediction model must be continuously updated according to actual operation data to make the fault prediction model more and more accurate, and therefore a dynamic training mechanism of the fault prediction model needs to be added.
Disclosure of Invention
Aiming at the problems in the prior art, the invention provides a method and an application system for online application of a power equipment fault prediction model. The invention can also be applied to other industrial equipment.
The invention is realized in such a way that a method for online application of a fault prediction model comprises the following steps:
classifying the power equipment fault prediction models generated by different prediction methods (adopting an RNN method, a logistic regression method and the like) according to the faults of different equipment, and generating an equipment fault prediction model library in an off-line manner;
deploying a fault prediction model library into an existing network operation system, performing equipment fault prediction on the current system, and generating a maintenance plan on line;
and (4) retraining the prediction model of the partial fault type, and updating the equipment fault prediction model library on line or off line.
Further, the offline generated equipment fault prediction model library generates fault prediction model libraries of different equipment by using historical alarm data and historical operation data according to faults generated by equipment of different models and based on different fault prediction methods.
Further, the library of predictive models includes three types of library structures: a fault model main library, a prediction method sub-library and a maintenance plan library;
the main fault model library is used for storing the prediction method indexes used by different faults of each equipment model;
the prediction method sub-library is used for storing characteristic parameters and evaluation parameters corresponding to different prediction methods adopted by different equipment according to different fault types, and the same prediction method can adopt the same prediction method sub-library.
The maintenance plan library is used for storing maintenance or maintenance plans, and the maintenance or maintenance plans are specifically maintenance or maintenance plans which are set according to the experience of experts and are adopted when the prediction evaluation index reaches a certain value.
Further, the online generation of the repair or maintenance plan includes: on the basis of the existing network dynamic loop monitoring system, equipment fault prediction model matching service is added in platform service, monitoring point data in a network system is collected in real time, characteristic matching is carried out on monitoring point characteristics corresponding to fault prediction models with different equipment models and different fault types and real-time data, when the matching rate reaches a set value, faults possibly occurring in equipment and the possible time of the faults are estimated, and a corresponding maintenance plan is given by combining a maintenance plan library.
Further, the device failure prediction model matching comprises:
and 2, performing characteristic matching according to the equipment fault prediction model base regularly or periodically.
Further, step 1 is implemented by using 1 thread, step 2 may be divided into 1 or n threads, or may be implemented by using a thread pool, and each thread may complete feature matching of one fault type or multiple fault types.
Further, the number of feature matching threads is divided according to the number of fault types in a fault prediction model library.
Further, the feature matching thread includes:
after the thread is started, the characteristic matching of a certain fault type is executed at regular time according to preset time, before the characteristic matching is carried out, the real-time data of the characteristic monitoring point corresponding to the fault type in the fault prediction model base is imported, the data is matched with the corresponding characteristic monitoring point in the prediction model base, and the actual evaluation parameter p of the equipment fault is obtained through calculation.
2-3 evaluation parameters can be set for different faults, and when p reaches the evaluation parameter set by the fault type in the prediction model library, different maintenance or repair plans are given by combining the experience of experts with the repair plan library;
and if p does not reach the specific value, continuing to match the fault model after the next set time is reached.
Further, the retraining of the model comprises:
monitoring faults generated in the dynamic loop monitoring system in real time, matching the detected relevant faults with the fault types in the equipment fault prediction model base, if the fault types do not exist in the fault prediction model base, performing no treatment, continuing to monitor the faults, and if the fault types are registered in the fault prediction model base, executing a subsequent retraining process.
Further, in the retraining process, firstly, real-time data of monitoring points related to detected faults are obtained, preprocessing and standardization processing are carried out on the real-time data, the processed data are added into a historical database which is subjected to standardization processing before to serve as an example of fault training, the example and historical data stored before serve as training data, the fault type prediction method in a fault model main base is utilized to carry out learning and training on the fault prediction model again, new parameters generated by training replace corresponding parameters of a prediction method sub-base in a prediction model base before, and one-time on-line updating of the fault prediction model is completed.
It is a further object of the invention to provide a computer device comprising a memory and a processor, the memory storing a computer program which, when executed by the processor, causes the processor to perform the steps of:
classifying the generated power equipment fault prediction model according to the faults of different equipment, and generating an equipment fault prediction model library in an off-line manner;
deploying a fault prediction model library into an existing network operation system, performing equipment fault prediction on the current system, and generating a maintenance plan on line;
and (4) retraining the prediction model of the partial fault type, and updating the equipment fault prediction model library on line or off line.
Another object of the present invention is to provide an online application system of a failure prediction model, comprising:
the model base generation module is used for generating an equipment fault prediction model base in an off-line manner;
the model matching module is used for generating a maintenance or service plan on line;
and the updating module is used for updating the equipment failure prediction model base on line or off line.
It is a further object of the present invention to provide a computer readable storage medium for storing a computer program, wherein the computer program, when invoked by a processor, implements a method for online application of a fault prediction model as described in any of the above.
By combining all the technical schemes, the invention has the advantages and positive effects that:
(1) the technical scheme provides a whole process scheme from generation of the prediction model base, online application and update and maintenance of the prediction model base.
(2) The generation of the fault prediction model base in the technical scheme is not only dependent on one fault prediction method, but also uses different prediction methods according to the characteristics of different fault types, thereby enhancing the accuracy of different fault predictions.
(3) According to the technical scheme, when the prediction model is applied to the system running in the network, different maintenance or maintenance plans can be implemented according to different failure prediction matching degrees, so that maintenance personnel can maintain the equipment more pertinently.
(4) When the technical scheme is applied to an actual system, the performance of the computer can be fully utilized, and the prediction of different faults can be processed in parallel, so that the on-line prediction rapidity and timeliness of the faults are improved.
(5) According to the technical scheme, when the fault prediction cannot meet the actual application requirement, the fault is dynamically updated, more fault prediction types can be added, and therefore the accuracy and the prediction capability of the equipment fault prediction are continuously improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed to be used in the embodiments of the present application will be briefly described below, and it is obvious that the drawings described below are only some embodiments of the present application, and it is obvious for those skilled in the art that other drawings can be obtained from the drawings without creative efforts.
Fig. 1 is a flowchart of a method for online application of a fault prediction model according to an embodiment of the present invention.
FIG. 2 is a diagram of the generation of a prediction model library and its application in a runtime environment according to an embodiment of the present invention.
Fig. 3 is a schematic diagram of an equipment failure prediction model library according to an embodiment of the present invention.
Fig. 4 is a thread allocation diagram of an equipment failure prediction model matching module according to an embodiment of the present invention.
Fig. 5 is a flowchart of a feature matching thread according to an embodiment of the present invention.
FIG. 6 is a diagram of a retraining process of an online failure prediction model according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is further described in detail with reference to the following embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
In view of the problems in the prior art, the present invention provides a method and an application system for online application of a power equipment fault prediction model, which are described in detail below with reference to the accompanying drawings.
Fig. 2 shows that the method for online application of the fault prediction model provided by the embodiment of the invention includes:
generating an equipment fault prediction model base in an off-line manner; generating a maintenance or service plan on line; and updating the equipment failure prediction model library online or offline.
In the invention, the off-line generation of the equipment failure prediction model library comprises the following steps:
because the related data volume is large, the operation of the equipment fault prediction model library takes a certain time, and meanwhile, the correctness of the established prediction model needs to be verified, so that the part is completed in a laboratory.
And aiming at the faults generated by different equipment, generating fault prediction models of the different equipment by using historical alarm data and historical operation data based on different fault prediction methods, wherein the different equipment refers to equipment with different models. And combining the equipment fault prediction models generated by different equipment models and different fault types to form an equipment fault prediction model library.
As shown in fig. 3, which is a schematic diagram of an equipment failure prediction model library provided in the embodiment of the present invention, the prediction model library may include three types of library structures: the system comprises a fault model main library, each prediction method sub-library and a maintenance plan library.
The main fault model library is mainly used for storing indexes of prediction methods used by different faults of each equipment model, and the stored contents include but are not limited to the following parts: model number, equipment model, fault type, method library number, and method library name.
For different fault types, in order to achieve a better prediction effect, the adopted prediction methods are different, for example, an RNN method, a logistic regression method, and the like can be adopted, the contents of the parts are stored in a prediction method sub-library, and the same prediction method can adopt the same prediction method sub-library. For example, if the effect of the prediction model of a certain fault type is ideal by using a logistic regression method, the prediction method sub-library needs to include the relevant parameters of the prediction method, and the contents in the library may include sub-library number, model number, feature point 1 correlation coefficient, feature point 2 correlation coefficient, … …, feature point n, feature n correlation coefficient, intercept, error term, fault occurrence probability evaluation value 1, fault occurrence probability evaluation value 2, fault occurrence probability evaluation value 3, and the like. The failure probability evaluation value refers to further processing which is required to be performed when the evaluation index reaches the evaluation index of the failure probability in the online operation process of the system, namely, different maintenance or maintenance plans are given according to different possibilities of the failure probability. The number of the evaluation parameters in the prediction method sub-library can be set to be 2-3.
The maintenance or repair plan is stored in a repair plan library, which may also be referred to as an expert experience library, that is, what maintenance or repair plan is to be taken when the prediction evaluation index reaches a certain value is set according to the experience of an expert.
In the present invention, generating a repair or maintenance plan online includes:
after the offline fault prediction model base is generated, equipment fault prediction needs to be carried out on the current system according to the built model, so that the fault prediction model base needs to be deployed into the current network operating system for prediction analysis to generate a maintenance or maintenance plan for a decision maker to make a decision, and the part of work needs to be completed on line.
The invention is based on the present network dynamic loop monitoring system, an equipment failure prediction model matching module is added in the platform service, the module collects the monitoring point data in the network system in real time, carries out characteristic matching according to the monitoring point characteristics corresponding to the failure prediction models of different equipment models and different failure types and the real-time data, when the matching rate reaches a set value, predicts the failure which possibly occurs to the equipment and the possible time of the failure, and combines an expert experience base to give a corresponding maintenance plan.
The module is designed in two parts: the first part classifies the characteristic monitoring points, namely, all monitoring point data collected in real time are classified and stored according to the fault types in the equipment fault prediction model base; and the other part is that the characteristic matching is carried out according to the equipment failure prediction model library regularly or periodically.
The first part is realized by 1 thread, while the second part can be divided into 1 or n threads, or realized by thread pool, and each thread can complete the feature matching of one fault type or multiple fault types. Fig. 4 is a thread allocation diagram of the device failure prediction model matching module according to an embodiment of the present invention.
Wherein x, y and z are more than or equal to 1 and less than or equal to 3, which can be equal or unequal, and a thread is recommended to process 3 fault types at most.
In fig. 4, the number of feature matching threads is divided according to the number of fault types in the fault prediction model library, for example, the fault prediction model library includes 50 fault types, 3 fault types are processed according to one thread, and 17 feature matching threads are required to be established.
Fig. 5 is a flowchart of a feature matching thread according to an embodiment of the present invention:
after the thread is started, the characteristic matching of a certain fault type is executed at fixed time according to a preset time t. Before feature matching, feature monitoring point real-time data corresponding to the fault type in a fault prediction model base needs to be imported, the data is matched with the corresponding feature monitoring point in the prediction model base, and an actual evaluation parameter p of the equipment fault is calculated and obtained.
2-3 evaluation parameters can be set for different faults, and when p reaches the evaluation parameter set by the fault type in the prediction model library, different maintenance or repair plans are given by using the experience of experts in combination with the experience of the experts. In fig. 4, p3> p2> p 1.
And if p does not reach the specific value, continuing to match the fault model after the next set time is reached, and repeating the steps.
In the invention, the online or offline updating of the equipment failure prediction model library comprises the following steps:
and updating the fault prediction model base, namely retraining the prediction model of partial fault types after the system runs for a period of time so as to achieve a better prediction effect.
The retraining of the model can adopt two methods, one method is that historical monitoring point data is manually derived off-line at regular intervals, a method which is the same as that of an off-line generation equipment fault prediction model is adopted to retrain a part of the fault prediction model, a new fault prediction model is updated into a fault prediction model base, and meanwhile, a new fault prediction model can be added to be stored in a base.
And the other method adopts an online method to update the fault prediction model base. On the basis of the existing network dynamic loop monitoring system, the invention adds an equipment fault prediction model retraining module in platform service, the module runs in real time, and the retraining process is shown in figure 6.
The module monitors faults generated in the dynamic loop monitoring system in real time, supposing that the system detects related faults G, the faults are matched with fault types in the equipment fault prediction model base, if the fault types do not exist in the fault prediction model base, no processing is carried out, and the faults are continuously monitored.
If the fault type is registered in the fault prediction model library, a subsequent retraining process is performed.
The invention also provides a fault prediction model online application system, which comprises:
and the model base generation module is used for generating an equipment fault prediction model base in an off-line manner.
And the model matching module is used for generating a maintenance or service plan on line.
And the updating module is used for updating the equipment failure prediction model base on line or off line.
In the description of the present invention, "a plurality" means two or more unless otherwise specified; the terms "upper", "lower", "left", "right", "inner", "outer", "front", "rear", "head", "tail", and the like, indicate orientations or positional relationships based on the orientations or positional relationships shown in the drawings, are only for convenience in describing and simplifying the description, and do not indicate or imply that the device or element referred to must have a particular orientation, be constructed in a particular orientation, and be operated, and thus, should not be construed as limiting the invention. Furthermore, the terms "first," "second," "third," and the like are used for descriptive purposes only and are not to be construed as indicating or implying relative importance.
The above description is only for the purpose of illustrating the present invention and the appended claims are not to be construed as limiting the scope of the invention, which is intended to cover all modifications, equivalents and improvements that are within the spirit and scope of the invention as defined by the appended claims.
Claims (10)
1. A method for online application of a fault prediction model is characterized in that the method for online application of the fault prediction model comprises the following steps:
classifying the generated power equipment fault prediction model according to the faults of different equipment, and generating an equipment fault prediction model library in an off-line manner;
deploying a fault prediction model library into an existing network operation system, performing equipment fault prediction on the current system, and generating a maintenance plan on line;
and (4) retraining the prediction model of the partial fault type, and updating the equipment fault prediction model library on line or off line.
2. The method for online application of a fault prediction model according to claim 1, wherein the offline generation of the device fault prediction model library generates the fault prediction model library of different devices based on different fault prediction methods by using historical alarm data and historical operating data for faults generated by different types of devices.
3. The method for online application of a fault prediction model of claim 2, wherein the library of prediction models comprises: a fault model main library, a prediction method sub-library and a maintenance plan library;
the main fault model library is used for storing the prediction method indexes used by different faults of each equipment model;
the prediction method sub-library is used for storing characteristic parameters and evaluation parameters corresponding to different prediction methods adopted by different types of faults of different equipment models, and the same prediction method adopts the same prediction method sub-library;
the maintenance plan library is used for storing maintenance or maintenance plans, and the maintenance or maintenance plans are specifically maintenance or maintenance plans which are set according to the experience of experts and are adopted when the prediction evaluation index reaches a certain value.
4. The method for online application of a fault prediction model of claim 1, wherein the online generation of a repair or maintenance plan comprises: adding equipment fault prediction model matching service in platform service, collecting monitoring point data in a network system in real time, performing characteristic matching between monitoring point characteristic parameters corresponding to fault prediction models of different equipment models and different fault types and real-time data, estimating possible faults of equipment and possible time of the faults when the matching rate reaches a set value, and providing a corresponding maintenance plan by combining a maintenance plan library.
5. The method for online application of a fault prediction model according to claim 4, wherein the method for matching of the equipment fault prediction model comprises:
step 1, classifying the characteristic monitoring points, and classifying and storing the characteristics of all monitoring point data acquired in real time according to the fault types in the equipment fault prediction model base;
and 2, performing characteristic matching according to the equipment fault prediction model base regularly or periodically.
6. The method for online application of the failure prediction model according to claim 5, wherein the step 1 is implemented by 1 thread, the step 2 is divided into 1 or n threads, or implemented by using a thread pool, and each thread completes feature matching of one failure type or multiple failure types;
the number of the characteristic matching threads is divided according to the number of fault types in a fault prediction model library;
the feature matching thread comprises: after the thread is started, executing feature matching of a certain fault type at regular time according to preset time, before feature matching, importing feature monitoring point real-time data corresponding to the fault type in a fault prediction model base, matching the data with corresponding feature monitoring points in the prediction model base, and calculating to obtain an actual evaluation parameter p of the equipment fault;
2-3 evaluation parameters can be set for different faults, and when p reaches the evaluation parameter set by the fault type in the prediction model library, different maintenance or repair plans are given by combining the experience of experts with the repair plan library;
and if p does not reach the specific value, continuing to match the fault model after the next set time is reached.
7. The method for online application of a fault prediction model of claim 1, wherein the retraining of the model comprises:
monitoring faults generated in a dynamic loop monitoring system in real time, matching the detected related faults with fault types in an equipment fault prediction model base, if the fault types do not exist in the fault prediction model base, performing no treatment, continuing to monitor the faults, and if the fault types are registered in the fault prediction model base, executing a subsequent retraining process;
in the retraining process, firstly, acquiring real-time data of a monitoring point related to the detected fault, preprocessing and standardizing the real-time data, adding the processed data into a historical database which is subjected to the standardized processing before as an example of the fault training, using the example and the historical data stored before as training data, re-learning and training the fault prediction model by using the fault type prediction method in the fault model main library, and replacing corresponding parameters of a prediction method sub-library in the prediction model library before with new parameters generated by training to finish the on-line updating of the fault prediction model.
8. A fault prediction model online application system, comprising:
the model base generation module is used for generating an equipment fault prediction model base in an off-line manner;
the model matching module is used for generating a maintenance or service plan on line;
and the updating module is used for updating the equipment failure prediction model base on line or off line.
9. A computer device, characterized in that the computer device comprises a memory and a processor, the memory storing a computer program which, when executed by the processor, causes the processor to carry out the steps of:
classifying the generated power equipment fault prediction model according to the faults of different equipment, and generating an equipment fault prediction model library in an off-line manner;
deploying a fault prediction model library into an existing network operation system, performing equipment fault prediction on the current system, and generating a maintenance plan on line;
and (4) retraining the prediction model of the partial fault type, and updating the equipment fault prediction model library on line or off line.
10. A computer-readable storage medium for storing a computer program, wherein the computer program, when invoked by a processor, implements a method for online application of a fault prediction model as claimed in any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011024022.3A CN112286088A (en) | 2020-09-25 | 2020-09-25 | Method and application system for online application of power equipment fault prediction model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011024022.3A CN112286088A (en) | 2020-09-25 | 2020-09-25 | Method and application system for online application of power equipment fault prediction model |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112286088A true CN112286088A (en) | 2021-01-29 |
Family
ID=74421344
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011024022.3A Pending CN112286088A (en) | 2020-09-25 | 2020-09-25 | Method and application system for online application of power equipment fault prediction model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112286088A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113013985A (en) * | 2021-02-20 | 2021-06-22 | 四川智水信息技术有限公司 | Transformer substation operation and maintenance method and device |
| CN113156243A (en) * | 2021-04-09 | 2021-07-23 | 南方电网电动汽车服务有限公司 | Fault prediction method and prediction system |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106842106A (en) * | 2017-02-23 | 2017-06-13 | 广东电网有限责任公司茂名供电局 | Electrical energy meter fault Forecasting Methodology and device |
| CN106981873A (en) * | 2017-04-25 | 2017-07-25 | 集美大学 | A kind of isolated island formula power system based on dynamic behavior is hidden failure prediction method |
| CN108520080A (en) * | 2018-05-11 | 2018-09-11 | 武汉理工大学 | Automatic system of marine diesel-generator failure predication and health status online evaluation system and method |
| CN108681747A (en) * | 2018-05-11 | 2018-10-19 | 武汉理工大学 | Rotary machinery fault diagnosis based on deep learning and condition monitoring system and method |
| CN109783461A (en) * | 2017-11-15 | 2019-05-21 | 波音公司 | Real-time crossfire for flight visual simulation is analyzed |
-
2020
- 2020-09-25 CN CN202011024022.3A patent/CN112286088A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106842106A (en) * | 2017-02-23 | 2017-06-13 | 广东电网有限责任公司茂名供电局 | Electrical energy meter fault Forecasting Methodology and device |
| CN106981873A (en) * | 2017-04-25 | 2017-07-25 | 集美大学 | A kind of isolated island formula power system based on dynamic behavior is hidden failure prediction method |
| CN109783461A (en) * | 2017-11-15 | 2019-05-21 | 波音公司 | Real-time crossfire for flight visual simulation is analyzed |
| CN108520080A (en) * | 2018-05-11 | 2018-09-11 | 武汉理工大学 | Automatic system of marine diesel-generator failure predication and health status online evaluation system and method |
| CN108681747A (en) * | 2018-05-11 | 2018-10-19 | 武汉理工大学 | Rotary machinery fault diagnosis based on deep learning and condition monitoring system and method |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113013985A (en) * | 2021-02-20 | 2021-06-22 | 四川智水信息技术有限公司 | Transformer substation operation and maintenance method and device |
| CN113156243A (en) * | 2021-04-09 | 2021-07-23 | 南方电网电动汽车服务有限公司 | Fault prediction method and prediction system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108375715B (en) | Power distribution network line fault risk day prediction method and system | |
| US20170082665A1 (en) | Detecting Non-Technical Losses in Electrical Networks Based on Multi-Layered Statistical Techniques from Smart Meter Data | |
| JP2018180759A (en) | System analysis system and system analysis method | |
| CN114267178B (en) | Intelligent operation maintenance method and device for station | |
| WO2021005943A1 (en) | Failure probability assessment system and method therefor | |
| CN112286088A (en) | Method and application system for online application of power equipment fault prediction model | |
| US20190048740A1 (en) | Turbine diagnostic feature selection system | |
| CN116843071B (en) | Transportation network operation index prediction method and device for intelligent port | |
| CN112257745A (en) | Hidden Markov-based method and device for predicting health degree of underground coal mine system | |
| CN115562225A (en) | Industrial robot operation and maintenance management method and device, computer equipment and storage medium | |
| CN115438726A (en) | Device life and fault type prediction method and system based on digital twin technology | |
| CN111027116A (en) | Building operation and maintenance management method and device, computer equipment and storage medium | |
| CN115421950A (en) | Automatic system operation and maintenance management method and system based on machine learning | |
| Borissova et al. | A concept of intelligent e-maintenance decision making system | |
| CN116384876A (en) | Spare part dynamic inventory-production control method, system and medium based on wiener process | |
| Lin et al. | Hpt-rl: Calibrating power system models based on hierarchical parameter tuning and reinforcement learning | |
| EP3413153A1 (en) | Method and distributed control system for carrying out an automated industrial process | |
| CN114676021A (en) | Job log monitoring method and device, computer equipment and storage medium | |
| Baptista et al. | Aircraft on-condition reliability assessment based on data-intensive analytics | |
| Liu et al. | On-line adaptive data-driven fault prognostics of complex systems | |
| Gruber et al. | Condition‐Based Maintenance v ia a Targeted B ayesian Network Meta‐Model | |
| CN112966785B (en) | Intelligent constellation state identification method and system | |
| Perlov et al. | Failure Forecasting System by the Diagnostic Data of the Radio Information Systems | |
| Hu et al. | Online fault prognostics based on degradation-oriented slow feature analysis and temporal smoothness analysis | |
| JP7257455B2 (en) | Method and monitoring system for monitoring controller decision logic performance |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210129 |
|
| RJ01 | Rejection of invention patent application after publication |