Fault diagnosis method and apparatus for battery swap station device, electronic device, and storage medium

Abstract

The present application relates to the technical field of battery swap stations, and particularly provides a fault diagnosis method and apparatus for a battery swap station device, an electronic device, and a storage medium, aiming to solve the technical problems in existing fault diagnosis methods of low efficiency and poor fault coverage caused by manual implementation. For this purpose, the fault diagnosis method for a battery swap station device of the present application comprises: collecting data information of a battery swap device and a battery pack; extracting a battery swap station data feature on the basis of the data information of the battery swap device and the battery pack; obtaining a fault diagnosis model; and performing fault diagnosis on the battery swap station device by means of the fault diagnosis model on the basis of the battery swap station data feature. Thus, the fault diagnosis accuracy for battery swap station devices is improved, and the coverage of diagnosis of all faulty components is improved.

Description

Battery swap station equipment fault diagnosis method, device, electronic device and storage medium

[0001] This application claims priority to Chinese patent application CN 202410156653.2, filed on February 4, 2024, entitled “Fault diagnosis method, device, electronic device and storage medium for battery swap station equipment”. The entire contents of the above Chinese patent application are incorporated into this application by reference. Technical Field

[0002] The present application relates to the technical field of battery swap stations, and specifically provides a method, device, electronic device and storage medium for diagnosing equipment faults in a battery swap station. Background Art

[0003] At present, battery replacement service is a key factor in ensuring the convenience of long-distance travel for electric vehicles and one of the important ways to replenish energy. As the number of battery replacement stations gradually increases, with the long-term operation of the equipment and the influence of environmental factors, the wear and tear of its machine components will increase, resulting in more and more parts damage. There may be a large number of potential failure modes, but a large part of them cannot be discovered and recalled in time in the early stages. Therefore, the pressure of unmanned battery replacement stations is increasing, resulting in a gradual increase in corporate costs.

[0004] Existing failure mode analysis methods mainly rely on previous knowledge of mechanisms and structural deformation after component damage, and lack data-driven methods. Therefore, the analysis of each unrecalled part is very labor-intensive and requires a lot of time to check the mechanism and subsequent analysis. The efficiency of the algorithm's online coverage is extremely low.

[0005] Accordingly, the art requires a new fault diagnosis solution for battery swap station equipment to solve the above problems.

[0006] Application Contents

[0007] In order to overcome the above-mentioned defects, the present application is proposed to provide a solution or at least partially solve the above-mentioned technical problems. The present application provides a method, device, electronic device and storage medium for diagnosing equipment faults in a battery swap station.

[0008] In a first aspect, the present application provides a method for diagnosing faults of battery swap station equipment, the method comprising:

[0009] Collect data information of battery swap equipment and battery packs;

[0010] Extracting data features of the battery swap station based on the data information of the battery swap equipment and the battery pack;

[0011] Obtaining a fault diagnosis model;

[0012] The fault diagnosis model is used to perform fault diagnosis on the battery swap station equipment based on the battery swap station data characteristics.

[0013] In one embodiment of the present application, the fault diagnosis model is obtained by training through the following steps:

[0014] Acquire multiple historical fault sample data in the battery swap station, and add a sample label to each of the historical fault sample data;

[0015] Determining initial model parameters based on the historical fault sample data and sample labels corresponding to the historical fault sample data;

[0016] Determining optimal model parameters based on the initial model parameters and a first preset threshold;

[0017] The fault diagnosis model is obtained based on the optimal model parameters.

[0018] In one embodiment of the present application, determining the initial model parameters based on the historical fault sample data and the sample labels corresponding to the historical fault sample data includes:

[0019] Extracting historical fault sample features based on the historical fault sample data;

[0020] Inputting each of the historical fault sample features and the sample label corresponding to the historical fault sample data into the fault diagnosis model to obtain a prediction result;

[0021] The model parameters of the fault diagnosis model are adjusted based on the prediction result and the label until the fault diagnosis model converges to obtain the initial model parameters.

[0022] In one embodiment of the present application, after adding a sample label to each of the historical fault sample data, and before determining the initial model parameters based on the historical fault sample data and the sample labels corresponding to the historical fault sample data, the method further includes: classifying the sample labels based on the fault type of the battery swap station equipment.

[0023] In one embodiment of the present application, the method further comprises:

[0024] Determining precision and recall based on the prediction results;

[0025] Determining the accuracy of the fault diagnosis model based on the precision rate and the recall rate;

[0026] Determining whether any one of the precision rate, the recall rate, and the accuracy is greater than a second preset threshold;

[0027] If not, continue training the fault diagnosis model based on the historical fault sample data and the sample labels.

[0028] In one embodiment of the present application, the data information includes a battery swap equipment fault signal, battery swap equipment fault data, battery swap equipment operating status data, and battery pack data information in the battery swap station.

[0029] In one embodiment of the present application, the method further comprises:

[0030] Generate a fault diagnosis report based on the fault diagnosis results of the battery swap station equipment; and / or

[0031] A maintenance plan for the faulty equipment in the battery swap station is generated based on the fault diagnosis result of the battery swap station equipment.

[0032] In a second aspect, the present application provides a device for diagnosing faults in a battery swap station, the device comprising:

[0033] Acquisition module, used to collect data information of battery swap equipment and battery packs;

[0034] An extraction module, configured to extract data features of a battery swap station based on data information of the battery swap device and the battery pack;

[0035] An acquisition module, used to acquire a fault diagnosis model;

[0036] The diagnostic module is used to perform fault diagnosis on the battery swap station equipment based on the battery swap station data characteristics by using the fault diagnosis model.

[0037] In a third aspect, an electronic device is provided, which includes at least one processor and at least one memory, wherein the memory is suitable for storing multiple program codes, and the program codes are suitable for being loaded and run by the processor to execute any of the above-mentioned methods for diagnosing faults in battery swap station equipment.

[0038] In a fourth aspect, a computer-readable storage medium is provided, wherein a plurality of program codes are stored in the computer-readable storage medium, wherein the program codes are suitable for being loaded and run by a processor to execute any one of the aforementioned methods for diagnosing faults in battery swap station equipment.

[0039] The above one or more technical solutions of this application have at least one or more of the following beneficial effects:

[0040] The battery swap station equipment fault diagnosis method in this application specifically includes: collecting data information of the battery swap equipment and battery pack; extracting the battery swap station data features based on the data information of the battery swap equipment and battery pack; obtaining a fault diagnosis model; and using the fault diagnosis model and the battery swap station data features to perform fault diagnosis on the battery swap station equipment. In this way, the pre-trained model can be used to accurately and efficiently diagnose faulty equipment at the battery swap station, so that the faulty equipment can be recalled in a timely manner, reducing labor costs and improving the fault diagnosis accuracy and fault diagnosis coverage of the battery swap station equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] The disclosure of this application will be more easily understood with reference to the accompanying drawings. Those skilled in the art will readily appreciate that these drawings are for illustrative purposes only and are not intended to limit the scope of protection of this application. Furthermore, similar numbers in the figures represent similar components, where:

[0042] FIG1 is a flow chart showing the main steps of a method for diagnosing faults in battery swap station equipment according to an embodiment of the present application;

[0043] FIG2 is a schematic diagram of a complete flow chart of a method for diagnosing faults in battery swap station equipment according to one embodiment of the present application;

[0044] FIG3 is a schematic diagram of a complete flow chart of a method for diagnosing faults in battery swap station equipment according to another embodiment of the present application;

[0045] FIG4 is a schematic diagram of a main structural block diagram of a device for diagnosing faults in a battery swap station according to an embodiment of the present application;

[0046] FIG5 is a schematic structural diagram of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0047] Some embodiments of the present application are described below with reference to the accompanying drawings. Those skilled in the art should understand that these embodiments are only used to explain the technical principles of the present application and are not intended to limit the scope of protection of the present application.

[0048] In the description of this application, "module" and "processor" may include hardware, software, or a combination of both. A module may include hardware circuitry, various suitable sensors, communication ports, and memory. It may also include software components, such as program code, or a combination of software and hardware. A processor may be a central processing unit, a microprocessor, an image processor, a digital signal processor, or any other suitable processor. A processor has data and / or signal processing capabilities. A processor may be implemented in software, hardware, or a combination of both. Non-transitory computer-readable storage media include any suitable medium capable of storing program code, such as magnetic disks, hard disks, optical disks, flash memory, read-only memory, random access memory, etc. The term "A and / or B" refers to all possible combinations of A and B, such as only A, only B, or both A and B. The terms "at least one of A or B" or "at least one of A and B" have similar meanings to "A and / or B" and may include only A, only B, or both A and B. The singular forms "a" and "the" may also include the plural forms.

[0049] Currently, traditional failure mode analysis methods mainly rely on preliminary knowledge of mechanisms and structural deformation after component damage, lacking data-driven methods. Therefore, the analysis of each unrecalled part is very labor-intensive and requires a lot of time to check the mechanism and subsequent analysis. The efficiency of the algorithm's online coverage is extremely low.

[0050] To this end, this application proposes a method for diagnosing faults in battery swap station equipment. The specific method includes: collecting data information from battery swap equipment and battery packs; extracting data features of the battery swap station based on the data information of the battery swap equipment and battery packs; obtaining a fault diagnosis model; and using the fault diagnosis model and the battery swap station data features to diagnose faults in the battery swap station equipment. In this way, the pre-trained model can be used to accurately and efficiently diagnose faulty equipment in the battery swap station, enabling the timely recall of faulty equipment, reducing labor costs, and improving the fault diagnosis accuracy and fault diagnosis coverage of the battery swap station equipment.

[0051] Referring to FIG1 , FIG1 is a flow chart showing the main steps of a method for diagnosing faults in a battery swap station according to an embodiment of the present application. As shown in FIG1 , the method for diagnosing faults in a battery swap station according to an embodiment of the present application mainly includes the following steps S101 to S104 .

[0052] Step S101: Collect data information of the battery replacement equipment and battery pack.

[0053] In a specific embodiment of the present application, the data information includes a battery swapping equipment fault signal in the battery swapping station, battery swapping equipment fault data, battery swapping equipment operating status data, and battery pack data information.

[0054] Specifically, the operating status data of the battery swap equipment includes but is not limited to the operating temperature of each component of the battery swap station and charging pile, current and voltage readings, equipment start and stop time, etc.

[0055] Battery pack data information includes but is not limited to key data such as battery voltage, current, temperature curve, SOC (State of Charge), SOH (State of Health), battery cycle count, single cell consistency, self-discharge rate, internal resistance change trend, etc. during the charge and discharge process.

[0056] The battery swapping equipment failure data includes the location, component name, failure time, etc. of the components when the battery swapping equipment fails.

[0057] In addition, in some other embodiments, environmental condition data of the battery swap station equipment may also be collected, such as the ambient temperature and humidity, light intensity, atmospheric pressure, etc. within the battery swap station. These factors may indirectly affect the operating conditions of the equipment and batteries.

[0058] Step S102: Extracting data features of the battery swap station based on the data information of the battery swap equipment and battery pack.

[0059] After collecting data on battery swap equipment and battery packs, it needs to be preprocessed to remove outliers, fill in missing values, and convert it into a format suitable for machine learning model analysis. Next, statistical methods and data mining techniques are used to extract features that reflect the health status of the battery swap station.

[0060] For example, take equipment status characteristics as an example, such as equipment working efficiency, fatigue index (based on operating time and load changes), life prediction index (based on accumulated wear and maintenance records), etc.

[0061] For example, take the performance characteristics of a battery pack as an example, such as battery capacity attenuation characteristics, thermal runaway risk index, imbalance coefficient, etc.

[0062] It can also include time series features, such as performing time series analysis on continuous device and battery status data to extract periodicity, trend and mutation features.

[0063] Step S103: Acquire a fault diagnosis model.

[0064] Fault diagnosis models include but are not limited to machine learning models, time series prediction models, deep learning models, or mechanism models.

[0065] Taking the machine learning model as an example, the machine learning algorithm can be selected from any of the models such as decision tree, support vector machine, random forest, deep neural network, etc.

[0066] Taking the time series prediction model as an example, the selected time series prediction model can be any one of the models such as ARIMA, Prophet, LSTM, etc.

[0067] Step S104: diagnose faults of the battery swap station equipment using the fault diagnosis model based on the battery swap station data characteristics.

[0068] Specifically, the data features of the battery swap station are input into the fault diagnosis model to perform fault diagnosis on the battery swap station equipment, thereby obtaining the location and fault time of the faulty equipment in the battery swap station.

[0069] Smart battery swap stations have an algorithm-based early warning and recall mechanism. When the monitoring system predicts a potential failure through data analysis, an algorithmic recall event is triggered and a corresponding alert notification is generated. The algorithmic recall data should include: the time of predicted failure, the type of failure, the location of the failure, the recall level (urgency), the comparison between the actual failure and the predicted failure, and whether maintenance service was scheduled in advance.

[0070] Based on steps S101-S104 above, data information about the battery swapping equipment and battery packs is first collected; data features of the battery swapping station are extracted based on the data information about the battery swapping equipment and battery packs; a fault diagnosis model is obtained; and fault diagnosis of the battery swapping station equipment is performed using the fault diagnosis model and the battery swapping station data features. In this way, the pre-trained model can be used to accurately and efficiently diagnose faulty equipment at the battery swapping station, enabling the timely recall of faulty equipment, reducing labor costs, improving the fault diagnosis accuracy of the battery swapping station equipment, and increasing the coverage efficiency of diagnosing all faulty components.

[0071] In a specific embodiment of the present application, the fault diagnosis model is obtained by training through the following steps S201 to S204.

[0072] Step S201: Acquire a plurality of historical fault sample data in a battery swap station, and add a sample label to each of the historical fault sample data.

[0073] Specifically, we collect all the failure cases of components in the history of the battery swap station equipment, the details of the replacement work orders, and whether there is an algorithm recall, etc. Through these data, we obtain multiple historical fault sample data in the battery swap station and store them in the form of a MySQL offline table to facilitate subsequent queries.

[0074] Specifically, all failure cases involving key components in the history of the battery swap station are collected, such as detailed records of the timestamp of each failure event, the specific model and serial number of the failed component, the failure mode (such as wear, aging, short circuit, etc.), failure cause analysis report, and related pictures or video materials and other detailed information.

[0075] Replacement work order details are another important data source. They include not only the actual replacement operation records for the failed component, but also the work order initiation time, expected completion time, actual completion time, information about the technician who performed the repair task, the model and serial number of the new component, and post-replacement test results. Based on the replacement work order details, repair plans can be developed for subsequent faulty equipment at the battery swap station.

[0076] To ensure data consistency and query efficiency, all of this information must be stored in structured offline MySQL database tables. This allows for quick and convenient analysis of component failure frequency within a specific time period, work order processing efficiency analysis, and retrospective verification of algorithm prediction accuracy. This provides strong data support for optimizing battery swap station operation and maintenance strategies, improving service quality, reducing downtime, and lowering operating costs.

[0077] After obtaining multiple historical fault sample data in the battery swap station, sample labels can be added to each historical fault sample data manually, or a conventional method of adding labels to data in this field can be used to add sample labels to each historical fault sample data. This application does not specifically limit the specific method of adding labels.

[0078] In a specific embodiment of the present application, after adding a sample label to each of the historical fault sample data, and before determining the initial model parameters based on the historical fault sample data and the sample labels corresponding to the historical fault sample data, the method also includes: classifying the sample labels based on the fault type of the battery swap station equipment.

[0079] Specifically, since there are many components in the battery swap station and the historical failures are very redundant, using all of them will result in a lot of noise in the data set. Therefore, it is necessary to conduct a mechanism analysis of different failure modes and perform label classification, including multi-level failure mode classification such as primary, secondary, and tertiary, to lay a data foundation for the subsequent backtesting algorithm. Subsequently, the fault prediction model can be trained according to the classified labels and the corresponding historical sample data, which is conducive to improving the training accuracy of the fault prediction model.

[0080] Step S202: determining initial model parameters based on the historical fault sample data and sample labels corresponding to the historical fault sample data.

[0081] In a specific embodiment of the present application, the initial model parameters are determined based on the historical fault sample data and the sample labels corresponding to the historical fault sample data, including: extracting historical fault sample features based on the historical fault sample data; inputting each of the historical fault sample features and the sample labels corresponding to the historical fault sample data into a fault diagnosis model to obtain a prediction result; adjusting the model parameters of the fault diagnosis model based on the prediction result and the label until the fault diagnosis model converges to obtain the initial model parameters.

[0082] Specifically, we conduct an in-depth analysis of all historical component failure cases and their work order details at the battery swap station to extract key features with representative and predictive value. These features may include, but are not limited to, component type, age, workload, environmental conditions, maintenance records, abnormal behavior patterns prior to failure, replacement frequency, and other information. Using statistical methods and machine learning algorithms, we perform dimensionality reduction, normalization, and missing value filling on the raw data to form a structured feature set of historical failure samples.

[0083] After obtaining the features of historical fault samples, each sample feature is associated with its corresponding fault category or severity (i.e., sample label) to construct a training dataset. These labels are accurate classification information based on actual fault conditions, expert evaluation, or historical maintenance records.

[0084] Next, the feature-label pairs are fed into a fault diagnosis model for training. This model can be a supervised learning model, such as a decision tree, random forest, or support vector machine, or a more complex neural network model, such as a deep learning model. The model learns the regularity of mapping input features to output labels and attempts to minimize the difference between the predicted results and the true labels.

[0085] During the training process, optimization algorithms (such as gradient descent or other iterative optimization strategies) are used to gradually adjust model parameters and continuously update the internal weight distribution and structure settings of the model to improve the performance of the model on the training set. The model is iterated repeatedly until the model performance indicators reach a convergence state.

[0086] Ultimately, the set of model parameters obtained when model training converges is the initial model parameters. This set of parameters enables the fault diagnosis model to provide relatively accurate fault prediction and diagnosis conclusions based on the new input feature data, thereby serving the intelligent operation and maintenance and fault prevention system of the battery swap station.

[0087] Multiple historical fault sample data can determine multiple initial model parameters.

[0088] Step S203: Determine optimal model parameters based on the initial model parameters and a first preset threshold.

[0089] The first preset threshold may be a suitable threshold automatically found through an optimization algorithm, where the optimization algorithm includes but is not limited to grid search, random search, threshold optimization function, and threshold adaptive adjustment.

[0090] For example, grid search is an exhaustive method that traverses a pre-defined threshold list, trains a model for each threshold, and calculates the corresponding evaluation indicators (such as F1 score, area under the AUC-ROC curve, etc.), and finally selects the threshold with the best indicator.

[0091] By comparing the multiple initial model parameters with the first preset threshold respectively, a group of initial model parameters that are smaller than the first preset threshold are used as optimal model parameters.

[0092] Step S204: Obtain the fault diagnosis model based on the optimal model parameters.

[0093] The obtained fault diagnosis model based on the optimal model parameters can be deployed in practical applications to monitor the status of battery swap station equipment in real time and issue early warnings of potential faults based on the model prediction results, thereby improving equipment operation and maintenance efficiency and reducing downtime risks.

[0094] In a specific embodiment of the present application, the method also includes: determining the precision and recall rate based on the prediction results; determining the accuracy of the fault diagnosis model based on the precision and recall rate; judging whether the precision, recall and accuracy 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 labels.

[0095] Precision refers to the proportion of positive examples predicted by the model that are actually positive, that is, TP / (TP+FP), where TP represents true positive examples (actually faulty examples that are correctly identified) and FP represents false positive examples (actually normal examples that are mistakenly identified as faulty examples).

[0096] Recall is the proportion of all positive examples that the model successfully finds, that is, TP / (TP+FN), where FN represents false negatives (actually faulty examples that are mistakenly identified as normal).

[0097] In one embodiment, the F1 score (F-score) is calculated by combining the precision and recall as a comprehensive accuracy indicator of the model.

[0098] The F1 score is the harmonic mean of precision and recall, and its formula is: 2×(precision×recall) / (precision+recall).

[0099] Then the model is evaluated, specifically to determine whether any one of the precision, recall and accuracy is greater than the second preset threshold. For example, if the F1 score or other selected comprehensive evaluation indicators of the model (such as precision, recall, etc.) are lower than this threshold, it means that the current performance of the model does not meet the requirements and needs to be further optimized. If the model accuracy does not meet expectations, the model parameters should be adjusted according to the actual situation, the feature engineering should be optimized, or other types of models should be tried, and the historical fault sample data and corresponding labels should be reused to continue training the model to improve the model's performance in the fault diagnosis task. In this way, it is conducive to further improving the training effect of the model and obtaining a more accurate fault diagnosis model.

[0100] In a specific embodiment of the present application, the method further includes: generating a diagnostic report based on the fault diagnosis results of the battery swap station equipment; and / or generating a maintenance plan for the faulty equipment in the battery swap station based on the fault diagnosis results of the battery swap station equipment.

[0101] Specifically, deploying the trained fault prediction model online can predict the fault conditions of battery swap station equipment in real time and generate a fault diagnosis report based on the fault conditions of the station equipment.

[0102] In addition, based on the fault conditions of the battery swap station equipment and combined with the work order conditions stored in the database, a maintenance plan for each faulty device can be generated, thereby improving the work efficiency of the battery swap station maintenance personnel.

[0103] In another embodiment, as shown in FIG2 and FIG3 , the battery swap station equipment fault diagnosis method of the present application can be specifically implemented through three parts: different failure mode label systems, backtesting framework system construction, and algorithm model reasoning.

[0104] For failure modes, it is necessary to collect failure cases of all components in the history of the battery swap station, details of replacement work orders, and whether there are algorithm recalls. These data need to be stored in the form of MySQL offline tables to facilitate subsequent queries.

[0105] Regarding failure labels, since there are many components in the battery swap station and the historical failures are very redundant, using all of them will result in a lot of noise in the data set. Therefore, it is necessary to conduct a mechanism analysis of different failure modes and perform label classification, including multi-level failure mode classification such as primary, secondary, and tertiary, to lay a data foundation for the subsequent backtesting algorithm.

[0106] The backtesting framework includes entities, samples, features, and labels. Entities represent the entities being backtested. They represent the data model of the model's prediction object and contain the associated feature set. Entities are used to represent uniqueness. For example, a specific day, component, or axis at a battery swap station can uniquely determine the date and component failure.

[0107] The sample is used to characterize the actual operating status of a component at a station on a certain day (can be accurate to the axis number and step condition).

[0108] Features represent information directly associated with an entity. Features can be important information extracted from collected data. A feature is designed as a table containing fields such as the entity ID and a list of features. A feature contains only one feature column. Multiple features are represented as a feature set.

[0109] Tags are used to represent the attributes associated with an entity, indicating whether a component at a station fails on a certain day (the status is normal or faulty).

[0110] The backtesting framework's inputs include feature sets, label sets, and model sets. All algorithms embedded in the framework support big data computing capabilities. The framework includes several algorithmic models, including a data reading module, a backtesting module, a plotting module, a parameter optimization module, a decision module, and a results module.

[0111] The data reading module is used to obtain feature sets, label sets and fault prediction models. The model set can be a machine learning model, a deep learning model or a mechanism model.

[0112] The backtesting module is the scheduling center of the entire backtesting framework, and the scheduling work of each module is carried out through the backtesting module.

[0113] The main function of the graphing module is to display and graph the backtesting results, including the calculated precision, recall, confusion matrix, etc.

[0114] The main function of the parameter optimization module is to automatically find the appropriate threshold using optimization algorithms.

[0115] Based on the fact that multiple sets of different backtesting results can be obtained from the backtesting module and parameter optimization module, this decision module is used to decide which set of results is the best and select the best parameter combination for display.

[0116] The result module will integrate the various modules mentioned above, and finally all the previous results can be displayed by directly calling the result module.

[0117] The backtesting framework in this application uses a timed method to regularly poll the failure result label table to train and obtain a fault prediction model. This can be achieved specifically through the following steps: first, all features and labels are obtained, decisions and calls are made within the backtesting framework, and the final backtesting results and the optimal decision model are obtained through online real-time operation. The optimal decision model is put online to automatically cover this unrecalled failure mode. Different failure modes will automatically iterate the above steps until all unrecalled cases within the scheduling deadline are covered and the equipment failure is diagnosed, thereby obtaining a diagnostic result.

[0118] Based on the diagnostic results, a diagnostic report, a list of optimal model parameters, and a list of missed reports can be generated. Faulty battery swap station equipment can also be recalled.

[0119] Based on the above method, by collecting the results of historical unrecalled cases, different failure modes are distinguished through mechanism and analysis. Through the application of the backtesting framework, automated feature selection and feature threshold selection are realized, and more accurate analysis of unrecalled cases is achieved. The entire process can be automated and the algorithm can be automatically launched to cover the corresponding failure modes, so that there is higher coverage of the full range of failure modes, while achieving higher robustness, accuracy and efficiency.

[0120] It should be pointed out that although the various steps in the above embodiments are described in a specific order, those skilled in the art will understand that in order to achieve the effect of the present application, different steps do not have to be performed in such an order. They can be performed simultaneously (in parallel) or in other orders. These changes are within the scope of protection of the present application.

[0121] Furthermore, the present application also provides a device for diagnosing equipment faults in a battery swap station.

[0122] Please refer to Figure 4, which is a main structural block diagram of a battery swap station equipment fault diagnosis device according to an embodiment of the present application.

[0123] As shown in Figure 4, the battery swap station equipment fault diagnosis device in the embodiment of the present application mainly includes 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 diagnosis module 14 can be combined into one module.

[0124] In some embodiments, the acquisition module 11 can be configured to collect data information of the battery replacement device and the battery pack.

[0125] The extraction module 12 can be configured to extract battery swap station data features based on the data information of the battery swap equipment and battery pack.

[0126] The acquisition module 13 may be configured to acquire a fault diagnosis model.

[0127] The diagnosis module 14 may be configured to perform fault diagnosis on the battery swap station equipment based on the battery swap station data features using the fault diagnosis model.

[0128] In one implementation, the description of specific implementation functions can refer to steps S101 to S104.

[0129] The above-mentioned battery swap station equipment fault diagnosis device is used to execute the battery swap station equipment fault diagnosis method embodiment shown in Figure 1. The technical principles, technical problems solved and technical effects produced by the two are similar. Technical personnel in this technical field can clearly understand that for the convenience and conciseness of description, the specific working process and related instructions of the battery swap station equipment fault diagnosis device can refer to the contents described in the embodiment of the battery swap station equipment fault diagnosis method, and will not be repeated here.

[0130] It will be understood by those skilled in the art that all or part of the processes in the method for implementing the above embodiment of the present application can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, it can implement the steps of each of the above method embodiments. The computer program includes computer program code, which can be in source code form, object code form, executable file or some intermediate form. The computer-readable storage medium can include: any entity or device, medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory, random access memory, electric carrier signal, telecommunication signal and software distribution medium that can carry the computer program code. It should be noted that the content contained in the computer-readable storage medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable storage media do not include electric carrier signals and telecommunication signals.

[0131] Furthermore, the present application also provides an electronic device. In an electronic device embodiment according to the present application, as shown in FIG5 , the electronic device includes at least one processor 51 and at least one memory 52. ​​The memory 52 can be configured to store a program for executing the battery swap station equipment fault diagnosis method of the above-mentioned method embodiment, and the processor 51 can be configured to execute the program in the memory, which includes but is not limited to a program for executing the battery swap station equipment fault diagnosis method of the above-mentioned method embodiment. For ease of explanation, only the parts related to the embodiment of the present application are shown. For specific technical details not disclosed, please refer to the method part of the embodiment of the present application.

[0132] In the embodiment of the present application, the electronic device may be a control device device formed by various devices. In some possible implementations, the electronic device may include multiple memories and multiple processors. The program for executing the battery swap station equipment fault diagnosis method of the above method embodiment may be divided into multiple subroutines, and each subroutine may be loaded and run by a processor to execute different steps of the battery swap station equipment fault diagnosis method of the above method embodiment. Specifically, each subroutine may be stored in different memories respectively, and each processor may be configured to execute the program in one or more memories to jointly implement the battery swap station equipment fault diagnosis method of the above method embodiment, that is, each processor executes different steps of the battery swap station equipment fault diagnosis method of the above method embodiment respectively to jointly implement the battery swap station equipment fault diagnosis method of the above method embodiment.

[0133] The aforementioned multiple processors may be processors deployed on the same device. For example, the aforementioned electronic device may be a high-performance device composed of multiple processors, and the aforementioned multiple processors may be processors configured on the high-performance device. Furthermore, the aforementioned multiple processors may also be processors deployed on different devices. For example, the aforementioned electronic device may be a server cluster, and the aforementioned multiple processors may be processors on different servers in the server cluster.

[0134] Furthermore, the present application also provides a computer-readable storage medium. In a computer-readable storage medium embodiment according to the present application, the computer-readable storage medium can be configured to store a program for executing the battery swap station equipment fault diagnosis method of the above-mentioned method embodiment, and the program can be loaded and run by the processor to implement the above-mentioned battery swap station equipment fault diagnosis method. For ease of explanation, only the parts related to the embodiment of the present application are shown. For specific technical details not disclosed, please refer to the method part of the embodiment of the present application. The computer-readable storage medium can be a memory device formed by various electronic devices. Optionally, the computer-readable storage medium in the embodiment of the present application is a non-temporary computer-readable storage medium.

[0135] Furthermore, it should be understood that since the configuration of each module is merely for the purpose of illustrating the functional units of the apparatus of the present application, the physical devices corresponding to these modules may be the processor itself, or a portion of the software in the processor, a portion of the hardware, or a combination of software and hardware. Therefore, the number of modules in the figure is merely illustrative.

[0136] Those skilled in the art will appreciate that the various modules in the device can be adaptively split or merged. Such splitting or merging of specific modules will not cause the technical solution to deviate from the principles of this application. Therefore, the technical solutions after splitting or merging will fall within the scope of protection of this application.

[0137] Thus far, the technical solutions of the present application have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is readily understood by those skilled in the art that the scope of protection of the present application is obviously not limited to these specific embodiments. Without departing from the principles of the present application, those skilled in the art may make equivalent changes or substitutions to the relevant technical features, and the technical solutions after such changes or substitutions will fall within the scope of protection of the present application.

Claims

1. A method for diagnosing equipment faults in a battery swap station, characterized in that: The method comprises: Collect data information of battery swap equipment and battery packs; Extracting data features of the battery swap station based on the data information of the battery swap equipment and the battery pack; Obtaining a fault diagnosis model; The fault diagnosis model is used to perform fault diagnosis on the battery swap station equipment based on the battery swap station data characteristics.

2. The method for diagnosing equipment faults in a battery swap station according to claim 1, characterized in that: The fault diagnosis model is obtained by training through the following steps: Acquire multiple historical fault sample data in the battery swap station, and add a sample label to each of the 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; The fault diagnosis model is obtained based on the optimal model parameters.

3. The method for diagnosing equipment faults in a battery swap station according to claim 2, characterized in that: The determining of initial model parameters based on the historical fault sample data and the sample labels corresponding to the historical fault sample data includes: Extracting historical fault sample features based on the historical fault sample data; Inputting each of the historical fault sample features and the sample label corresponding to the historical fault sample data into the fault diagnosis model to obtain a prediction result; The model parameters of the fault diagnosis model are adjusted based on the prediction result and the label until the fault diagnosis model converges to obtain the initial model parameters.

4. The method for diagnosing equipment faults in a battery swap station according to claim 2, characterized in that: After adding a sample label to each of the historical fault sample data, and before determining initial model parameters based on the historical fault sample data and the sample labels corresponding to the historical fault sample data, the method further includes: classifying the sample labels based on the fault type of the battery swap station equipment.

5. The method for diagnosing equipment faults in a battery swap station according to claim 3, characterized in that: The method further comprises: Determining precision and recall based on the prediction results; Determining the accuracy of the fault diagnosis model based on the precision rate and the recall rate; Determining whether any one of the precision rate, the recall rate, and the accuracy is greater than a second preset threshold; If not, continue training the fault diagnosis model based on the historical fault sample data and the sample labels.

6. The method for diagnosing equipment faults in a battery swap station according to claim 1, characterized in that: The data information includes the battery swap equipment fault signal, battery swap equipment fault data, battery swap equipment operating status data and battery pack data information in the battery swap station.

7. The method for diagnosing equipment faults in a battery swap station according to claim 1, characterized in that: The method further comprises: Generate a fault diagnosis report based on the fault diagnosis results of the battery swap station equipment; and / or A maintenance plan for the faulty equipment in the battery swap station is generated based on the fault diagnosis result of the battery swap station equipment.

8. A fault diagnosis device for equipment in a battery swap station, characterized in that: The device comprises: Acquisition module, used to collect data information of battery swap equipment and battery packs; An extraction module, configured to extract data features of a battery swap station based on data information of the battery swap device and the battery pack; An acquisition module, used to acquire a fault diagnosis model; The diagnostic module is used to perform fault diagnosis on the battery swap station equipment based on the battery swap station data characteristics by using the fault diagnosis model.

9. An electronic device comprising at least one processor and at least one memory, wherein the memory is adapted to store a plurality of program codes, wherein: The program code is suitable for being loaded and run by the processor to execute the battery swap station equipment fault diagnosis method according to any one of claims 1 to 7.

10. A computer-readable storage medium storing a plurality of program codes, characterized in that: The program code is suitable for being loaded and run by a processor to execute the battery swap station equipment fault diagnosis method according to any one of claims 1 to 7.

Images