Fault detection method and device of battery changing cabinet and storage medium
By receiving equipment attribute and operating status data from the battery swapping cabinet, and performing feature engineering and model training, the problem of low fault detection efficiency in the battery swapping cabinet is solved, and efficient and accurate fault identification is achieved.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-12-29
- Publication Date
- 2026-04-03
AI Technical Summary
The existing battery swapping cabinets rely on manual inspections and rule-based automatic alarms for fault detection, which makes it difficult to achieve real-time and accurate health status identification, resulting in low detection efficiency.
By receiving equipment attribute data and operating status data from the battery swapping cabinet, feature engineering and exploratory data analysis are performed. The health status is then output using the battery swapping cabinet fault detection model, including exploratory data analysis, feature screening, feature importance ranking, and model training, thereby improving detection efficiency.
It enables efficient fault detection of battery swapping cabinets, improves the real-time performance and accuracy of detection, and enhances the precision of fault identification.
Smart Images
Figure CN121784424A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of artificial intelligence, and more specifically, to a fault detection method, device, and storage medium for a battery swapping cabinet. Background Technology
[0002] The battery swapping cabinet integrates functions such as intelligent control, charging, battery status monitoring, and safe battery storage. It aims to provide fast and safe battery replacement services for electric bicycles, electric motorcycles, and other electric vehicles, effectively improving battery recycling rate and user service experience.
[0003] However, in the existing technology, the fault detection of battery swapping cabinets mainly relies on regular manual inspections and automatic alarms based on preset rules. Manual inspections are difficult to monitor the operating status of all battery swapping cabinets in real time, while rule-based automatic alarm systems are affected by the subjective setting of rules and are difficult to identify the health status of battery swapping cabinets in a timely and accurate manner.
[0004] There is currently no effective solution to the problem of low fault detection efficiency in battery swapping cabinets in related technologies. Summary of the Invention
[0005] The main objective of this application is to provide a fault detection method, device, and storage medium for a battery swapping cabinet, so as to solve the problem of low fault detection efficiency of battery swapping cabinets in related technologies.
[0006] To achieve the above objectives, according to one aspect of this application, a fault detection method for a battery swapping cabinet is provided. The method includes: receiving equipment attribute data and operating status data within a preset time range for the battery swapping cabinet to be tested, wherein the equipment attribute data represents the inherent basic information of the equipment; performing feature engineering based on the operating status data and equipment attribute data to obtain a target feature combination for the battery swapping cabinet to be tested; inputting the target feature combination into a battery swapping cabinet fault detection model; and using the battery swapping cabinet fault detection model to output a detection result for the battery swapping cabinet to be tested, wherein the detection result represents the health status of the battery swapping cabinet.
[0007] Furthermore, feature engineering is performed based on the operating status data and equipment attribute data to obtain the target feature combination of the battery swapping cabinet to be tested, including: conducting exploratory data analysis on the operating status data and equipment attribute data to obtain the data exploratory analysis results, and determining multiple first features based on the data exploratory analysis results; ranking the feature importance based on the multiple first features to obtain the ranking results, and determining multiple second features based on the ranking results; and determining the target feature combination based on the multiple second features and the maintenance log of the battery swapping cabinet to be tested.
[0008] Furthermore, exploratory data analysis is conducted on the operational status data and equipment attribute data. The results of the exploratory data analysis include: handling missing values and outliers in the operational status data and equipment attribute data to obtain processing results; performing correlation analysis based on the processing results to obtain correlation analysis results; performing feature filtering on the operational status data and equipment attribute data based on the correlation analysis results to obtain feature filtering results; determining central tendency measures and dispersion measures based on the feature filtering results; and determining the exploratory data analysis results based on the feature filtering results, central tendency measures, and dispersion measures.
[0009] Further, the importance of multiple first features is ranked to obtain a ranking result, and multiple second features are determined based on the ranking result, including: determining the weight coefficient corresponding to each first feature according to the support vector machine algorithm, wherein the weight coefficient is used to represent the importance of the first feature; ranking the multiple first features according to the weight coefficient to obtain a ranked multiple first features; and extracting a preset number of first features from the ranked multiple first features to obtain multiple second features.
[0010] Furthermore, determining the target feature combination based on multiple second features and the maintenance log of the battery swapping cabinet to be tested includes: determining the maintenance parameters of multiple maintenance components based on the maintenance log of the battery swapping cabinet to be tested, wherein the maintenance parameters include maintenance time and maintenance frequency; and filtering multiple second features based on the maintenance parameters of multiple maintenance components to obtain the target feature combination.
[0011] Furthermore, the training steps for the battery swapping cabinet fault detection model include: obtaining a training dataset for battery swapping cabinet fault detection, wherein the training dataset includes multiple equipment attribute samples, operating status samples, and fault type labels; and training a random forest model based on the training dataset to obtain the battery swapping cabinet fault detection model.
[0012] To achieve the above objectives, according to another aspect of this application, a fault detection device for a battery swapping cabinet is provided. The device includes: a data receiving unit for receiving equipment attribute data and operating status data within a preset time range of the battery swapping cabinet to be tested, wherein the equipment attribute data represents the inherent basic information of the equipment; a feature engineering unit for performing feature engineering based on the operating status data and equipment attribute data to obtain a target feature combination of the battery swapping cabinet to be tested; and a result prediction unit for inputting the target feature combination into a battery swapping cabinet fault detection model and outputting a detection result of the battery swapping cabinet to be tested using the battery swapping cabinet fault detection model, wherein the detection result represents the health status of the battery swapping cabinet.
[0013] Furthermore, the feature engineering unit includes: a first processing module, used to perform exploratory data analysis on operating status data and equipment attribute data, obtain exploratory data analysis results, and determine multiple first features based on the exploratory data analysis results; a second processing module, used to sort the feature importance based on the multiple first features, obtain sorting results, and determine multiple second features based on the sorting results; and a third processing module, used to determine a target feature combination based on the multiple second features and the maintenance log of the battery swapping cabinet to be tested.
[0014] Furthermore, the first processing module includes: a data processing submodule, used to process missing values and outliers in the operating status data and equipment attribute data to obtain processing results; a correlation analysis submodule, used to perform correlation analysis based on the processing results to obtain correlation analysis results, and to perform feature filtering on the operating status data and equipment attribute data based on the correlation analysis results to obtain feature filtering results; and a result determination submodule, used to determine the central tendency measure and dispersion measure based on the feature filtering results, and to determine the data exploratory analysis results based on the feature filtering results, the central tendency measure, and the dispersion measure.
[0015] Furthermore, the second processing module includes: a weight coefficient determination submodule, used to determine the weight coefficient corresponding to each first feature according to the support vector machine algorithm, wherein the weight coefficient is used to represent the importance of the first feature; a feature sorting submodule, used to sort the multiple first features according to the weight coefficient to obtain multiple sorted first features; and a second feature determination submodule, used to extract a preset number of first features from the sorted multiple first features to obtain multiple second features.
[0016] Furthermore, the third processing module includes: a maintenance parameter determination submodule, used to determine the maintenance parameters of multiple maintenance components based on the maintenance log of the battery swapping cabinet to be tested, wherein the maintenance parameters include maintenance time and maintenance frequency; and a target feature combination determination submodule, used to filter multiple second features based on the maintenance parameters of multiple maintenance components to obtain a target feature combination.
[0017] Furthermore, the device also includes: a dataset acquisition unit for acquiring a training dataset for battery swapping cabinet fault detection, wherein the training dataset includes multiple equipment attribute samples, operating status samples, and fault type labels; and a model training unit for training a random forest model based on the training dataset to obtain a battery swapping cabinet fault detection model.
[0018] According to another aspect of this application, a computer-readable storage medium is provided, the computer-readable storage medium including a stored program, wherein, when the program is executed, it controls the device where the computer-readable storage medium is located to execute any fault detection method for a battery swapping cabinet.
[0019] According to another aspect of this application, an electronic device is provided, comprising: one or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, and the one or more programs include a fault detection method for performing any type of battery swapping cabinet.
[0020] According to another aspect of this application, a computer program product is provided, including computer instructions, which, when executed by a processor, implement the steps of the fault detection method for a battery swapping cabinet as described above.
[0021] In this embodiment, the system receives device attribute data and operating status data within a preset time range from the battery swapping cabinet to be tested. The device attribute data represents the inherent basic information of the device. Feature engineering is performed based on the operating status data and device attribute data to obtain a target feature combination of the battery swapping cabinet to be tested. The target feature combination is input into the battery swapping cabinet fault detection model, and the battery swapping cabinet fault detection model outputs the detection result of the battery swapping cabinet to be tested. The detection result represents the health status of the battery swapping cabinet, thus solving the technical problem of low fault detection efficiency of battery swapping cabinets in the prior art. Attached Figure Description
[0022] The accompanying drawings, which form part of this application, are used to provide a further understanding of this application. The illustrative embodiments and descriptions of this application are used to explain this application and do not constitute an undue limitation of this application. In the drawings:
[0023] Figure 1 A hardware structure block diagram of a computer terminal for implementing a fault detection method for a battery swapping cabinet is shown.
[0024] Figure 2 This is a flowchart of a fault detection method for a battery swapping cabinet according to an embodiment of this application;
[0025] Figure 3 This is a schematic diagram of a fault detection device for a battery swapping cabinet according to an embodiment of this application;
[0026] Figure 4 This is a structural block diagram of an electronic device according to an embodiment of this application. Detailed Implementation
[0027] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall within the scope of protection of the present application.
[0028] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.
[0029] It should be noted that the information collected in this application (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for display, data used for analysis, etc.) are information and data authorized by the user or fully authorized by all parties. Furthermore, the collection, storage, use, processing, transmission, provision, disclosure, and application of this data all comply with relevant laws, regulations, and standards, necessary confidentiality measures have been taken, and they do not violate public order and good morals. Corresponding access points are provided for users to choose to authorize or refuse. For example, interfaces are set up between this system and relevant users or organizations, providing users with corresponding access points to choose to agree to or refuse automated decision-making results; if the user chooses to refuse, the process proceeds to the expert decision-making stage.
[0030] Example 1
[0031] According to an embodiment of this application, a method embodiment for fault detection of a battery swapping cabinet is also provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.
[0032] The method embodiment provided in Embodiment 1 of this application can be executed on a mobile terminal, computer terminal, or similar computing device. Figure 1A hardware block diagram of a computer terminal (or mobile device) for implementing a fault detection method for a battery swapping cabinet is shown. Figure 1 As shown, the computer terminal 10 (or mobile device) may include one or more processors 102 (shown as 102a, 102b, ..., 102n in the figure) 102 (processor 102 may include, but is not limited to, a microprocessor MCU or a programmable logic device FPGA, etc.), a memory 104 for storing data, and a transmission device 106 for communication functions. In addition, it may also include: a display, an input / output interface (I / O interface), a universal serial bus (USB) port (which may be included as one of the ports of a BUS bus), a network interface, a power supply, and / or a camera. Those skilled in the art will understand that... Figure 1 The structure shown is for illustrative purposes only and does not limit the structure of the aforementioned electronic device. For example, computer terminal 10 may also include... Figure 1 The more or fewer components shown, or having the same Figure 1 The different configurations shown.
[0033] It should be noted that the aforementioned one or more processors 102 and / or other data processing circuits are generally referred to herein as "data processing circuits". These data processing circuits may be embodied, in whole or in part, in software, hardware, firmware, or any other combination thereof. Furthermore, the data processing circuits may be a single, independent processing module, or may be integrated, in whole or in part, into any other element within the computer terminal 10 (or mobile device). As involved in the embodiments of this application, the data processing circuits serve as a processor control mechanism (e.g., selection of a variable resistor termination path connected to an interface).
[0034] The memory 104 can be used to store software programs and modules for application software, such as the program instructions / data storage device corresponding to the fault detection method for the battery swapping cabinet in this embodiment. The processor 102 executes various functional applications and data processing by running the software programs and modules stored in the memory 104, thereby realizing the aforementioned fault detection method for the battery swapping cabinet. The memory 104 may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include memory remotely located relative to the processor 102, and these remote memories can be connected to the computer terminal 10 via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.
[0035] The transmission device 106 is used to receive or send data via a network. Specific examples of the network described above may include a wireless network provided by the communication provider of the computer terminal 10. In one example, the transmission device 106 includes a Network Interface Controller (NIC), which can connect to other network devices via a base station to communicate with the Internet. In another example, the transmission device 106 may be a Radio Frequency (RF) module, used for wireless communication with the Internet.
[0036] The display may be, for example, a touchscreen liquid crystal display (LCD) that allows the user to interact with the user interface of the computer terminal 10 (or mobile device).
[0037] Under the aforementioned operating environment, this application provides the following: Figure 2 The fault detection method for the battery swapping cabinet is shown. Figure 2 This is a flowchart of a fault detection method for a battery swapping cabinet according to Embodiment 1 of this application.
[0038] Step S201: Receive the device attribute data and operating status data within a preset time range of the battery swapping cabinet to be tested. The device attribute data is used to represent the inherent basic information of the device.
[0039] Optionally, operational status data represents the operation and performance indicators of the battery swapping cabinet during operation. This operational status data is dynamic and may include sensor indicators (e.g., temperature sensor), cabinet control system status, door opening / closing status, battery replacement frequency, remaining battery power, rectifier module status, and charging module status. Equipment attribute data represents the inherent basic information of the equipment, i.e., static data, and may include equipment model, production date, installation date, etc. Equipment attribute data can be determined through equipment ledgers and collected through sensors and intelligent control systems, with a preset time range of up to two months.
[0040] Step S202: Based on the operating status data and equipment attribute data, feature engineering is performed to obtain the target feature combination of the battery swapping cabinet to be tested.
[0041] Optionally, the operational status data includes multiple status data or sensor indicators, while the device attribute data may include multiple basic information. Multiple status data or sensor indicators and multiple basic information can be combined to obtain a first set of features. For example, for discrete basic information such as device model, one-hot encoding can be performed to obtain the corresponding features. Feature engineering can be performed on the first set of features to obtain a second set of features as the target feature combination. For example, feature engineering can be performed on 20 features to obtain 15 features, which are then combined as the target feature combination.
[0042] Step S203: Input the target feature combination into the battery swapping cabinet fault detection model, and use the battery swapping cabinet fault detection model to output the detection result of the battery swapping cabinet to be detected, wherein the detection result is used to represent the health status of the battery swapping cabinet.
[0043] Optionally, a support vector machine, decision tree, or convolutional neural network can be selected as the baseline model for the battery swapping cabinet fault detection model. Samples are collected and labeled to obtain a training dataset for battery swapping cabinet fault detection. The baseline model is trained using the training dataset to obtain the battery swapping cabinet fault detection model. The categories of test results (i.e., fault type labels) can include normal operation (all components and systems of the battery swapping cabinet are in normal working condition, and no abnormal events or fault signals are reported), status warning (minor issues that do not affect normal service are detected in the battery swapping cabinet, such as a temporary decrease in the performance of individual temperature sensors. The battery swapping cabinet can still provide basic service, but it needs to be monitored for potential problems and upgrades), maintenance needs (the battery swapping cabinet has faults that require immediate attention, such as some compartment doors being disabled, charging modules stopping working, rectifier modules malfunctioning, etc. These issues may affect battery replacement efficiency and service quality, but have not completely stopped the system), emergency repair (critical systems of the battery swapping cabinet (e.g., cabinet control system, intelligent power system) have experienced serious failures, resulting in most or all compartments being unavailable and unable to provide battery replacement or charging services), and performance degradation (although the battery swapping cabinet is still running, its performance is significantly lower than normal and requires regular evaluation and optimization).
[0044] In summary, by acquiring the equipment attribute data and operating status data within a preset time range of the battery swapping cabinet to be tested, multiple data sources were obtained from both static and dynamic data dimensions. Based on this, the target feature combination was determined through feature engineering. Then, the detection results of the battery swapping cabinet to be tested were output using the battery swapping cabinet fault detection model, thus achieving efficient acquisition of battery swapping cabinet detection results and improving fault detection efficiency.
[0045] To improve the fault detection efficiency of battery swapping cabinets, feature engineering is performed based on operating status data and equipment attribute data to obtain the target feature combination of the battery swapping cabinet to be tested. This includes: conducting exploratory data analysis on the operating status data and equipment attribute data to obtain the data exploratory analysis results, and determining multiple first features based on the data exploratory analysis results; ranking the feature importance based on the multiple first features to obtain the ranking results, and determining multiple second features based on the ranking results; and determining the target feature combination based on the multiple second features and the maintenance log of the battery swapping cabinet to be tested.
[0046] For example, Exploratory Data Analysis (EDA) is used to understand the distribution of data, identify outliers and missing values through visualization methods, assess the correlation between different features, and obtain exploratory data analysis results. Based on these results, multiple data points in operational status data and multiple basic information points in equipment attribute data are filtered to obtain multiple primary features. Models such as random forests, gradient boosting trees, or regularized regression can be used to determine the ranking of the importance of these primary features, and cross-validation using multiple models can ensure the accuracy of the ranking. Maintenance logs include historical records of faults encountered by the battery swapping cabinet under inspection during actual operation. The target feature combination can be determined based on multiple secondary features and the maintenance logs of the battery swapping cabinet under inspection.
[0047] In summary, by conducting exploratory data analysis on operational status data and equipment attribute data, the results of the exploratory data analysis were obtained, and multiple primary features were determined based on the results. The importance of the features was ranked according to the multiple primary features, and multiple secondary features were determined based on the ranking results. The target feature combination was determined based on the multiple secondary features and the maintenance log of the battery swapping cabinet to be tested, thereby improving the fault detection efficiency of the battery swapping cabinet.
[0048] To improve the fault detection efficiency of the battery swapping cabinet, exploratory data analysis was conducted on the operating status data and equipment attribute data. The results of the exploratory data analysis included: handling missing values and outliers in the operating status data and equipment attribute data; performing correlation analysis based on the handling results; performing feature filtering on the operating status data and equipment attribute data based on the correlation analysis results; determining the central tendency measure and dispersion measure based on the feature filtering results; and finally, determining the exploratory data analysis results based on the feature filtering results, central tendency measure, and dispersion measure.
[0049] Optionally, the pandas library (a Python package) can be used as an exploratory data analysis tool to perform exploratory analysis on operational status data and device attribute data. Missing value and outlier handling can involve examining each column (i.e., feature) in the dataset to identify missing values. If missing values exist, rows containing missing values can be deleted or filled with the corresponding median (or mean). For example, if there are missing values in the "charging module temperature" data, historical average temperatures can be used to fill them. Box plots can be drawn for the operational status data and device attribute data, and outliers can be identified and deleted based on the box plots. Correlation coefficients (e.g., Pearson correlation coefficients) between features in the operational status data and device attribute data can be used to filter and remove features that are redundant with other features, resulting in feature selection results. For example, if "ambient temperature" and "charging module temperature" are highly correlated, only one needs to be retained in the target feature set, improving the efficiency of subsequent model training and the accuracy of prediction. It can calculate the central tendency measure (e.g., mean, median, and mode) and dispersion measure (e.g., standard deviation, variance, range, etc.) for each feature in operational status data and equipment attribute data, and integrate the feature selection results, central tendency measure, and dispersion measure to obtain the data exploratory analysis results.
[0050] In summary, by handling missing and outlier values in the operational status data and equipment attribute data, processing results were obtained. Correlation analysis was performed based on the processing results to obtain correlation analysis results. Feature filtering was then performed on the operational status data and equipment attribute data based on the correlation analysis results to obtain feature filtering results. Central tendency and dispersion measures were determined based on the feature filtering results, central tendency and dispersion measures, and exploratory data analysis results were determined based on the feature filtering results, central tendency and dispersion measures, thereby improving the fault detection efficiency of the battery swapping cabinet.
[0051] To improve the fault detection efficiency of the battery swapping cabinet, multiple first features are ranked according to their importance to obtain a ranking result. Based on the ranking result, multiple second features are determined, including: determining the weight coefficient corresponding to each first feature according to the support vector machine algorithm, where the weight coefficient is used to represent the importance of the first feature; ranking the multiple first features according to the weight coefficient to obtain a ranked set of first features; and extracting a preset number of first features from the ranked set of first features to obtain multiple second features.
[0052] For example, a Support Vector Machine (SVM) algorithm can be used to train a training dataset for battery swapping cabinet fault detection (feature engineering, as described above, yields the first features corresponding to the training dataset). After training, an SVM model is obtained. The SVM model assigns a weight coefficient to each first feature. The absolute value of the weight coefficient reflects the contribution of the first feature to the decision boundary of the SVM, i.e., the importance of the feature. First features with larger weight coefficients contribute more to the decision boundary. The weight coefficients of each first feature can be sorted from largest to smallest, resulting in a list of first features in descending order of weight coefficients. A predetermined number of first features (e.g., 10) are then selected from the list of first features and used as the second features.
[0053] In summary, by determining the weight coefficients corresponding to each first feature based on the support vector machine algorithm, where the weight coefficients represent the importance of the first feature; sorting the multiple first features according to the weight coefficients to obtain sorted first features; and extracting a preset number of first features from the sorted first features to obtain multiple second features, the fault detection efficiency of the battery swapping cabinet is improved.
[0054] To improve the fault detection efficiency of battery swapping cabinets, the target feature combination is determined based on multiple second features and the maintenance log of the battery swapping cabinet to be tested. This includes: determining the maintenance parameters of multiple maintenance components based on the maintenance log of the battery swapping cabinet to be tested, wherein the maintenance parameters include maintenance time and maintenance frequency; and filtering multiple second features based on the maintenance parameters of multiple maintenance components to obtain the target feature combination.
[0055] For example, maintenance parameters for each repairable component can be determined from the maintenance log. These parameters include maintenance time and frequency. Maintenance time can be the latest maintenance time for that component from the current time, and maintenance frequency can refer to the number of times that component is repaired within a fixed time period (e.g., one year). The time difference between the maintenance time and the current time can be determined, and the feature corresponding to the repairable component can be identified from multiple second features (e.g., the feature corresponding to a cabinet door sensor is the door opening and closing frequency). The time difference is multiplied by a first coefficient to obtain a first score, and the maintenance frequency is multiplied by a second coefficient to obtain a second score. The first score and the second score are added to obtain the log score corresponding to that feature. For multiple repairable components involved in the maintenance log, the feature corresponding to each repairable component is identified from multiple second features, resulting in multiple features to be filtered. Features among the multiple second features that do not correspond to repairable components are not included in the filtering. The log score corresponding to each feature to be filtered is calculated based on the maintenance time and maintenance frequency. Features among the multiple second features whose log scores are less than or equal to a preset score threshold are deleted, resulting in the target feature combination.
[0056] In summary, by determining the maintenance parameters of multiple repairable components based on the maintenance logs of the battery swapping cabinet to be tested, including maintenance time and frequency, and by filtering multiple secondary features based on the maintenance parameters of multiple repairable components, a target feature combination is obtained, which improves the fault detection efficiency of the battery swapping cabinet.
[0057] To improve the efficiency of fault detection in battery swapping cabinets, the training steps for the fault detection model include: obtaining a training dataset for battery swapping cabinet fault detection, which includes multiple device attribute samples, operating status samples, and fault type labels; and training a random forest model based on the training dataset to obtain the battery swapping cabinet fault detection model.
[0058] For example, the system can include the battery swapping cabinet's log system, sensor data acquisition equipment attribute samples, operating status samples, and fault type labels. Equipment attribute samples may include equipment model, service life, etc.; operating status samples may include actual values such as temperature, voltage, and current; fault type labels are obtained by annotating the sample data based on historical fault records. The equipment attribute samples and operating status samples can be processed using the feature engineering methods described above to obtain a processed sample feature set. Then, based on the processed sample feature set and fault type labels, a random forest model can be trained to obtain the battery swapping cabinet fault detection model.
[0059] In summary, by obtaining a training dataset for battery swapping cabinet fault detection, which includes multiple device attribute samples, operating status samples, and fault type labels, and training a random forest model based on the training dataset, a battery swapping cabinet fault detection model is obtained, thus improving the fault detection efficiency of the battery swapping cabinet.
[0060] It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases the steps shown or described may be executed in a different order than that shown here.
[0061] Example 2
[0062] This application also provides a fault detection device for a battery swapping cabinet. It should be noted that the fault detection device for the battery swapping cabinet in this application can be used to execute the fault detection method for the battery swapping cabinet provided in this application. The following describes the fault detection device for the battery swapping cabinet provided in this application.
[0063] According to an embodiment of this application, an apparatus for implementing the above-described fault detection method for a battery swapping cabinet is also provided, such as... Figure 3 As shown, the device includes:
[0064] The data receiving unit 301 is used to receive the equipment attribute data and the operating status data within a preset time range of the battery swapping cabinet to be tested. The equipment attribute data is used to represent the basic information inherent in the equipment.
[0065] Feature engineering unit 302 is used to perform feature engineering based on operating status data and equipment attribute data to obtain the target feature combination of the battery swapping cabinet to be tested.
[0066] The result prediction unit 303 is used to input the target feature combination into the battery swapping cabinet fault detection model, and use the battery swapping cabinet fault detection model to output the detection result of the battery swapping cabinet to be detected, wherein the detection result is used to represent the health level of the battery swapping cabinet.
[0067] The fault detection device for a battery swapping cabinet provided in this application embodiment receives equipment attribute data and operating status data within a preset time range from the battery swapping cabinet to be detected through a data receiving unit 301. The equipment attribute data represents the inherent basic information of the equipment. A feature engineering unit 302 performs feature engineering based on the operating status data and equipment attribute data to obtain a target feature combination for the battery swapping cabinet to be detected. A result prediction unit 303 inputs the target feature combination into a battery swapping cabinet fault detection model, and the model outputs the detection result for the battery swapping cabinet to be detected. The detection result represents the health status of the battery swapping cabinet, thus solving the problem of low fault detection efficiency in related technologies. This achieves the effect of improving the fault detection efficiency of battery swapping cabinets.
[0068] Optionally, in the fault detection device for the battery swapping cabinet provided in this application embodiment, the feature engineering unit 302 includes: a first processing module, used to perform exploratory data analysis on operating status data and equipment attribute data, obtain exploratory data analysis results, and determine multiple first features based on the exploratory data analysis results; a second processing module, used to sort the feature importance based on the multiple first features, obtain sorting results, and determine multiple second features based on the sorting results; and a third processing module, used to determine a target feature combination based on the multiple second features and the maintenance log of the battery swapping cabinet to be detected.
[0069] Optionally, in the fault detection device for the battery swapping cabinet provided in this application embodiment, the first processing module includes: a data processing submodule, used to process missing values and outliers in the operating status data and equipment attribute data to obtain processing results; a correlation analysis submodule, used to perform correlation analysis based on the processing results to obtain correlation analysis results, and to perform feature filtering on the operating status data and equipment attribute data based on the correlation analysis results to obtain feature filtering results; and a result determination submodule, used to determine the central tendency measure and dispersion measure based on the feature filtering results, and to determine the data exploratory analysis results based on the feature filtering results, the central tendency measure, and the dispersion measure.
[0070] Optionally, in the fault detection device for the battery swapping cabinet provided in this application embodiment, the second processing module includes: a weight coefficient determination submodule, used to determine the weight coefficient corresponding to each first feature according to the support vector machine algorithm, wherein the weight coefficient is used to represent the importance of the first feature; a feature sorting submodule, used to sort the multiple first features according to the weight coefficient to obtain the sorted multiple first features; and a second feature determination submodule, used to extract a preset number of first features from the sorted multiple first features to obtain multiple second features.
[0071] Optionally, in the fault detection device for the battery swapping cabinet provided in this application embodiment, the third processing module includes: a maintenance parameter determination submodule, used to determine the maintenance parameters of multiple maintenance components based on the maintenance log of the battery swapping cabinet to be tested, wherein the maintenance parameters include maintenance time and maintenance frequency; and a target feature combination determination submodule, used to filter multiple second features based on the maintenance parameters of multiple maintenance components to obtain a target feature combination.
[0072] Optionally, in the fault detection device for the battery swapping cabinet provided in the embodiments of this application, the device further includes: a dataset acquisition unit, used to acquire a training dataset for battery swapping cabinet fault detection, wherein the training dataset includes multiple equipment attribute samples, operating status samples and fault type labels; and a model training unit, used to train a random forest model based on the training dataset to obtain a battery swapping cabinet fault detection model.
[0073] It should be noted that the data receiving unit 301, feature engineering unit 302, and result prediction unit 303 mentioned above correspond to steps S201 to S203 in Embodiment 1. The instances and application scenarios implemented by the units and corresponding steps are the same, but are not limited to the content disclosed in Embodiment 1. It should be noted that the above modules or units can be hardware or software components stored in memory (e.g., memory 104) and processed by one or more processors (e.g., processors 102a, 102b, ..., 102n). The above modules can also be part of the device and run in the computer terminal 10 provided in Embodiment 1.
[0074] Example 3
[0075] Embodiments of this application may provide an electronic device. Figure 4 This is a structural block diagram of an electronic device according to an embodiment of this application. Figure 4 As shown, the electronic device may include: one or more ( Figure 4 (Only one is shown) Processor 402, memory 404, memory controller, and peripheral interface, wherein the peripheral interface is connected to the radio frequency module, audio module and display.
[0076] The memory can be used to store software programs and modules, such as the program instructions / modules corresponding to the methods and apparatus in the embodiments of this application. The processor executes various functional applications and data processing by running the software programs and modules stored in the memory, thereby implementing the above-described methods. The memory may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory may further include memory remotely located relative to the processor, and these remote memories can be connected to the terminal via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.
[0077] The processor can call the information and application program stored in the memory through the transmission device to perform the following steps: receiving the equipment attribute data and the operating status data within a preset time range of the battery swapping cabinet to be tested, wherein the equipment attribute data is used to represent the inherent basic information of the equipment; performing feature engineering based on the operating status data and equipment attribute data to obtain the target feature combination of the battery swapping cabinet to be tested; inputting the target feature combination into the battery swapping cabinet fault detection model, and using the battery swapping cabinet fault detection model to output the detection result of the battery swapping cabinet to be tested, wherein the detection result is used to represent the health level of the battery swapping cabinet.
[0078] The processor can also call the information and application programs stored in the memory through the transmission device to perform the following steps: perform exploratory data analysis on the operating status data and device attribute data to obtain the data exploratory analysis results, and determine multiple first features based on the data exploratory analysis results; sort the feature importance based on the multiple first features to obtain the sorting results, and determine multiple second features based on the sorting results; determine the target feature combination based on the multiple second features and the maintenance log of the battery swapping cabinet to be tested.
[0079] The processor can also call the information and application programs stored in the memory through the transmission device to perform the following steps: perform missing value processing and outlier processing on the operating status data and device attribute data to obtain processing results; perform correlation analysis based on the processing results to obtain correlation analysis results, and perform feature filtering on the operating status data and device attribute data based on the correlation analysis results to obtain feature filtering results; determine the central tendency measure and dispersion measure based on the feature filtering results, and determine the data exploratory analysis results based on the feature filtering results, central tendency measure, and dispersion measure.
[0080] The processor can also call the information and application stored in the memory through the transmission device to perform the following steps: determine the weight coefficient corresponding to each first feature according to the support vector machine algorithm, wherein the weight coefficient is used to represent the importance of the first feature; sort the multiple first features according to the weight coefficient to obtain multiple sorted first features; extract a preset number of first features from the sorted multiple first features to obtain multiple second features.
[0081] The processor can also call the information and application program stored in the memory through the transmission device to perform the following steps: determine the maintenance parameters of multiple maintenance parts based on the maintenance log of the battery swapping cabinet to be tested, wherein the maintenance parameters include maintenance time and maintenance frequency; filter multiple second features based on the maintenance parameters of multiple maintenance parts to obtain a target feature combination.
[0082] The processor can also call the information and application stored in the memory through the transmission device to perform the following steps: obtain the training dataset for battery swapping cabinet fault detection, wherein the training dataset includes multiple equipment attribute samples, operating status samples and fault type labels; train the random forest model based on the training dataset to obtain the battery swapping cabinet fault detection model.
[0083] This application provides a fault detection scheme for battery swapping cabinets. It receives equipment attribute data and operating status data within a preset time range from the battery swapping cabinet to be tested. The equipment attribute data represents the inherent basic information of the equipment. Feature engineering is performed based on the operating status data and equipment attribute data to obtain a target feature combination for the battery swapping cabinet to be tested. This target feature combination is input into a battery swapping cabinet fault detection model, which then outputs the detection result of the battery swapping cabinet to be tested. The detection result represents the health status of the battery swapping cabinet, thus solving the technical problem of low fault detection efficiency in existing battery swapping cabinet technologies.
[0084] Those skilled in the art will understand that Figure 4 The structure shown is for illustrative purposes only. Electronic devices can also be smartphones, tablets, handheld computers, mobile internet devices (MIDs), PADs, and other terminal devices. Figure 4 This does not limit the structure of the aforementioned electronic device. For example, electronic devices may also include components that are more... Figure 4 The more or fewer components shown (such as network interfaces, display devices, etc.), or having the same Figure 4 The different configurations shown.
[0085] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be implemented by a program instructing the hardware related to the terminal device. The program can be stored in a computer-readable storage medium, which may include: flash drive, read-only memory (ROM), random access memory (RAM), disk or optical disk, etc.
[0086] Example 4
[0087] Embodiments of this application also provide a storage medium. Optionally, in this embodiment, the storage medium can be used to store the program code executed by the fault detection method of the battery swapping cabinet provided in Embodiment 1.
[0088] Optionally, in this embodiment, the storage medium may be located in any computer terminal in a group of computer terminals in a computer network, or in any mobile terminal in a group of mobile terminals.
[0089] Optionally, in this embodiment, the computer-readable storage medium is configured to store program code for performing the following steps: receiving device attribute data and operating status data within a preset time range for the battery swapping cabinet to be tested, wherein the device attribute data is used to represent the inherent basic information of the device; performing feature engineering based on the operating status data and device attribute data to obtain a target feature combination for the battery swapping cabinet to be tested; inputting the target feature combination into a battery swapping cabinet fault detection model, and using the battery swapping cabinet fault detection model to output the detection result of the battery swapping cabinet to be tested, wherein the detection result is used to represent the health level of the battery swapping cabinet.
[0090] Optionally, in this embodiment, the computer-readable storage medium is further configured to store program code for performing the following steps: performing exploratory data analysis on operating status data and device attribute data to obtain exploratory data analysis results, and determining multiple first features based on the exploratory data analysis results; ranking the features according to their importance based on the multiple first features to obtain ranking results, and determining multiple second features based on the ranking results; and determining a target feature combination based on the multiple second features and the maintenance log of the battery swapping cabinet to be detected.
[0091] Optionally, in this embodiment, the computer-readable storage medium is further configured to store program code for performing the following steps: handling missing values and outliers in the operating status data and device attribute data to obtain processing results; performing correlation analysis based on the processing results to obtain correlation analysis results, and performing feature filtering on the operating status data and device attribute data based on the correlation analysis results to obtain feature filtering results; determining central tendency measure and dispersion measure based on the feature filtering results, and determining data exploratory analysis results based on the feature filtering results, central tendency measure, and dispersion measure.
[0092] Optionally, in this embodiment, the computer-readable storage medium is further configured to store program code for performing the following steps: determining the weight coefficient corresponding to each first feature according to the support vector machine algorithm, wherein the weight coefficient is used to represent the importance of the first feature; sorting the multiple first features according to the weight coefficient to obtain a sorted multiple first features; extracting a preset number of first features from the sorted multiple first features to obtain a multiple second features.
[0093] Optionally, in this embodiment, the computer-readable storage medium is further configured to store program code for performing the following steps: determining maintenance parameters of multiple maintenance components based on the maintenance log of the battery swapping cabinet to be tested, wherein the maintenance parameters include maintenance time and maintenance frequency; filtering multiple second features based on the maintenance parameters of the multiple maintenance components to obtain a target feature combination.
[0094] Optionally, in this embodiment, the computer-readable storage medium is further configured to store program code for performing the following steps: obtaining a training dataset for battery swapping cabinet fault detection, wherein the training dataset includes multiple device attribute samples, operating status samples, and fault type labels; training a random forest model based on the training dataset to obtain a battery swapping cabinet fault detection model.
[0095] This application also provides a computer program product, which, when executed on a data processing device, is suitable for performing the steps of a fault detection method for a battery swapping cabinet.
[0096] The sequence numbers of the embodiments in this application are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.
[0097] In the above embodiments of this application, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.
[0098] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual coupling, direct coupling, or communication connection may be through some interfaces; the indirect coupling or communication connection between units or modules may be electrical or other forms.
[0099] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.
[0100] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.
[0101] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as a USB flash drive, read-only memory (ROM), random access memory (RAM), portable hard drive, magnetic disk, or optical disk.
[0102] The above description is only a preferred embodiment of this application. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of this application, and these improvements and modifications should also be considered within the scope of protection of this application.
Claims
1. A fault detection method for a battery swapping cabinet, characterized in that, include: The device receives equipment attribute data and operating status data within a preset time range for the battery swapping cabinet to be tested, wherein the equipment attribute data is used to represent the inherent basic information of the device; Based on the operating status data and the equipment attribute data, feature engineering is performed to obtain the target feature combination of the battery swapping cabinet to be detected; The target features are combined and input into the battery swapping cabinet fault detection model. The battery swapping cabinet fault detection model is used to output the detection result of the battery swapping cabinet to be detected, wherein the detection result is used to represent the health status of the battery swapping cabinet.
2. The method according to claim 1, characterized in that, Based on the operating status data and the equipment attribute data, feature engineering is performed to obtain the target feature combination of the battery swapping cabinet to be detected, including: The operating status data and the device attribute data are subjected to exploratory data analysis to obtain exploratory data analysis results, and multiple first features are determined based on the exploratory data analysis results; The importance of the features is ranked according to the plurality of first features to obtain a ranking result, and a plurality of second features are determined according to the ranking result; The target feature combination is determined based on the plurality of second features and the maintenance log of the battery swapping cabinet to be detected.
3. The method according to claim 2, characterized in that, Exploratory data analysis was performed on the operational status data and the device attribute data, and the results of the exploratory data analysis include: The missing value and outlier value processing are performed on the operating status data and the device attribute data to obtain the processing result; Based on the processing results, a correlation analysis is performed to obtain the correlation analysis results. Based on the correlation analysis results, feature filtering is performed on the operating status data and the device attribute data to obtain the feature filtering results. Based on the feature selection results, a central tendency measure and a dispersion measure are determined, and based on the feature selection results, the central tendency measure, and the dispersion measure, the data exploratory analysis results are determined.
4. The method according to claim 2, characterized in that, Based on the plurality of first features, feature importance is ranked to obtain a ranking result, and based on the ranking result, a plurality of second features are determined, including: The weight coefficients corresponding to each of the first features are determined based on the support vector machine algorithm, wherein the weight coefficients are used to represent the importance of the first feature; The plurality of first features are sorted according to the weight coefficients to obtain a plurality of sorted first features; A predetermined number of first features are extracted from the sorted first features to obtain the plurality of second features.
5. The method according to claim 2, characterized in that, The target feature combination is determined based on the plurality of second features and the maintenance log of the battery swapping cabinet to be detected, including: Based on the maintenance log of the battery swapping cabinet to be tested, the maintenance parameters of multiple maintenance components are determined, wherein the maintenance parameters include maintenance time and maintenance frequency; The target feature combination is obtained by filtering the multiple second features based on the maintenance parameters of the multiple maintenance parts.
6. The method according to claim 1, characterized in that, The training steps for the battery swapping cabinet fault detection model include: Obtain a training dataset for battery swapping cabinet fault detection, wherein the training dataset includes multiple device attribute samples, operating status samples, and fault type labels; The random forest model is trained based on the training dataset to obtain the fault detection model for the battery swapping cabinet.
7. A fault detection device for a battery swapping cabinet, characterized in that, include: The data receiving unit is used to receive the equipment attribute data and the operating status data within a preset time range of the battery swapping cabinet to be tested, wherein the equipment attribute data is used to represent the inherent basic information of the equipment; The feature engineering unit is used to perform feature engineering based on the operating status data and the equipment attribute data to obtain the target feature combination of the battery swapping cabinet to be detected. The result prediction unit is used to input the target feature combination into the battery swapping cabinet fault detection model, and use the battery swapping cabinet fault detection model to output the detection result of the battery swapping cabinet to be detected, wherein the detection result is used to represent the health level of the battery swapping cabinet.
8. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored executable program, wherein, when the executable program is executed, it controls the device containing the computer-readable storage medium to perform the fault detection method for the battery swapping cabinet according to any one of claims 1 to 6.
9. An electronic device, characterized in that, include: Memory, which stores executable programs; A processor for running the program, wherein the program executes the fault detection method for the battery swapping cabinet according to any one of claims 1 to 6.
10. A computer program product comprising computer instructions, characterized in that, When the computer instructions are executed by the processor, they implement the steps of the fault detection method for the battery swapping cabinet according to any one of claims 1 to 6.