Method and related device for identifying charging pile fault type

Abstract

The present application provides a method and related device for identifying the fault type of a charging pile, the method comprising: obtaining multiple working states of a target charging pile; obtaining all sample data sets corresponding to the multiple working states to obtain a reference data set; performing a preset data processing operation on the reference data set to obtain a target data set; dividing the target data set according to a preset ratio to obtain a training set and a test set; building a model based on the training set and training to obtain a target model; the target model is used to identify the working state of the target charging pile; testing the target model based on the test set to obtain a test result, and determining a target model performance indicator corresponding to the test result; if the target model performance indicator meets the preset conditions, the real-time operation data of the target charging pile is input into the target model to obtain a target working state label.

Description

Technical Field

[0001] The present application relates to the technical field of charging pile fault identification in data identification, and in particular to a method for identifying charging pile fault types and related devices. Background Art

[0002] At present, in the field of electric vehicle charging facilities, especially in the fault identification of charging pile equipment, traditional fault identification methods usually rely on manual experience or preset thresholds, but this method is likely to lead to misjudgment and it is difficult to accurately identify the specific fault type, thus affecting maintenance efficiency and accuracy.

[0003] Therefore, how to accurately identify the fault types of charging piles in order to improve operation and maintenance efficiency needs to be solved urgently. Summary of the invention

[0004] The embodiments of the present application provide a method and related device for identifying the fault type of a charging pile. By collecting sample data of the charging pile in different working conditions and performing preset data processing operations on the sample data, the data quality and the accuracy of feature extraction can be improved, thereby improving the accuracy of identifying the fault type of the charging pile.

[0005] In a first aspect, an embodiment of the present application provides a method for identifying a fault type of a charging pile, the method comprising:

[0006] Acquire multiple working states of the target charging pile; the multiple working states include a fault state and a normal state; each of the a fault states corresponds to a fault category; each working state corresponds to a working state label and a sample data set, and each sample data set includes at least one operation data; a is a positive integer;

[0007] Acquire all sample data sets corresponding to the multiple working states to obtain a reference data set;

[0008] Performing a preset data processing operation on the reference data set to obtain a target data set;

[0009] Dividing the target data set according to a preset ratio to obtain a training set and a test set;

[0010] A model is built and trained according to the training set to obtain a target model; the target model is used to identify the working status of the target charging pile;

[0011] Testing the target model according to the test set to obtain a test result, and determining a target model performance indicator corresponding to the test result;

[0012] If the performance index of the target model meets the preset conditions, the real-time operation data of the target charging pile is input into the target model to obtain the target working status label.

[0013] In a second aspect, an embodiment of the present application provides a device for identifying a fault type of a charging pile, the device comprising an acquisition module, a processing module, a division module, a training module, a testing module, and an identification module, wherein:

[0014] The acquisition module is used to acquire multiple working states of the target charging pile; the multiple working states include a fault state and a normal state; each of the a fault states corresponds to a fault category; each working state corresponds to a working state label and a sample data set, and each sample data set includes at least one operation data; a is a positive integer;

[0015] The acquisition module is further used to acquire all sample data sets corresponding to the multiple working states to obtain a reference data set;

[0016] The processing module is used to perform a preset data processing operation on the reference data set to obtain a target data set;

[0017] The partitioning module is used to partition the target data set according to a preset ratio to obtain a training set and a test set;

[0018] The training module is used to build a model according to the training set and perform training to obtain a target model; the target model is used to identify the working status of the target charging pile;

[0019] The testing module is used to test the target model according to the test set, obtain the test result, and determine the target model performance index corresponding to the test result;

[0020] The identification module is used to input the real-time operation data of the target charging pile into the target model to obtain a target working status label if the performance index of the target model meets the preset conditions.

[0021] In a third aspect, an embodiment of the present application provides an electronic device, comprising a processor, a memory, a communication interface, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the processor, and the program includes instructions for executing the steps of any method in the first aspect of the embodiment of the present application.

[0022] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program for electronic data exchange, wherein the computer program enables a computer to execute part or all of the steps described in any method of the first aspect of the embodiment of the present application.

[0023] In a fifth aspect, an embodiment of the present application provides a computer program product, wherein the computer program product includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to cause a computer to execute some or all of the steps described in any method of the first aspect of the embodiment of the present application. The computer program product may be a software installation package.

[0024] By implementing the embodiments of the present application, sample data of the charging pile in different working conditions can be collected, and preset data processing operations can be performed on the sample data, which helps to improve data quality and the accuracy of feature extraction, thereby improving the accuracy of identifying the fault type of the charging pile. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0026] Figure 1 This is a system architecture diagram of a charging pile intelligent fault diagnosis system provided in an embodiment of the present application;

[0027] Figure 2 It is a structural schematic diagram of an electronic device provided in an embodiment of the present application;

[0028] Figure 3 It is a flowchart of a method for identifying a charging pile fault type provided in an embodiment of the present application;

[0029] Figure 4 This is a block diagram of the functional modules of a device for identifying charging pile fault types provided in an embodiment of the present application. DETAILED DESCRIPTION

[0030] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0031] The terms "first", "second", etc. in the specification and claims of this application and the above-mentioned drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally includes steps or units that are not listed, or optionally includes other steps or units inherent to these processes, methods, products or devices.

[0032] It should be understood that the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article indicates that the associated objects before and after are in an "or" relationship. The "plurality" appearing in the embodiments of the present application refers to two or more.

[0033] In the embodiments of the present application, "at least one item" or similar expressions refer to any combination of these items, including any combination of single items or plural items, and refer to one or more, and multiple refers to two or more. For example, at least one item of a, b, or c can represent the following seven situations: a, b, c, a and b, a and c, b and c, a, b, and c. Among them, each of a, b, and c can be an element or a set containing one or more elements.

[0034] The "connection" that appears in the embodiments of the present application refers to various connection methods such as direct connection or indirect connection to achieve communication between devices, and the embodiments of the present application do not impose any limitations on this.

[0035] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0036] The following is an explanation of the relevant terms involved in this application, as follows:

[0037] One-dimensional convolutional neural network (1D-CNN) model: refers to an important deep learning model that is widely used in signal processing, speech recognition, text classification and other fields.

[0038] Adaptive Moment Estimation (Adam) algorithm: refers to an optimization algorithm widely used in deep learning, which combines the advantages of momentum and adaptive learning rate and is suitable for processing sparse gradients and non-stationary targets.

[0039] Hilbert-Huang Transform (HHT) marginal spectrum: refers to a time-frequency analysis method that can reveal the amplitude changes of the signal in the frequency domain, can provide higher time-frequency resolution, and is suitable for processing non-stationary signals.

[0040] At present, in the field of electric vehicle charging facilities, especially in the fault identification of charging pile equipment, traditional fault identification methods usually rely on manual experience or preset thresholds, but this method is likely to lead to misjudgment and it is difficult to accurately identify the specific fault type, thus affecting maintenance efficiency and accuracy. Therefore, how to accurately identify the fault type of charging piles to improve operation and maintenance efficiency is an urgent problem to be solved.

[0041] To solve the above problems, an embodiment of the present application provides a method and a related device for identifying the fault type of a charging pile. First, multiple working states of a target charging pile are obtained; the multiple working states include a fault states and a normal state; each of the a fault states corresponds to a fault category; each working state corresponds to a working state label and a sample data set, and each sample data set includes at least one operation data; a is a positive integer; then, all sample data sets corresponding to the multiple working states are obtained to obtain a reference data set; a preset data processing operation is performed on the reference data set to obtain a target data set; the target data set is divided according to a preset ratio to obtain a training set and a test set; a model is built and trained according to the training set to obtain a target model; the target model is used to identify the working state of the target charging pile; finally, the target model is tested according to the test set to obtain a test result, and a target model performance indicator corresponding to the test result is determined; if the target model performance indicator meets the preset conditions, the real-time operation data of the target charging pile is input into the target model to obtain a target working state label. By collecting sample data of charging piles under different working conditions and performing preset data processing operations on the sample data, the data quality and the accuracy of feature extraction can be improved, thereby improving the accuracy of identifying charging pile fault types.

[0042] Combine the following Figure 1 A system architecture for executing a method for identifying a charging pile fault type in an embodiment of the present application is described. Figure 1It is a system architecture diagram of a charging pile intelligent fault diagnosis system provided in an embodiment of the present application. The charging pile intelligent fault diagnosis system includes a data acquisition module, a data preprocessing module, a neural network training module, and a fault diagnosis module.

[0043] Among them, the data acquisition module is used to collect the operation data of the charging pile, which includes but is not limited to current, voltage, temperature, and charging status. The collected data can be stored and transmitted to the data preprocessing module to ensure that the data can smoothly enter the next processing flow. The data preprocessing module is used to clean, extract features, and divide the data. It can remove noise and outliers in the data to ensure data quality, and divide the processed data into training sets and test sets to prepare for model training and evaluation. The neural network training module is used to establish a neural network model based on the training set, select a suitable network architecture, such as a convolutional neural network, a recurrent neural network, etc., and train the neural network model so that it can effectively identify and predict the fault category of the charging pile. The fault diagnosis module is used for real-time diagnosis, fault warning, and status reporting. The fault diagnosis module can analyze the operation data of the charging pile in real time based on the trained neural network model, identify the current working status, and if its working status is a faulty state, it can also identify the corresponding fault category. When a potential fault or abnormality is detected, an alarm can be issued in time or the maintenance personnel can be notified so that appropriate measures can be taken to repair or prevent it. At the same time, the fault diagnosis module can generate and display the status report of the charging pile, including the diagnosis results and fault history records, to provide a reference for maintenance and management.

[0044] It can be seen that through the above system architecture, machine learning and neural network technology can be used to accurately identify the working status and fault category of the charging pile, reduce false alarms and missed alarms, and ensure that the cause of the charging pile failure can be accurately identified, thereby saving time and maintenance costs.

[0045] Combine the following Figure 2 The electronic device in the embodiment of the present application is described. Figure 2 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application is shown in FIG. Figure 2 As shown, the electronic device includes one or more processors, a memory, a communication interface and one or more programs, and the processor is communicatively connected with the memory and the communication interface via an internal communication bus.

[0046] Among them, the processor is mainly used for:

[0047] Acquire multiple working states of the target charging pile; the multiple working states include a fault state and a normal state; each fault state in the a fault state corresponds to a fault category; each working state corresponds to a working state label and a sample data set, and each sample data set includes at least one operation data; a is a positive integer;

[0048] Obtain all sample data sets corresponding to multiple working states to obtain a reference data set;

[0049] Performing a preset data processing operation on the reference data set to obtain a target data set;

[0050] Divide the target data set according to the preset ratio to obtain the training set and the test set;

[0051] Build a model based on the training set and perform training to obtain a target model; the target model is used to identify the working status of the target charging pile;

[0052] Test the target model according to the test set, obtain the test results, and determine the target model performance indicators corresponding to the test results;

[0053] If the performance index of the target model meets the preset conditions, the real-time operation data of the target charging pile is input into the target model to obtain the target working status label.

[0054] The one or more programs are stored in the above-mentioned memory and are configured to be executed by the above-mentioned processor, and the one or more programs include instructions for executing any step in the above-mentioned method embodiment.

[0055] Among them, the processor can be, for example, a central processing unit (CPU), a general processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, transistor logic devices, hardware components or any combination thereof. It can implement or execute various exemplary logic blocks, units and circuits described in conjunction with the disclosure of this application. The processor can also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of DSP and microprocessors, and the like. The communication unit can be a communication interface, a transceiver, a transceiver circuit, and the like, and the storage unit can be a memory.

[0056] The memory may be a volatile memory or a nonvolatile memory, or may include both volatile and nonvolatile memories. Among them, the nonvolatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may be a random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of random access memory (RAM) are available, such as static RAM (SRAM), dynamic random access memory (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), and direct RAM bus RAM (DR RAM).

[0057] It is understandable that the electronic device may include more or fewer structural elements than those in the above structural block diagram, for example, including a power module, physical buttons, Wi-Fi module, speaker, Bluetooth module, sensor, display module, etc., which are not limited here. It is understandable that the electronic device may be equipped with Figure 1 The system architecture described.

[0058] After understanding the software and hardware architecture of this application, Figure 3 A method for identifying a charging pile fault type in an embodiment of the present application is described. Figure 3 A flow chart of a method for identifying a charging pile fault type provided in an embodiment of the present application specifically includes the following steps:

[0059] Step S301, obtaining multiple working states of the target charging pile.

[0060] Among them, the multiple working states include a fault states and one normal state; each of the a fault states corresponds to a fault category; each working state corresponds to a working state label and a sample data set, and each sample data set includes at least one operation data; a is a positive integer.

[0061] Specifically, the historical operation data of the target charging pile can be analyzed and classified to obtain a fault state. Among them, the target charging pile includes but is not limited to the charging pile of electric vehicles, the charging pile of electric bicycles, and the charging pile of electric motorcycles. Each fault state corresponds to a fault category. For example, the fault category corresponding to the first fault state is the charging module output overvoltage, and the fault category corresponding to the second fault state is the charging module output overcurrent. It should be noted that the fault category includes but is not limited to the charging module output overvoltage, the charging module output overcurrent, the charging module output short circuit, the charging module fault, the AC input fault, and the AC circuit breaker fault. In addition, each working state corresponds to a working state label and a sample data set. For example, the working state label corresponding to the first working state is 1, and corresponds to the first sample data set, and the working state label corresponding to the second working state is 2, and corresponds to the second sample data set. It should be noted that each sample data set includes M1 operating data, and the sampling frequency is D, and M1 and D are both positive integers. Among them, the operating data includes but is not limited to the charging module input voltage, the charging module input current, the charging module output voltage, the charging module output current, the charging module output power, the target demand voltage, and the target demand current.

[0062] It should be noted that the target charging pile includes but is not limited to a charging module, a power module, a control system, a communication module, a safety protection device, and a heat dissipation system. Among them, the charging module is used to connect the charging plug of the electric vehicle, and convert the AC power into a DC power suitable for charging the battery of the electric vehicle, and ensure the safety and efficiency of the charging process. The power module is used to convert the input grid power into a charging voltage and current suitable for the electric vehicle, and filter and stabilize the input grid power. The control system is used to manage the charging process, including current and voltage regulation, fault detection, and communication functions. The communication module is used to exchange data with the electric vehicle and the background management system. The safety protection device is used for overcurrent protection, overvoltage protection, and leakage protection to ensure the safety of the charging process. The heat dissipation system is used to cool the internal components of the target charging pile and keep the target charging pile within a suitable temperature range. Among them, when the voltage regulation circuit fails or components are damaged, the charging module output may cause overvoltage; when the load is too large, the current sensor fails or there is a problem with the internal circuit, the charging module output may cause overcurrent; when the internal components of the charging module are damaged, the charging module may fail; when the AC power input in the power module has power outages, abnormal voltage, or abnormal frequency, it may cause AC input failure; when the AC circuit breaker in the power module is damaged or cannot properly disconnect the circuit, it may cause the AC circuit breaker to fail.

[0063] In a possible embodiment, the first working state is a first fault state, whose fault category is charging module output overvoltage, and the working state label is 1; the second working state is a second fault state, whose fault category is charging module output overcurrent, and the working state label is 2; the third working state is a third fault state, whose fault category is charging module output short circuit, and the working state label is 3; the fourth working state is a fourth fault state, whose fault category is charging module failure, and the working state label is 4; the fifth working state is a fifth fault state, whose fault category is AC input failure, and the working state label is 5; the sixth working state is a sixth fault state, whose fault category is AC circuit breaker failure, and the working state label is 6; the seventh working state is a normal state, and the working state label is 7.

[0064] It can be seen that the accurate analysis and classification of the historical operation data of charging piles will help the subsequent training and testing of the model, and can significantly improve the accuracy and reliability of fault diagnosis.

[0065] Step S302: Acquire all sample data sets corresponding to the multiple working states to obtain a reference data set.

[0066] Among them, the sample data set corresponding to each working state includes M1 pieces of operating data, and the target charging pile has a+1 working states in total, then the reference data set includes M2 pieces of operating data, and M2=(a+1)×M1.

[0067] Step S303: performing a preset data processing operation on the reference data set to obtain a target data set.

[0068] The reference data set includes multiple pieces of operation data; the reference operation data is any one piece of operation data among the multiple pieces of operation data, and the preset data processing operation is performed on the reference data set to obtain the target data set, and the specific steps include:

[0069] A1. Performing empirical mode decomposition on the reference operation data to obtain n modal components, where n is a positive integer;

[0070] A2. Perform validity identification on the n modal components according to a preset correlation coefficient method to obtain N valid modal components; n is greater than or equal to N;

[0071] A3, performing Hilbert transform on each of the N effective modal components to obtain N target modal components;

[0072] A4. Calculate a feature data set of each of the N target modal components to obtain N feature data sets;

[0073] A5. Determine a joint spectrum expression corresponding to the reference running data according to the N feature data sets to obtain a joint spectrum expression; the joint spectrum expression is used to represent how the amplitude of the data changes over time and frequency;

[0074] A6. Integrate the joint spectrum expression over time to obtain target data corresponding to the reference operating data.

[0075] Wherein, in the step A1, performing empirical mode decomposition on the reference operation data to obtain n modal components specifically includes:

[0076] Performing empirical mode decomposition on the reference operating data according to a preset mode decomposition formula to obtain the n mode components;

[0077] The preset modal decomposition formula is as follows:

[0078]

[0079] in, represents the reference running data; k is a positive integer less than or equal to 7, used to represent the data type label corresponding to the reference running data; t represents the time points corresponding to the n modal components respectively; represents the i-th modal component among the n modal components.

[0080] It should be noted that the operating data includes the charging module input voltage, the charging module input current, the charging module output voltage, the charging module output current, the charging module output power, the target demand voltage, and the target demand current. Each data type corresponds to a data type label k. For example, the charging module input voltage corresponds to k=1, and the charging module input current corresponds to k=2. Each modal component contains the components of its operating data in different frequency bands, and the center frequencies of the modal components are different and will change with the changes in the operating data. Among them, the frequency spectrum of each modal component can be obtained by performing a Fourier transform on each modal component. The position with the largest amplitude of the operating data in the frequency spectrum is obtained, and the frequency corresponding to the position is determined as the center frequency. The center frequency can be used for subsequent data analysis or processing.

[0081] Wherein, in the step A2, the validity identification of the n modal components is performed according to a preset correlation coefficient method to obtain N valid modal components, which specifically includes:

[0082] Calculate the correlation coefficient between each of the n modal components and the reference operating data according to a preset correlation coefficient calculation formula to obtain n correlation coefficients;

[0083] The preset correlation coefficient calculation formula is as follows:

[0084]

[0085] in, represents the correlation coefficient between the i-th modal component and the reference operating data; T is the duration of the time period corresponding to the reference operating data;

[0086] Determine a correlation coefficient among the n correlation coefficients that is greater than or equal to a preset correlation coefficient threshold, and obtain N target correlation coefficients;

[0087] Determine the effective modal components corresponding to the N target correlation coefficients among the n modal components to obtain the N effective modal components; each target correlation coefficient corresponds to one effective modal component.

[0088] It should be noted that the correlation coefficient threshold can be preset based on the maximum value in the correlation coefficient sequence. The specific formula is as follows:

[0089]

[0090] in, is the correlation coefficient threshold, is the correlation coefficient sequence, and .

[0091] It can be seen that in fault detection, by calculating the correlation coefficient between the modal components of the charging pile and the operating data, the most relevant features, namely the effective modal components, can be screened out, which helps to reduce interference data and improve the accuracy of fault detection.

[0092] Wherein, in the step A3, Hilbert transform is performed on each of the N effective modal components to obtain N target modal components, which specifically includes:

[0093] Performing a Hilbert transform on each of the N effective modal components according to a preset Hilbert transform formula to obtain the N target modal components;

[0094] The preset Hilbert transform formula is as follows:

[0095]

[0096] in, represents the i-th target modal component; Express Perform a Hilbert transform.

[0097] Wherein, in the step A4, calculating the feature data set of each target modal component in the N target modal components to obtain N feature data sets specifically includes:

[0098] The i-th target modal component is calculated according to a preset characteristic calculation formula to obtain a characteristic data set corresponding to the i-th target modal component; the target modal component corresponds to the characteristic data set one by one; the i-th target modal component is any one of the N target modal components;

[0099] The preset feature calculation formula is as follows:

[0100]

[0101]

[0102]

[0103]

[0104] in, represents the instantaneous amplitude of the i-th target modal component; represents the instantaneous phase of the i-th target modal component; represents the instantaneous angular frequency of the i-th target modal component; represents the frequency of the i-th target modal component.

[0105] Wherein, in the step A5, determining the joint spectrum expression corresponding to the reference operating data according to the N feature data sets to obtain the joint spectrum expression specifically includes:

[0106] The joint spectrum expression corresponding to the reference running data is constructed based on N feature data sets, and the feature data sets include , , , . The joint spectrum expression is:

[0107]

[0108] in, To get the real part, It is a joint spectrum expression, which refers to a complete time-frequency-energy joint spectrum. It can be seen that the expression of the reference operating data is the corresponding joint spectrum expression. By analyzing the joint spectrum expression, we can not only obtain the frequency changes corresponding to different time periods, but also obtain the changes in the amplitude of the operating data over time and frequency.

[0109] Wherein, in the step A6, integrating the joint spectrum expression over time to obtain the target data corresponding to the reference operation data specifically includes:

[0110] The joint spectrum expression is integrated in time according to a preset time integration formula to obtain the target data corresponding to the reference operation data. The preset time integration formula is as follows:

[0111]

[0112] in, is the target data corresponding to the reference operating data, that is, the target marginal spectrum corresponding to the reference operating data. The target marginal spectrum can accurately describe the variation law of the amplitude of the operating data with time and frequency, and can reflect the amplitude distribution of the operating data at each instantaneous frequency point. It should be noted that the target marginal spectrum can be the HHT marginal spectrum, which is not specifically limited here.

[0113] It can be seen that by analyzing the marginal spectrum of the operating data, the frequency and amplitude characteristics corresponding to different fault types can be more clearly determined, thereby improving the accuracy of working status identification and fault diagnosis of the charging pile.

[0114] Step S304, dividing the target data set according to a preset ratio to obtain a training set and a test set.

[0115] Specifically, the preset ratio may be 8:2, that is, 80% of the data in the target data set is divided into a training set, and 20% of the data is divided into a test set, which is not specifically limited here.

[0116] Step S305, building a model according to the training set and performing training to obtain a target model.

[0117] The target model is used to identify the working status of the target charging pile.

[0118] In a possible embodiment, a reference model is built based on the data of the training set. The reference model is a 1D-CNN model, and its structure is as follows:

[0119]

[0120] Among them, None is a null value and has no actual meaning. The input layer is used to receive one-dimensional sequence data as the input of the model; the convolution layer is used to perform convolution operations, that is, use a series of trainable convolution kernels to slide on the input data and extract features. The convolution operation can effectively extract local information, thereby capturing the local pattern of the input sequence, that is, the convolution layer performs convolution operations on the input data by sliding a fixed-size window, extracting features within the window, and then mapping these features to the next layer; the pooling layer is used to reduce the dimension of the convolution layer output, reduce the amount of calculation, and improve the robustness and generalization ability of the model; the Dropout layer is a random inactivation layer; the fully connected layer is used to map the output of the pooling layer to the output of the model, usually for classification tasks.

[0121] Furthermore, when the reference model is trained, the algorithm of the corresponding 1D-CNN model optimizer can be set to the Adam algorithm, the learning rate is set to 0.0002, and the number of iterations is set to 50 times, which are not specifically limited here. After the reference model is trained according to the data of the training set, the target model is obtained.

[0122] If the sampling frequency D=800, each piece of operating data corresponds to 800 data points. For example, the operating data corresponding to the output current of the charging module is , the length is T, and after sampling it according to the sampling frequency D, It becomes a data sequence including 800 data points. It can be seen that if a=6, then a+1=7, that is, the output result of the target model includes 7 types of working states.

[0123] It can be seen that the target model can identify complex signal patterns and features through multi-layer convolution and pooling operations. At the same time, the target model is highly robust to noise and interference, and can effectively extract useful information even when there is noise or interference in the signal, thereby improving the accuracy and reliability of fault detection. In addition, the target model is adaptable to different types of input data, including voltage, current, power, etc., enabling it to process various signal types of charging piles and provide comprehensive fault detection capabilities.

[0124] Step S306, testing the target model according to the test set to obtain a test result, and determining a target model performance indicator corresponding to the test result.

[0125] The test result includes a first quantity Ax, a second quantity Bx, and a third quantity Cx; the first quantity Ax is the quantity of the predicted working state label x output by the target model and the actual working state label x; the second quantity Bx is the quantity of the predicted working state label x output by the target model and the actual working state label y; the third quantity Cx is the quantity of the predicted working state label y output by the target model and the actual working state label x; the determination of the target model performance index corresponding to the test result specifically includes:

[0126] Calculate the first quantity Ax, the second quantity Bx, and the third quantity Cx according to a preset reference model performance calculation formula to obtain a reference model performance indicator Dx;

[0127] The preset reference model performance calculation formula is as follows:

[0128]

[0129] Calculate the reference model performance index Dx according to a preset averaging calculation formula to obtain the target model performance index;

[0130] The preset average calculation formula is as follows:

[0131]

[0132] Among them, ACC represents the target model performance index; a+1 represents the number of types of working status labels corresponding to the test results.

[0133] It should be noted that after the test set data is input into the target model, the target model outputs the test results. The test results are shown in the following table:

[0134]

[0135] Among them, the first number Ax is the number of predicted working state labels output by the target model as x and the actual working state labels as x; the second number Bx is the number of predicted working state labels output by the target model as x but the actual working state labels as y; the third number Cx is the number of predicted working state labels output by the target model as y but the actual working state labels as x. Both x and y are positive integers less than or equal to 7, and x is not equal to y. The reference model performance index Dx can be calculated based on the first number Ax, the second number Bx, and the third number Cx.

[0136] Step S307: If the target model performance index meets the preset conditions, the real-time operation data of the target charging pile is input into the target model to obtain a target working status label.

[0137] Specifically, the model performance index threshold can be pre-set to 0.9, which is not specifically limited here. When the target model performance index is greater than or equal to the model performance index threshold, that is, ACC is greater than or equal to 0.9, it is determined that the target model can be put into use. Then, the real-time operation data of the target charging pile is collected. The real-time operation data includes but is not limited to the real-time charging module input voltage, charging module input current, charging module output voltage, charging module output current, charging module output power, target demand voltage, and target demand current. Finally, the real-time operation data is input into the target model, and the target working status label is output. According to the target working status label, it can be determined whether the target charging pile is faulty. If the target charging pile is faulty, its fault category can be further determined. In addition, the output results of the target model can also be uploaded to the monitoring system background of the target charging pile for further analysis and timely processing by the operation and maintenance personnel.

[0138] In a possible embodiment, the target model can be used to identify the working status of multiple charging piles and obtain multiple working status tags. If it is determined that the multiple charging piles are all faulty according to the multiple working status tags, then the relevant information corresponding to the working status tag K is obtained; the working status tag K is any one of the multiple working status tags; the relevant information includes at least one of the following: maintenance records, processing status.

[0139] Determine the target fault frequency corresponding to the working status tag K according to the maintenance record; determine the target severity corresponding to the working status tag K according to the processing situation; obtain an initial first weight and an initial second weight; determine the first adjustment factor corresponding to the target fault frequency according to the mapping relationship between the preset adjustment factor and the fault frequency; adjust the initial first weight according to the first adjustment factor to obtain the target first weight; determine the first priority corresponding to the target fault frequency according to the mapping relationship between the preset priority and the fault frequency; determine the second adjustment factor corresponding to the target severity according to the mapping relationship between the preset adjustment factor and the severity; adjust the initial second weight according to the second adjustment factor to obtain the target second weight; determine the second priority corresponding to the target severity according to the mapping relationship between the preset priority and the severity; calculate the target first weight, the first priority, the target second weight, and the second priority according to the preset priority calculation formula to obtain the target priority; wherein the preset priority calculation formula is: target first weight×first priority+target second weight×second priority=target priority.

[0140] The processing operation of the working status tag K is performed on the multiple working status tags to obtain multiple target priorities; a charging pile priority processing list is determined according to the multiple target priorities; and the multiple charging piles are repaired and managed according to the charging pile priority processing list.

[0141] It can be seen that by calculating the target priority of each charging pile, maintenance and management resources can be allocated more effectively, and the most important and urgent faulty charging piles can be handled first. At the same time, by combining the fault frequency and severity of the charging piles, the impact of the fault can be accurately assessed, and the targeted maintenance and handling can be improved. In addition, by dynamically adjusting the weight and priority, different fault conditions can be responded to in a timely manner, reducing the impact of charging pile faults on the charging business.

[0142] Among them, the target model performance index is compared with the model performance index obtained by random forest and support vector machine algorithms. The comparison results are shown in the following table:

[0143]

[0144] Among them, the random forest algorithm is a commonly used ensemble learning method and a supervised learning algorithm. It is mainly used for classification and regression tasks. It builds multiple decision trees and combines their results for prediction. The support vector machine algorithm is a supervised learning algorithm used for classification and regression tasks. It aims to find the best hyperplane to separate data points of different categories and has good generalization ability. According to the comparison results, the recognition accuracy of the target model obtained based on the marginal spectrum and 1D-CNN method is higher than that of the model obtained by the random forest and support vector machine algorithms.

[0145] It can be seen that by screening effective modal components through correlation coefficients, using HHT marginal spectra for precise signal analysis, applying 1D-CNN for feature extraction, and combining the HHT-1D-CNN method, efficient and accurate charging pile fault detection and type identification can be achieved.

[0146] The above mainly introduces the scheme of the embodiment of the present application from the perspective of the execution process on the method side. It is understandable that, in order to realize the above functions, the electronic device includes a hardware structure and / or software module corresponding to the execution of each function. It should be easily appreciated by those skilled in the art that, in combination with the units and algorithm steps of each example described in the embodiments provided herein, the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present application.

[0147] The embodiment of the present application can divide the electronic device into functional units according to the above method example. For example, each functional unit can be divided according to each function, or two or more functions can be integrated into one processing unit. The above integrated unit can be implemented in the form of hardware or in the form of software functional units. It should be noted that the division of units in the embodiment of the present application is schematic and is only a logical function division. There may be other division methods in actual implementation.

[0148] In the case of dividing each functional module into corresponding functional modules, Figure 4 A functional module composition block diagram of a device for identifying a charging pile fault type provided in an embodiment of the present application, wherein the device 400 for identifying a charging pile fault type includes an acquisition module 410, a processing module 420, a division module 430, a training module 440, a test module 450, and an identification module 460, wherein:

[0149] The acquisition module 410 is used to acquire multiple working states of the target charging pile; the multiple working states include a fault state and a normal state; each fault state in the a fault state corresponds to a fault category; each working state corresponds to a working state label and a sample data set, and each sample data set includes at least one operation data; a is a positive integer;

[0150] The acquisition module 410 is further used to acquire all sample data sets corresponding to the multiple working states to obtain a reference data set;

[0151] The processing module 420 is used to perform a preset data processing operation on the reference data set to obtain a target data set;

[0152] A partitioning module 430 is used to partition the target data set according to a preset ratio to obtain a training set and a test set;

[0153] The training module 440 is used to build a model according to the training set and perform training to obtain a target model; the target model is used to identify the working state of the target charging pile;

[0154] A testing module 450 is used to test the target model according to the test set, obtain a test result, and determine a target model performance indicator corresponding to the test result;

[0155] The identification module 460 is used to input the real-time operation data of the target charging pile into the target model to obtain a target working status label if the target model performance index meets the preset conditions.

[0156] Optionally, the reference data set includes multiple pieces of operation data; the reference operation data is any one piece of operation data among the multiple pieces of operation data; in performing a preset data processing operation on the reference data set to obtain a target data set, the processing module 420 is specifically used to:

[0157] Performing empirical mode decomposition on the reference operating data to obtain n modal components, where n is a positive integer;

[0158] Performing validity identification on the n modal components according to a preset correlation coefficient method to obtain N valid modal components; n is greater than or equal to N;

[0159] Performing a Hilbert transform on each of the N effective modal components to obtain N target modal components;

[0160] Calculating a feature data set of each target modal component in the N target modal components to obtain N feature data sets;

[0161] Determine a joint spectrum expression corresponding to the reference running data according to the N feature data sets to obtain a joint spectrum expression; the joint spectrum expression is used to represent how the amplitude of the data changes over time and frequency;

[0162] The joint spectral expression is integrated over time to obtain target data corresponding to the reference operating data.

[0163] Optionally, in the aspect of performing empirical mode decomposition on the reference operation data to obtain n modal components, the processing module 420 is further specifically configured to:

[0164] Performing empirical mode decomposition on the reference operating data according to a preset mode decomposition formula to obtain the n mode components;

[0165] The preset modal decomposition formula is as follows:

[0166]

[0167] in, represents the reference running data; k is a positive integer less than or equal to 7, used to represent the data type label corresponding to the reference running data; t represents the time points corresponding to the n modal components respectively; represents the i-th modal component among the n modal components.

[0168] Optionally, in the aspect of performing validity identification on the n modal components according to a preset correlation coefficient method to obtain N valid modal components, the processing module 420 is further specifically used for:

[0169] Calculate the correlation coefficient between each of the n modal components and the reference operating data according to a preset correlation coefficient calculation formula to obtain n correlation coefficients;

[0170] The preset correlation coefficient calculation formula is as follows:

[0171]

[0172] in, represents the correlation coefficient between the i-th modal component and the reference operating data; T is the duration of the time period corresponding to the reference operating data;

[0173] Determine a correlation coefficient among the n correlation coefficients that is greater than or equal to a preset correlation coefficient threshold, and obtain N target correlation coefficients;

[0174] Determine the effective modal components corresponding to the N target correlation coefficients among the n modal components to obtain the N effective modal components; each target correlation coefficient corresponds to one effective modal component.

[0175] Optionally, in the aspect of performing Hilbert transform on each of the N effective modal components to obtain N target modal components, the processing module 420 is further specifically configured to:

[0176] Performing a Hilbert transform on each of the N effective modal components according to a preset Hilbert transform formula to obtain the N target modal components;

[0177] The preset Hilbert transform formula is as follows:

[0178]

[0179] in, represents the i-th target modal component; Express Perform a Hilbert transform.

[0180] Optionally, in the aspect of calculating the feature data set of each target modal component in the N target modal components to obtain N feature data sets, the processing module 420 is further specifically used for:

[0181] The i-th target modal component is calculated according to a preset characteristic calculation formula to obtain a characteristic data set corresponding to the i-th target modal component; the target modal component corresponds to the characteristic data set one by one; the i-th target modal component is any one of the N target modal components;

[0182] The preset feature calculation formula is as follows:

[0183]

[0184]

[0185]

[0186]

[0187] in, represents the instantaneous amplitude of the i-th target modal component; represents the instantaneous phase of the i-th target modal component; represents the instantaneous angular frequency of the i-th target modal component; represents the frequency of the i-th target modal component.

[0188] Optionally, the test result includes a first number Ax, a second number Bx, and a third number Cx; the first number Ax is the number of predicted working state labels output by the target model as x and the actual working state labels as x; the second number Bx is the number of predicted working state labels output by the target model as x and the actual working state labels as y; the third number Cx is the number of predicted working state labels output by the target model as y and the actual working state labels as x; in terms of determining the target model performance indicator corresponding to the test result, the test module 450 is specifically used to:

[0189] Calculate the first quantity Ax, the second quantity Bx, and the third quantity Cx according to a preset reference model performance calculation formula to obtain a reference model performance indicator Dx;

[0190] The preset reference model performance calculation formula is as follows:

[0191]

[0192] Calculate the reference model performance index Dx according to a preset averaging calculation formula to obtain the target model performance index;

[0193] The preset average calculation formula is as follows:

[0194]

[0195] Among them, ACC represents the target model performance index; a+1 represents the number of types of working status labels corresponding to the test results.

[0196] It can be seen that by collecting sample data of the charging pile under different working conditions and performing preset data processing operations on the sample data, the data quality and the accuracy of feature extraction can be improved, thereby improving the accuracy of identifying the fault type of the charging pile.

[0197] It should be noted that the specific implementation of each operation can adopt the corresponding description of the method embodiment shown above, and the device 400 for identifying the fault type of the charging pile can be used to execute the above method embodiment of the present application, which will not be described in detail.

[0198] An embodiment of the present application also provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program for electronic data exchange, wherein the computer program enables a computer to execute part or all of the steps of any method recorded in the above method embodiments, and the above computer includes an electronic device.

[0199] The embodiment of the present application also provides a computer program product, the computer program product includes a non-transitory computer-readable storage medium storing a computer program, the computer program is operable to cause a computer to execute some or all of the steps of any method described in the method embodiment. The computer program product may be a software installation package, and the computer includes an electronic device.

[0200] It should be noted that, for the above-mentioned various embodiments, for the sake of simple description, they are all expressed as a series of action combinations. Those skilled in the art should be aware that the present application is not limited by the described order of actions, because some steps in the embodiments of the present application can be performed in other orders or simultaneously. In addition, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions, steps, modules or units involved are not necessarily required by the embodiments of the present application.

[0201] In the above embodiments, the embodiments of the present application have different focuses on the description of each embodiment. For parts that are not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0202] Those skilled in the art can understand that to implement all or part of the processes in the above-mentioned embodiments, the processes can be completed by computer programs to instruct related hardware, and the programs can be stored in computer-readable storage media. When the programs are executed, they can include the processes of the above-mentioned method embodiments. The aforementioned storage media include: ROM or random access memory RAM, magnetic disk or optical disk and other media that can store program codes.

[0203] The steps of the method or algorithm described in the embodiments of the present application can be implemented in hardware or by executing software instructions by a processor. The software instructions can be composed of corresponding software modules, and the software modules can be stored in RAM, flash memory, ROM, EPROM, electrically erasable programmable read-only memory (electrically EPROM, EEPROM), registers, hard disks, mobile hard disks, read-only compact disks (CD-ROMs) or any other form of storage medium known in the art. An exemplary storage medium is coupled to the processor so that the processor can read information from the storage medium and write information to the storage medium. Of course, the storage medium can also be a component of the processor. The processor and the storage medium can be located in an ASIC. In addition, the ASIC can be located in a terminal device or a management device. Of course, the processor and the storage medium can also exist in a terminal device or a management device as discrete components.

[0204] Those skilled in the art should be aware that in one or more of the above examples, the functions described in the embodiments of the present application can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions may be transmitted from a website site, computer, server, or data center to another website site, computer, server, or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium may be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more available media integrated. The available medium may be a magnetic medium (eg, a floppy disk, a hard disk, a magnetic tape), an optical medium (eg, a digital video disc (DVD)), or a semiconductor medium (eg, a solid state disk (SSD)).

[0205] The modules / units included in the devices and products described in the above embodiments may be software modules / units or hardware modules / units, or may be partially software modules / units and partially hardware modules / units. For example, for the devices and products applied to or integrated in the chip, the modules / units included therein may all be implemented in the form of hardware such as circuits, or at least some of the modules / units may be implemented in the form of software programs, which run on the processor integrated inside the chip, and the remaining (if any) modules / units may be implemented in the form of hardware such as circuits; for the devices and products applied to or integrated in the chip module, the modules / units included therein may all be implemented in the form of hardware such as circuits, and different modules / units may be located in the same component (such as chip, circuit module, etc.) or different components of the chip module, or at least some of the modules / units may be implemented in the form of software programs. It is implemented in the form of a software program that runs on a processor integrated inside the chip module, and the remaining (if any) modules / units can be implemented in hardware such as circuits; for various devices and products applied to or integrated in the terminal equipment, the various modules / units contained therein can be implemented in hardware such as circuits, and different modules / units can be located in the same component (for example, chip, circuit module, etc.) or different components in the terminal equipment, or at least some of the modules / units can be implemented in the form of a software program that runs on a processor integrated inside the terminal equipment, and the remaining (if any) modules / units can be implemented in hardware such as circuits.

[0206] The specific implementation methods described above further illustrate the purpose, technical solutions and beneficial effects of the embodiments of the present application. It should be understood that the above description is only the specific implementation method of the embodiments of the present application and is not intended to limit the protection scope of the embodiments of the present application. Any modifications, equivalent substitutions, improvements, etc. made on the basis of the technical solutions of the embodiments of the present application should be included in the protection scope of the embodiments of the present application.

Claims

1. A method for identifying the fault type of a charging pile, characterized in that: include: Acquire multiple working states of the target charging pile; the multiple working states include a fault state and a normal state; Each of the a fault states corresponds to a fault category; each working state corresponds to a working state label and a sample data set, and each sample data set includes at least one operation data; a is a positive integer; Acquire all sample data sets corresponding to the multiple working states to obtain a reference data set; Performing a preset data processing operation on the reference data set to obtain a target data set; Dividing the target data set according to a preset ratio to obtain a training set and a test set; Building a model according to the training set and performing training to obtain a target model; The target model is used to identify the working state of the target charging pile; Testing the target model according to the test set to obtain a test result, and determining a target model performance indicator corresponding to the test result; If the target model performance index meets the preset conditions, the real-time operation data of the target charging pile is input into the target model to obtain a target working status label; The reference data set includes multiple pieces of operation data; the reference operation data is any one piece of operation data among the multiple pieces of operation data; and performing a preset data processing operation on the reference data set to obtain a target data set includes: Performing empirical mode decomposition on the reference operating data to obtain n modal components, where n is a positive integer; Performing validity identification on the n modal components according to a preset correlation coefficient method to obtain N valid modal components; n is greater than or equal to N; Performing a Hilbert transform on each of the N effective modal components to obtain N target modal components; Calculating a feature data set of each target modal component in the N target modal components to obtain N feature data sets; Determine a joint spectrum expression corresponding to the reference running data according to the N feature data sets to obtain a joint spectrum expression; the joint spectrum expression is used to represent how the amplitude of the data changes over time and frequency; Integrating the joint spectrum expression over time to obtain target data corresponding to the reference operating data; The step of performing empirical mode decomposition on the reference operation data to obtain n modal components includes: Performing empirical mode decomposition on the reference operating data according to a preset mode decomposition formula to obtain the n mode components; The preset modal decomposition formula is as follows: in, represents the reference running data; k is a positive integer less than or equal to 7, used to represent the data type label corresponding to the reference running data; t represents the time points corresponding to the n modal components respectively; represents the i-th modal component among the n modal components; The method of performing validity identification on the n modal components according to a preset correlation coefficient method to obtain N valid modal components includes: Calculate the correlation coefficient between each of the n modal components and the reference operating data according to a preset correlation coefficient calculation formula to obtain n correlation coefficients; The preset correlation coefficient calculation formula is as follows: in, represents the correlation coefficient between the i-th modal component and the reference operating data; T is the duration of the time period corresponding to the reference operating data; Determine a correlation coefficient among the n correlation coefficients that is greater than or equal to a preset correlation coefficient threshold, and obtain N target correlation coefficients; Determine the effective modal components corresponding to the N target correlation coefficients among the n modal components to obtain the N effective modal components; each target correlation coefficient corresponds to one effective modal component; Wherein, the test result includes a first quantity Ax, a second quantity Bx, and a third quantity Cx; the first quantity Ax is the quantity of the predicted working state label x output by the target model and the actual working state label x; the second quantity Bx is the quantity of the predicted working state label x output by the target model and the actual working state label y; the third quantity Cx is the quantity of the predicted working state label y output by the target model and the actual working state label x; the determination of the target model performance index corresponding to the test result includes: Calculate the first quantity Ax, the second quantity Bx, and the third quantity Cx according to a preset reference model performance calculation formula to obtain a reference model performance indicator Dx; The preset reference model performance calculation formula is as follows: Calculate the reference model performance index Dx according to a preset averaging calculation formula to obtain the target model performance index; The preset average calculation formula is as follows: Among them, ACC represents the target model performance index; a+1 represents the number of types of working status labels corresponding to the test results.

2. The method according to claim 1, characterized in that The Hilbert transform is performed on each of the N effective modal components to obtain N target modal components, including: Performing a Hilbert transform on each of the N effective modal components according to a preset Hilbert transform formula to obtain the N target modal components; The preset Hilbert transform formula is as follows: in, represents the i-th target modal component; Express Perform a Hilbert transform.

3. The method according to claim 2, characterized in that The calculating the feature data set of each target modal component in the N target modal components to obtain N feature data sets includes: The i-th target modal component is calculated according to a preset characteristic calculation formula to obtain a characteristic data set corresponding to the i-th target modal component; the target modal component corresponds to the characteristic data set one by one; the i-th target modal component is any one of the N target modal components; The preset feature calculation formula is as follows: in, represents the instantaneous amplitude of the i-th target modal component; represents the instantaneous phase of the i-th target modal component; represents the instantaneous angular frequency of the i-th target modal component; represents the frequency of the i-th target modal component.

4. A device for identifying the fault type of a charging pile, used to execute the method for identifying the fault type of a charging pile as claimed in claim 1, characterized in that: The device comprises an acquisition module, a processing module, a division module, a training module, a testing module and an identification module, wherein: The acquisition module is used to acquire multiple working states of the target charging pile; the multiple working states include a fault state and a normal state; each of the a fault states corresponds to a fault category; each working state corresponds to a working state label and a sample data set, and each sample data set includes at least one operation data; a is a positive integer; The acquisition module is further used to acquire all sample data sets corresponding to the multiple working states to obtain a reference data set; The processing module is used to perform a preset data processing operation on the reference data set to obtain a target data set; The partitioning module is used to partition the target data set according to a preset ratio to obtain a training set and a test set; The training module is used to build a model according to the training set and perform training to obtain a target model; the target model is used to identify the working status of the target charging pile; The testing module is used to test the target model according to the test set, obtain the test result, and determine the target model performance index corresponding to the test result; The identification module is used to input the real-time operation data of the target charging pile into the target model to obtain a target working status label if the performance index of the target model meets the preset conditions.

5. An electronic device, characterized in that: include: A processor, a memory, a communication interface, and one or more programs; The one or more programs are stored in the memory and configured to be executed by the processor, the programs comprising instructions for executing the steps in the method according to any one of claims 1 to 3.

6. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, wherein the computer program includes program instructions, and when the program instructions are executed by a processor, the processor is caused to perform the method according to any one of claims 1 to 3.

Images