CN117972493A - Method and device for diagnosing faults of power exchange station equipment, electronic equipment and storage medium - Google Patents
Method and device for diagnosing faults of power exchange station equipment, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN117972493A CN117972493A CN202410156653.2A CN202410156653A CN117972493A CN 117972493 A CN117972493 A CN 117972493A CN 202410156653 A CN202410156653 A CN 202410156653A CN 117972493 A CN117972493 A CN 117972493A
- Authority
- CN
- China
- Prior art keywords
- exchange station
- fault
- fault diagnosis
- equipment
- data
- 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
- 238000000034 method Methods 0.000 title claims abstract description 70
- 238000003745 diagnosis Methods 0.000 claims abstract description 120
- 238000012423 maintenance Methods 0.000 claims description 13
- 230000015654 memory Effects 0.000 claims description 13
- 238000012549 training Methods 0.000 claims description 10
- 238000000605 extraction Methods 0.000 claims description 5
- 238000004422 calculation algorithm Methods 0.000 description 18
- 238000004458 analytical method Methods 0.000 description 14
- 230000007246 mechanism Effects 0.000 description 9
- 238000005457 optimization Methods 0.000 description 8
- 238000004590 computer program Methods 0.000 description 6
- 238000010801 machine learning Methods 0.000 description 6
- 230000006870 function Effects 0.000 description 5
- 230000007613 environmental effect Effects 0.000 description 4
- 238000005259 measurement Methods 0.000 description 4
- 238000013136 deep learning model Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000011156 evaluation Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000012360 testing method Methods 0.000 description 3
- 239000002131 composite material Substances 0.000 description 2
- 238000003066 decision tree Methods 0.000 description 2
- 238000013507 mapping Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000007637 random forest analysis Methods 0.000 description 2
- 238000007619 statistical method Methods 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 238000012706 support-vector machine Methods 0.000 description 2
- 206010000117 Abnormal behaviour Diseases 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 238000005299 abrasion Methods 0.000 description 1
- 230000006978 adaptation Effects 0.000 description 1
- 230000032683 aging Effects 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 238000013499 data model Methods 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 238000007599 discharging Methods 0.000 description 1
- 238000011478 gradient descent method Methods 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 230000003862 health status Effects 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- YHXISWVBGDMDLQ-UHFFFAOYSA-N moclobemide Chemical compound C1=CC(Cl)=CC=C1C(=O)NCCN1CCOCC1 YHXISWVBGDMDLQ-UHFFFAOYSA-N 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000001502 supplementing effect Effects 0.000 description 1
- 238000012731 temporal analysis Methods 0.000 description 1
- 238000000700 time series analysis Methods 0.000 description 1
- 238000011282 treatment Methods 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Landscapes
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The application relates to the technical field of power exchange stations, in particular to a power exchange station equipment fault diagnosis method, a device, electronic equipment and a storage medium, and aims to solve the technical problems of low efficiency and poor fault coverage rate caused by manual implementation of the existing fault diagnosis method. For this purpose, the method for diagnosing the fault of the power exchange station equipment of the application comprises the following steps: collecting data information of the battery pack and the battery replacement equipment; extracting data characteristics of the battery exchange station based on data information of the battery exchange equipment and the battery pack; obtaining a fault diagnosis model; and performing fault diagnosis on the power exchange station equipment based on the data characteristics of the power exchange station by using a fault diagnosis model. Therefore, the fault diagnosis precision of the power exchange station equipment is improved, and the coverage efficiency of diagnosis of all fault components is improved.
Description
Technical Field
The application relates to the technical field of power exchange stations, and particularly provides a power exchange station equipment fault diagnosis method, a device, electronic equipment and a storage medium.
Background
At present, battery replacement service is a key element for guaranteeing convenience of long-distance travel of an electric automobile, one of important energy supplementing modes is gradually increased along with the gradual increase of a power exchange station, the use abrasion degree of machine parts of the power exchange station is increased along with the long-time operation of equipment and the influence of environmental factors, the damage of the parts is increased, a large number of potential failure modes possibly exist, but a large part of the potential failure modes cannot be found and recalled in time in the early stage, so that unattended pressure of the power exchange station is increased, and the enterprise cost is increased gradually.
The existing failure mode analysis method mainly comprises the steps of analyzing based on the previous mechanism knowledge, structural deformation and the like after the components are damaged, and lacks a data-driven method, so that the analysis of each non-recalled part is very labor-consuming, a great amount of time is required for checking the mechanism and the analysis after the fact, and the online coverage efficiency of an algorithm is very low.
Accordingly, there is a need in the art for a new battery plant fault diagnosis solution to address the above-mentioned problems.
Content of the application
The present application has been made to overcome the above-mentioned drawbacks, and to provide a solution or at least partially solve the above-mentioned technical problems. The application provides a method and a device for diagnosing faults of power exchange station equipment, electronic equipment and a storage medium.
In a first aspect, the present application provides a method for diagnosing a fault in a power exchange station apparatus, the method comprising:
Collecting data information of the battery pack and the battery replacement equipment;
Extracting data characteristics of the battery exchange station based on the data information of the battery exchange equipment and the battery pack;
obtaining a fault diagnosis model;
and performing fault diagnosis on the power exchange station equipment based on the power exchange station data characteristics by using the fault diagnosis model.
In one embodiment of the application, the fault diagnosis model is obtained by training the following steps:
Obtaining a plurality of historical fault sample data in a power exchange station, and adding a sample label for each historical fault sample data;
determining initial model parameters based on the historical fault sample data and sample labels corresponding to the historical fault sample data;
determining optimal model parameters based on the initial model parameters and a first preset threshold;
And obtaining the fault diagnosis model based on the optimal model parameters.
In one embodiment of the present application, the determining the initial model parameter based on the historical fault sample data and the sample label corresponding to the historical fault sample data includes:
extracting historical fault sample features based on the historical fault sample data;
Inputting each historical fault sample feature and a sample label corresponding to the historical fault sample data into a fault diagnosis model to obtain a prediction result;
And adjusting model parameters of the fault diagnosis model based on the prediction result and the label until the fault diagnosis model converges, so as to obtain the initial model parameters.
In one embodiment of the present application, after adding a sample tag to each of the historical fault sample data and before determining an initial model parameter based on the historical fault sample data and a sample tag corresponding to the historical fault sample data, the method further comprises: the sample tags are classified based on the type of failure of the power exchange station equipment.
In one embodiment of the application, the method further comprises:
determining an accuracy rate and a recall rate based on the prediction result;
determining an accuracy of the fault diagnosis model based on the precision rate and the recall rate;
Judging whether any one of the precision rate, the recall rate and the precision is greater than a second preset threshold;
If not, continuing to train the fault diagnosis model based on the historical fault sample data and the sample label.
In one embodiment of the application, the data information comprises a power exchange equipment fault signal, power exchange equipment fault data, power exchange equipment operating state data and battery pack data information in the power exchange station.
In one embodiment of the application, the method further comprises:
generating a fault diagnosis report based on the fault diagnosis result of the power exchange station equipment; and/or
And generating a maintenance scheme of the fault equipment of the power exchange station based on the fault diagnosis result of the power exchange station.
In a second aspect, the present application provides a power exchange station equipment fault diagnosis apparatus, the apparatus comprising:
the acquisition module is used for acquiring data information of the battery pack and the battery replacement equipment;
the extraction module is used for extracting the data characteristics of the battery exchange station based on the data information of the battery exchange equipment and the battery pack;
the acquisition module is used for acquiring the fault diagnosis model;
And the diagnosis module is used for diagnosing faults of the power exchange station equipment based on the data characteristics of the power exchange station by utilizing the fault diagnosis model.
In a third aspect, an electronic device is provided, comprising at least one processor and at least one memory adapted to store a plurality of program code adapted to be loaded and executed by the processor to perform the battery exchange station fault diagnosis method of any of the preceding claims.
In a fourth aspect, a computer readable storage medium is provided, in which a plurality of program codes are stored, which program codes are adapted to be loaded and run by a processor to perform the battery exchange station fault diagnosis method of any of the preceding claims.
The technical scheme provided by the application has at least one or more of the following beneficial effects:
The application relates to a fault diagnosis method for power exchange station equipment, which specifically comprises the following steps: collecting data information of the battery pack and the battery replacement equipment; extracting data characteristics of the battery exchange station based on data information of the battery exchange equipment and the battery pack; obtaining a fault diagnosis model; and performing fault diagnosis on the power exchange station equipment based on the data characteristics of the power exchange station by using a fault diagnosis model. Therefore, the fault equipment of the power exchange station can be accurately and efficiently diagnosed by utilizing the pre-trained model, so that the timely recall of the fault equipment is realized, the labor cost is reduced, and the fault diagnosis precision and the fault diagnosis coverage rate of the power exchange station equipment are improved.
Drawings
The present disclosure will become more readily understood with reference to the accompanying drawings. As will be readily appreciated by those skilled in the art: the drawings are for illustrative purposes only and are not intended to limit the scope of the present application. Moreover, like numerals in the figures are used to designate like parts, wherein:
FIG. 1 is a flow chart illustrating the main steps of a method for diagnosing a fault in a power exchange plant according to one embodiment of the present application;
FIG. 2 is a schematic diagram of a complete flow of a method for diagnosing a fault in a power exchange plant in an embodiment of the present application;
FIG. 3 is a schematic flow chart of a method for diagnosing a fault in a power exchange plant according to another embodiment of the present application;
FIG. 4 is a schematic block diagram of the major structure of a power plant equipment fault diagnosis apparatus according to one embodiment of the present application;
fig. 5 is a schematic structural view of an electronic device according to an embodiment of the present application.
Detailed Description
Some embodiments of the application are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are merely for explaining the technical principles of the present application, and are not intended to limit the scope of the present application.
In the description of the present application, a "module," "processor" may include hardware, software, or a combination of both. A module may comprise hardware circuitry, various suitable sensors, communication ports, memory, or software components, such as program code, or a combination of software and hardware. The processor may be a central processor, a microprocessor, an image processor, a digital signal processor, or any other suitable processor. The processor has data and/or signal processing functions. The processor may be implemented in software, hardware, or a combination of both. Non-transitory computer readable storage media include any suitable medium that can store program code, such as magnetic disks, hard disks, optical disks, flash memory, read-only memory, random access memory, and the like. The term "a and/or B" means all possible combinations of a and B, such as a alone, B alone or a and B. The term "at least one A or B" or "at least one of A and B" has a meaning similar to "A and/or B" and may include A alone, B alone or A and B. The singular forms "a", "an" and "the" include plural referents.
At present, the traditional failure mode analysis method mainly comprises the steps of analyzing based on the previous mechanism knowledge, structural deformation and the like after the components are damaged, and lacks a data-driven method, so that the analysis of each non-recalled part is very labor-consuming, a great deal of time is required for checking the mechanism and the analysis after the fact, and the online coverage efficiency of an algorithm is very low.
Therefore, the application provides a fault diagnosis method for power exchange station equipment, which comprises the following steps: collecting data information of the battery pack and the battery replacement equipment; extracting data characteristics of the battery exchange station based on data information of the battery exchange equipment and the battery pack; obtaining a fault diagnosis model; and performing fault diagnosis on the power exchange station equipment based on the data characteristics of the power exchange station by using a fault diagnosis model. Therefore, the fault equipment of the power exchange station can be accurately and efficiently diagnosed by utilizing the pre-trained model, so that the timely recall of the fault equipment is realized, the labor cost is reduced, and the fault diagnosis precision and the fault diagnosis coverage rate of the power exchange station equipment are improved.
Referring to fig. 1, fig. 1 is a schematic flow chart of main steps of a fault diagnosis method for a power exchange station according to an embodiment of the present application. As shown in fig. 1, the fault diagnosis method for the power exchange station equipment in the embodiment of the present application mainly includes the following steps S101 to S104.
Step S101: and collecting data information of the battery pack and the battery exchange equipment.
In one embodiment of the present application, the data information includes a power exchange device fault signal in the power exchange station, power exchange device fault data, power exchange device operation state data, and battery pack data information.
Specifically, the battery exchange device operating state data includes, but is not limited to, battery exchange station and charging pile component operating temperatures, current and voltage readings, device start-up and shut-down times, and the like.
The battery pack data information includes, but is not limited to, key data such as voltage, current, temperature curve, SOC (State of Charge), SOH (State of Health), battery cycle number, cell consistency, self-discharge rate, internal resistance change trend, etc. of the battery during charging and discharging.
The battery exchange equipment fault data includes the position of the component, the name of the component, the time of failure, etc. when the battery exchange equipment fails.
In addition, in other embodiments, environmental condition data of the plant equipment may be collected, such as environmental temperature and humidity, light intensity, atmospheric pressure, etc. within the plant, which may indirectly affect the operating conditions of the equipment and the battery.
Step S102: and extracting the data characteristics of the battery exchange station based on the data information of the battery exchange equipment and the battery pack.
After the data of the battery replacement equipment and the battery pack are collected, the data are preprocessed to remove abnormal values and fill missing values, and are converted into a format suitable for machine learning model analysis. Next, features reflecting the health status of the power exchange station are extracted using statistical methods and data mining techniques.
Illustratively, the equipment status features are taken as examples, such as the operating efficiency of the equipment, fatigue indicators (based on run time and load changes), life predictions (based on accumulated wear and maintenance records), and so forth.
Illustratively, battery pack performance characteristics such as battery capacity fade characteristics, thermal runaway risk indicators, imbalance coefficients, and the like are taken as examples.
Time series features, such as time series analysis of continuous device and battery status data, may also be included to extract periodic, trending and mutability features.
Step S103: and obtaining a fault diagnosis model.
The fault diagnosis model includes, but is not limited to, a machine learning model, a time series prediction model, a deep learning model, a mechanism model, or the like.
Taking a machine learning model as an example, the machine learning algorithm can be selected from any one of models such as decision trees, support vector machines, random forests, deep neural networks and the like.
Taking the time series prediction model as an example, the selected time series prediction model may be any one of models such as ARIMA, prophet, LSTM.
Step S104: and performing fault diagnosis on the power exchange station equipment based on the power exchange station data characteristics by using the fault diagnosis model.
Specifically, the data characteristics of the power exchange station are input into the fault diagnosis model to perform fault diagnosis on the power exchange station equipment, and the position and the fault time of the fault equipment of the power exchange station can be obtained.
For intelligent battery-changing stations, there are algorithm-based early warning and recall mechanisms. When the monitoring system predicts potential faults through data analysis, an algorithm recall event is triggered, and a corresponding alarm notification is generated. The algorithmic recalled data should include: the time of the predicted failure, the type of failure, the location of the failure, the recall level (urgency), the comparison of actual failure with predicted failure, and whether maintenance service is scheduled in advance accordingly.
Based on the steps S101-S104, firstly, collecting data information of the battery replacement equipment and the battery pack; extracting data characteristics of the battery exchange station based on data information of the battery exchange equipment and the battery pack; obtaining a fault diagnosis model; and performing fault diagnosis on the power exchange station equipment based on the data characteristics of the power exchange station by using a fault diagnosis model. Therefore, the fault equipment of the power exchange station can be accurately and efficiently diagnosed by utilizing the pre-trained model, so that the timely recall of the fault equipment is realized, the labor cost is reduced, the fault diagnosis precision of the power exchange station equipment is improved, and the coverage efficiency of the diagnosis of all fault components is improved.
In one embodiment of the present application, the fault diagnosis model is obtained through training in step S201 to step S204 described below.
Step S201: obtaining a plurality of historical fault sample data in the power exchange station, and adding a sample label to each historical fault sample data.
Specifically, failure cases, details of a replacement work order, whether an algorithm recall exists or not and the like of all parts of the power exchange station equipment in history are collected, a plurality of historical fault sample data in the power exchange station are obtained through the data, and the data are stored in a mysql offline table mode, so that follow-up inquiry is facilitated.
Specifically, all historical failure cases involving critical components of the power exchange station are collected, such as a detailed record of the time stamp of each failure event, the specific model and serial number of the failed component, failure modes (e.g., wear, aging, shorting, etc.), failure cause analysis reports, and related picture or video data.
The details of the replacement work order are another important data source, and the details not only comprise the actual replacement operation record of the failed component, but also comprise the contents of work order starting time, predicted completion time, actual completion time, technician information for executing maintenance tasks, new component model and serial numbers of replacement, test results after replacement and the like. According to the replacement work order, a maintenance scheme can be provided for the fault equipment of the subsequent replacement station.
To ensure data consistency and query efficiency, all of the information described above needs to be stored in a structured MySQL offline database table. Therefore, statistics of failure frequency of components in a specific time period, analysis of processing efficiency of a work order and retrospective verification of algorithm prediction accuracy can be realized quickly and conveniently, so that powerful data support is provided for optimizing operation and maintenance strategies of a power exchange station, improving service quality, reducing downtime and reducing operation cost.
After obtaining a plurality of historical fault sample data in the power exchange station, a sample label can be manually added to each historical fault sample data, or a sample label is added to each historical fault sample data by adopting a data adding labeling method which is conventional in the art, and the specific mode for adding the label is not particularly limited.
In one embodiment of the present application, after adding a sample tag to each of the historical fault sample data and before determining an initial model parameter based on the historical fault sample data and a sample tag corresponding to the historical fault sample data, the method further comprises: the sample tags are classified based on the type of failure of the power exchange station equipment.
Specifically, since the parts of the power exchange station are very many and the historical failures are very redundant, the total use of the parts can lead to a large amount of noise of the data set, so that the mechanism analysis is needed to be carried out on different failure modes, and the label classification is carried out, wherein the label classification comprises one-level, two-level, three-level and other multi-level failure mode classification, a data base is laid for a subsequent back algorithm, and the fault prediction model can be trained according to the classified labels and corresponding historical sample data, so that the training precision of the fault prediction model is improved.
Step S202: and determining initial model parameters based on the historical fault sample data and sample labels corresponding to the historical fault sample data.
In one embodiment of the present application, the determining the initial model parameter based on the historical fault sample data and the sample label corresponding to the historical fault sample data includes: extracting historical fault sample features based on the historical fault sample data; inputting each historical fault sample feature and a sample label corresponding to the historical fault sample data into a fault diagnosis model to obtain a prediction result; and adjusting model parameters of the fault diagnosis model based on the prediction result and the label until the fault diagnosis model converges, so as to obtain the initial model parameters.
Specifically, the historical failure cases of all parts of the power exchange station and the details of the work orders thereof are subjected to deep analysis, and key features with representative and predictive values are extracted from the failure cases. These features may include, but are not limited to, information in multiple dimensions of component type, age, workload, environmental conditions, maintenance records, abnormal behavior patterns before failure, frequency of replacement, etc. And performing treatments such as dimension reduction, normalization, missing value filling and the like on the original data through a statistical method and a machine learning algorithm to form a structured historical fault sample feature set.
After the historical fault sample features are obtained, each sample feature is associated with its corresponding fault category or severity (i.e., sample label) to construct a training dataset. The labels are accurate classification information obtained through expert evaluation according to actual fault conditions or according to past maintenance records.
Next, feature-tag pairs are input into the fault diagnosis model for training. The model can be a supervised learning model such as decision trees, random forests, support vector machines, or a more complex neural network model such as deep learning model. The model attempts to minimize the difference between the predicted result and the real label by learning the law of mapping from the input features to the output labels.
In the training process, the model parameters are gradually adjusted by using an optimization algorithm (such as a gradient descent method or other iterative optimization strategies), the internal weight distribution and the structure setting of the model are continuously updated so as to improve the performance capability of the model on a training set, and the iteration is repeated until the model performance index reaches a convergence state.
Finally, the set of model parameters obtained when the model training converges is the initial model parameters. The set of parameters enables the fault diagnosis model to provide more accurate fault prediction and diagnosis conclusions based on new input characteristic data, thereby serving an intelligent operation and fault prevention system of the power exchange station.
The plurality of historical fault sample data may determine a plurality of initial model parameters.
Step S203: and determining optimal model parameters based on the initial model parameters and a first preset threshold.
The first preset threshold may be a suitable threshold found automatically by an optimization class algorithm including, but not limited to, grid search, random search, threshold optimization function, threshold adaptation, and the like.
For example, grid search (GRID SEARCH), which is an exhaustive method, trains a model for each threshold by traversing a predefined list of thresholds and calculates a corresponding evaluation index (e.g., F1 score, area under AUC-ROC curve, etc.), and finally selects the threshold with the optimal index.
And respectively comparing the plurality of initial model parameters with a first preset threshold value, and taking a group of initial model parameters smaller than the first preset threshold value as optimal model parameters.
Step S204: and obtaining the fault diagnosis model based on the optimal model parameters.
The obtained fault diagnosis model based on the optimal model parameters can be deployed into practical application, the state of the power exchange station equipment is monitored in real time, potential faults are early-warned in time according to the model prediction result, and therefore equipment operation and maintenance efficiency is improved, and shutdown risks are reduced.
In one embodiment of the present application, the method further comprises: determining an accuracy rate and a recall rate based on the prediction result; determining an accuracy of the fault diagnosis model based on the precision rate and the recall rate; judging whether the precision rate, the recall rate and the precision are greater than a second preset threshold; if not, continuing to train the fault diagnosis model based on the historical fault sample data and the sample label.
Precision refers to the proportion of model prediction as actually positive in positive cases, i.e., TP/(tp+fp), where TP represents the true case (actually faulty and correctly identified), and FP represents the false positive case (actually normal but misjudged as faulty).
The Recall (Recall) is the proportion of all positive cases successfully found by the model, i.e., TP/(tp+fn), where FN represents a false negative case (actually a fault but incorrectly identified as normal).
In one embodiment, an F1 score (F-score) is calculated as a composite accuracy indicator of the model in combination with the precision and recall.
The F1 score is the harmonic mean of the precision and recall, and the formula is: 2× (precision x recall)/(precision + recall).
And then performing model evaluation, specifically judging whether any one of the precision rate, the recall rate and the accuracy is larger than a second preset threshold value. Illustratively, if the F1 score or other selected composite rating (e.g., precision, recall, etc.) of the model is below this threshold, it is indicated that the current performance of the model is not meeting the requirements and further optimization is required. If the model accuracy is not expected, the model parameters are adjusted, the feature engineering is optimized or other types of models are tried to be used according to actual conditions, and the model is continuously trained by reusing the historical fault sample data and the corresponding labels so as to improve the performance of the model on fault diagnosis tasks. Therefore, the training effect of the model is further improved, and the fault diagnosis model with better precision is obtained.
In one embodiment of the present application, the method further comprises: generating a diagnosis report based on the fault diagnosis result of the power exchange station equipment; and/or generating a maintenance scheme of the fault equipment of the power exchange station based on the fault diagnosis result of the power exchange station.
Specifically, the trained fault prediction model is deployed on line, so that the fault condition of the power station equipment can be predicted in real time, and a fault diagnosis report can be generated according to the fault condition of the power station equipment.
In addition, according to the fault condition of the power exchange station equipment, the maintenance scheme aiming at each fault equipment can be generated by combining the work order conditions stored in the database, so that the working efficiency of maintenance personnel of the power exchange station is improved.
In another embodiment, as shown in fig. 2 and fig. 3, the fault diagnosis method of the power exchange station equipment can be specifically realized through three parts, namely different failure mode label systems, a loop framework system construction and algorithm model reasoning.
For failure modes, failure cases of all parts in the history of the power exchange station, details of the work orders for replacement and whether algorithms are recalled need to be collected, and the data need to be stored in a mysql offline table mode, so that follow-up inquiry is facilitated.
For failure tags, since the components of the power exchange station are very many and the historical failures are very redundant, the total use of the components can lead to a large amount of noise of the data set, so that mechanism analysis is needed for different failure modes, tag classification is performed, and multi-level failure mode classification including primary, secondary, tertiary and the like is performed, so that a data base is laid for a subsequent back-calculation method.
The frame for the return includes entities, samples, features, and tags. Wherein the entities are used for characterizing what entities are back-measured, the entities represent a data model of the model prediction object, which contains a feature set associated with the model prediction object, and the uniqueness is represented by the entities, such as a certain day, a certain component, and a certain axis of the power exchange station, so that it can be uniquely determined which component is dead on which day.
The sample is used for representing the actual running state of a certain component of a certain station on a certain day (the shaft number and the working condition of the step can be accurately calculated).
Features are used to characterize information directly associated with an entity, and features may be important information extracted from the collected data information. A feature is designed as a table containing fields such as entity id and feature list, and a feature contains only one feature column if there are multiple features represented as feature sets.
The tag is used to characterize the attribute associated with an entity, expressed as whether a component of a station fails (state is normal or failed) on a certain day.
For the return frame algorithm, the input of the return frame comprises a feature set, a label set and a model set, and all algorithms embedded in the return frame support big data computing capability. The back-testing framework comprises a plurality of algorithm models, such as a data reading module, a back-testing module, a drawing module, a parameter optimizing module, a decision module, a result module and the like.
The data reading module is used for acquiring a feature set, a tag set and a fault prediction model, wherein the model set can be a machine learning model or a deep learning model.
The return module is a dispatching center of the whole return frame, and the dispatching work of each module is carried out through the return module.
The main functions of the mapping module are to map the presentation of the recall result, including the calculated precision, recall, confusion matrix, etc.
The main function of the parameter optimization module is to find a proper threshold value automatically by using an optimization class algorithm.
Based on the fact that a plurality of groups of different back measurement results can be obtained for the back measurement module and the parameter optimization module, the decision module is used for deciding which group of results are optimal, and the optimal parameter combination is selected for display.
The result module integrates the previous various modules, and finally, all the results in the previous stage can be displayed by directly calling the result module.
The application uses a timing method to periodically poll the failure result label table to train and obtain the failure prediction model. The method comprises the following steps: firstly, all the characteristics and the labels are acquired, decision making and calling are carried out in the return measurement frame, and the final return measurement result and the optimal decision model are obtained through on-line real-time operation. And (3) automatically covering the unresumed failure mode when the optimal decision model is on line. Different failure modes can automatically iterate the steps until all the non-recalled cases within the expiration scheduling date are covered and diagnosis of equipment faults is performed, so that a diagnosis result is obtained.
And a diagnosis report, an optimal model parameter list, a missing report list and the like can be generated according to the diagnosis result. The failed power exchange station equipment can be further recalled.
Based on the method, the mechanism and analysis are distinguished for different failure modes through the result collection of the history recall cases, the automatic feature selection and feature threshold selection are realized through the application of the recall frame, the more accurate analysis of the recall cases is realized, the automation of the whole process and the coverage of the corresponding failure modes by an automatic online algorithm can be realized, the coverage rate of the total failure modes is higher, and the robustness, the accuracy and the high efficiency are obtained.
It should be noted that, although the foregoing embodiments describe the steps in a specific order, it will be understood by those skilled in the art that, in order to achieve the effects of the present application, the steps are not necessarily performed in such an order, and may be performed simultaneously (in parallel) or in other orders, and these variations are within the scope of the present application.
Furthermore, the application also provides a fault diagnosis device for the power exchange station equipment.
Referring to fig. 4, fig. 4 is a main structural block diagram of a fault diagnosis apparatus for a power exchange station according to an embodiment of the present application.
As shown in fig. 4, the fault diagnosis device for the power exchange station equipment in the embodiment of the application mainly comprises an acquisition module 11, an extraction module 12, an acquisition module 13 and a diagnosis module 14. In some embodiments, one or more of the acquisition module 11, the extraction module 12, the acquisition module 13, and the diagnostic module 14 may be combined together into one module.
In some embodiments, the acquisition module 11 may be configured to acquire data information of the battery pack and the battery exchange device.
The extraction module 12 may be configured to extract battery exchange station data features based on the battery pack and the battery pack data information.
The acquisition module 13 may be configured to acquire a fault diagnosis model.
The diagnostic module 14 may be configured to utilize the fault diagnosis model to perform fault diagnosis of the battery plant based on the battery plant data characteristics.
In one embodiment, the description of the specific implementation function may be described with reference to step S101 to step S104.
The foregoing power plant equipment fault diagnosis apparatus is used for executing the power plant equipment fault diagnosis method embodiment shown in fig. 1, and the technical principles of the two embodiments, the technical problems to be solved and the technical effects to be produced are similar, and those skilled in the art can clearly understand that, for convenience and brevity of description, the specific working process and the related description of the power plant equipment fault diagnosis apparatus may refer to the description of the power plant equipment fault diagnosis method embodiment, and will not be repeated herein.
It will be appreciated by those skilled in the art that the present application may implement all or part of the above-described methods according to the above-described embodiments, or may be implemented by means of a computer program for instructing relevant hardware, where the computer program may be stored in a computer readable storage medium, and where the computer program may implement the steps of the above-described embodiments of the method when executed by a processor. Wherein the computer program comprises computer program code which may be in source code form, object code form, executable file or some intermediate form etc. The computer readable storage medium may include: any entity or device, medium, usb disk, removable hard disk, magnetic disk, optical disk, computer memory, read-only memory, random access memory, electrical carrier wave signals, telecommunications signals, software distribution media, and the like capable of carrying the computer program code. It should be noted that the computer readable storage medium may include content that is subject to appropriate increases and decreases as required by jurisdictions and by jurisdictions in which such computer readable storage medium does not include electrical carrier signals and telecommunications signals.
The application further provides electronic equipment. In one embodiment of an electronic device according to the present application, as shown in fig. 5, the electronic device comprises at least one processor 51 and at least one memory 52, the memory 52 may be configured to store a program for performing the battery exchange device fault diagnosis method of the above-described method embodiment, and the processor 51 may be configured to execute the program in the memory, including, but not limited to, the program for performing the battery exchange device fault diagnosis method of the above-described method embodiment. For convenience of explanation, only those portions of the embodiments of the present application that are relevant to the embodiments of the present application are shown, and specific technical details are not disclosed, please refer to the method portions of the embodiments of the present application.
The electronic device in the embodiment of the application can be a control device formed by various devices. In some possible implementations, an electronic device may include multiple memories and multiple processors. The program for executing the power plant equipment fault diagnosis method of the above method embodiment may be divided into a plurality of sub-programs, and each sub-program may be loaded and executed by the processor to execute different steps of the power plant equipment fault diagnosis method of the above method embodiment. Specifically, each of the sub-programs may be stored in a different memory, respectively, and each of the processors may be configured to execute the programs in one or more memories to collectively implement the power plant fault diagnosis method of the above method embodiment, that is, each of the processors executes different steps of the power plant fault diagnosis method of the above method embodiment, respectively, to collectively implement the power plant fault diagnosis method of the above method embodiment.
The plurality of processors may be processors disposed on the same device, for example, the electronic device may be a high-performance device composed of a plurality of processors, and the plurality of processors may be processors configured on the high-performance device. In addition, the plurality of processors may be processors disposed on different devices, for example, the electronic device may be a server cluster, and the plurality of processors may be processors on different servers in the server cluster.
Further, the application also provides a computer readable storage medium. In one computer-readable storage medium embodiment according to the present application, the computer-readable storage medium may be configured to store a program for performing the above-described power plant fault diagnosis method of the method embodiment, which program may be loaded and executed by a processor to implement the above-described power plant fault diagnosis method. For convenience of explanation, only those portions of the embodiments of the present application that are relevant to the embodiments of the present application are shown, and specific technical details are not disclosed, please refer to the method portions of the embodiments of the present application. The computer readable storage medium may be a memory device formed of various electronic devices, and optionally, the computer readable storage medium in embodiments of the present application is a non-transitory computer readable storage medium.
Further, it should be understood that, since the respective modules are merely set to illustrate the functional units of the apparatus of the present application, the physical devices corresponding to the modules may be the processor itself, or a part of software in the processor, a part of hardware, or a part of a combination of software and hardware. Accordingly, the number of individual modules in the figures is merely illustrative.
Those skilled in the art will appreciate that the various modules in the apparatus may be adaptively split or combined. Such splitting or combining of specific modules does not cause the technical solution to deviate from the principle of the present application, and therefore, the technical solution after splitting or combining falls within the protection scope of the present application.
Thus far, the technical solution of the present application has been described in connection with the preferred embodiments shown in the drawings, but it is easily understood by those skilled in the art that the scope of protection of the present application is not limited to these specific embodiments. Equivalent modifications and substitutions for related technical features may be made by those skilled in the art without departing from the principles of the present application, and such modifications and substitutions will fall within the scope of the present application.
Claims (10)
1. A method for diagnosing a fault in a power exchange plant, the method comprising:
Collecting data information of the battery pack and the battery replacement equipment;
Extracting data characteristics of the battery exchange station based on the data information of the battery exchange equipment and the battery pack;
obtaining a fault diagnosis model;
and performing fault diagnosis on the power exchange station equipment based on the power exchange station data characteristics by using the fault diagnosis model.
2. The power plant equipment fault diagnosis method according to claim 1, characterized in that the fault diagnosis model is obtained by training the following steps:
Obtaining a plurality of historical fault sample data in a power exchange station, and adding a sample label for each historical fault sample data;
determining initial model parameters based on the historical fault sample data and sample labels corresponding to the historical fault sample data;
determining optimal model parameters based on the initial model parameters and a first preset threshold;
And obtaining the fault diagnosis model based on the optimal model parameters.
3. The battery exchange station device fault diagnosis method according to claim 2, wherein the determining initial model parameters based on the historical fault sample data and sample tags corresponding to the historical fault sample data comprises:
extracting historical fault sample features based on the historical fault sample data;
Inputting each historical fault sample feature and a sample label corresponding to the historical fault sample data into a fault diagnosis model to obtain a prediction result;
And adjusting model parameters of the fault diagnosis model based on the prediction result and the label until the fault diagnosis model converges, so as to obtain the initial model parameters.
4. The battery exchange station device fault diagnosis method according to claim 2, wherein after adding a sample tag to each of the historical fault sample data and before determining an initial model parameter based on the sample tag of the historical fault sample data corresponding to the historical fault sample data, the method further comprises: the sample tags are classified based on the type of failure of the power exchange station equipment.
5. A method of diagnosing a battery exchange station apparatus failure according to claim 3, further comprising:
determining an accuracy rate and a recall rate based on the prediction result;
determining an accuracy of the fault diagnosis model based on the precision rate and the recall rate;
Judging whether any one of the precision rate, the recall rate and the precision is greater than a second preset threshold;
If not, continuing to train the fault diagnosis model based on the historical fault sample data and the sample label.
6. The battery exchange station fault diagnosis method according to claim 1, wherein the data information includes a battery exchange station fault signal, battery exchange station fault data, battery exchange station operation state data, and battery pack data information in the battery exchange station.
7. The power plant equipment fault diagnosis method according to claim 1, characterized in that the method further comprises:
generating a fault diagnosis report based on the fault diagnosis result of the power exchange station equipment; and/or
And generating a maintenance scheme of the fault equipment of the power exchange station based on the fault diagnosis result of the power exchange station.
8. A power exchange station apparatus fault diagnosis apparatus, characterized in that the apparatus comprises:
the acquisition module is used for acquiring data information of the battery pack and the battery replacement equipment;
the extraction module is used for extracting the data characteristics of the battery exchange station based on the data information of the battery exchange equipment and the battery pack;
the acquisition module is used for acquiring the fault diagnosis model;
And the diagnosis module is used for diagnosing faults of the power exchange station equipment based on the data characteristics of the power exchange station by utilizing the fault diagnosis model.
9. An electronic device comprising at least one processor and at least one memory, the memory being adapted to store a plurality of program code, characterized in that the program code is adapted to be loaded and executed by the processor to perform the battery exchange station fault diagnosis method of any one of claims 1 to 7.
10. A computer readable storage medium, in which a plurality of program codes are stored, characterized in that the program codes are adapted to be loaded and run by a processor to perform the battery exchange station fault diagnosis method of any one of claims 1 to 7.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202410156653.2A CN117972493A (en) | 2024-02-04 | 2024-02-04 | Method and device for diagnosing faults of power exchange station equipment, electronic equipment and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202410156653.2A CN117972493A (en) | 2024-02-04 | 2024-02-04 | Method and device for diagnosing faults of power exchange station equipment, electronic equipment and storage medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN117972493A true CN117972493A (en) | 2024-05-03 |
Family
ID=90856123
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202410156653.2A Pending CN117972493A (en) | 2024-02-04 | 2024-02-04 | Method and device for diagnosing faults of power exchange station equipment, electronic equipment and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN117972493A (en) |
-
2024
- 2024-02-04 CN CN202410156653.2A patent/CN117972493A/en active Pending
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111241154B (en) | Storage battery fault early warning method and system based on big data | |
Al-Dahidi et al. | Remaining useful life estimation in heterogeneous fleets working under variable operating conditions | |
CN113708493B (en) | Cloud edge cooperation-based power distribution terminal operation and maintenance method and device and computer equipment | |
CN113156917B (en) | Power grid equipment fault diagnosis method and system based on artificial intelligence | |
CN114282434A (en) | Industrial equipment health management system and method | |
CN116154900B (en) | Active safety three-stage prevention and control system and method for battery energy storage power station | |
CN112561736A (en) | Fault diagnosis system and method for relay protection device of intelligent substation | |
CN114267178B (en) | Intelligent operation maintenance method and device for station | |
CN115343623B (en) | Online detection method and device for faults of electrochemical energy storage battery | |
CN115902646B (en) | Energy storage battery fault identification method and system | |
CN116914917A (en) | Big data-based monitoring and management system for operation state of power distribution cabinet | |
CN110703743A (en) | Equipment failure prediction and detection system and method | |
CN117973902B (en) | Intelligent decision method and system based on level-keeping table fault handling | |
CN115684792A (en) | Electrical automation equipment detecting system based on artificial intelligence | |
CN117150418B (en) | Transformer operation detection period formulation method and system based on state characteristic fault tree | |
CN114493238A (en) | Power supply service risk prediction method, system, storage medium and computer equipment | |
CN117331790A (en) | Machine room fault detection method and device for data center | |
CN117521498A (en) | Charging pile guide type fault diagnosis prediction method and system | |
Bond et al. | A hybrid learning approach to prognostics and health management applied to military ground vehicles using time-series and maintenance event data | |
CN116714469A (en) | Charging pile health monitoring method, device, terminal and storage medium | |
CN117972493A (en) | Method and device for diagnosing faults of power exchange station equipment, electronic equipment and storage medium | |
CN116149895A (en) | Big data cluster performance prediction method and device and computer equipment | |
Trstenjak et al. | A Decision Support System for the Prediction of Wastewater Pumping Station Failures Based on CBR Continuous Learning Model. | |
CN117875946B (en) | Man-machine collaborative autonomous infrared inspection method for operation and maintenance of transformer substation equipment | |
CN118091406B (en) | Motor detection and repair method and device, electronic equipment and storage medium |
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 |