Charging gun intelligent electric leakage detection method, storage medium and execution equipment

Abstract

The invention discloses an intelligent electric leakage detection method for a charging gun, a storage medium and execution equipment. According to the method, accurate detection of electric leakage of the charging gun is realized by integrating multiple technologies. Firstly, the state of a charging gun is monitored in real time by identifying charging activities in a detection range and calling operation data of a charging pile; and when the charging gun is separated from the charging pile, whether electric leakage occurs is automatically detected. The method comprises the steps of obtaining key data such as current, magnetic field parameters and temperature of the output end of a charging gun in real time, calculating the difference between theoretical output and actual output in combination with charging pile parameter information, and obtaining abnormal parameters and electric leakage factors. In addition, the insulation abnormity rate is analyzed by recording electric signals, the service life of the insulation part is evaluated, a charging monitoring request is generated, and detection comprehensiveness is ensured. Current data are indirectly acquired by using magnetic field parameters, an index set is generated in combination with a tolerance range, feature fusion and matrix conversion are performed, and finally, abnormal parameters are calculated through a performance analysis model, so that intelligent detection and early warning of electric leakage of the charging gun are realized.

Description

Technical Field

[0001] The present invention relates to the technical field of charging guns, and in particular to an intelligent leakage detection method, storage medium and execution device for a charging gun. Background Art

[0002] With the popularity of electric vehicles, the safety and reliability of charging facilities have become a crucial issue. As a connecting bridge between electric vehicles and charging piles, the working status of the charging gun is directly related to the safety and efficiency of the charging process. However, since the charging gun may be affected by various environmental factors during use, such as moisture, corrosion, wear, etc., the risk of leakage in the charging gun increases. Traditional leakage detection methods often rely on manual inspections or simple electrical tests, which are not only inefficient, but also difficult to detect leakage in real time and accurately. Therefore, an efficient and accurate charging gun leakage detection method is urgently needed to ensure the safety and reliability of the charging process.

[0003] The existing charging gun leakage detection technology has many shortcomings, such as low detection accuracy, poor real-time performance, and inability to fully monitor the working status of the charging gun. These problems not only affect the normal operation of charging facilities, but may also cause safety hazards to electric vehicle users. For example, leakage may cause serious accidents such as electric shock and fire, posing a threat to people's lives and property. Therefore, the development of a charging gun leakage detection method is of great significance to improving the safety and reliability of charging facilities. Summary of the invention

[0004] 1. Technical issues to be resolved To solve the above problems, the present invention proposes a charging gun intelligent leakage detection method, storage medium and execution device, aiming to solve the problem in the prior art that the leakage current detection accuracy is low and the charging gun is still in a non-working state after abnormal recovery.

[0005] (II) Technical solution The present invention provides a charging gun intelligent leakage detection method, the leakage detection method comprising: The charging within the range of the identification detection device is identified, and the operation data, charging pile parameter information and operation status information of each charging pile are retrieved. When the charging gun is separated from the charging pile, a first control signal is sent to the detection device to determine whether the charging gun is leaking electricity at this time; Obtain the current value and magnetic field parameters of the output end of the charging gun in real time to obtain the leakage factor; Obtain the output current value, voltage value and temperature value of the charging gun at the current time point in real time, calculate the theoretical output current and theoretical output power of the charging gun by analyzing the charging pile parameter information, compare the theoretical output current and theoretical output power with the actual output current and output power, and obtain abnormal parameters; Determine whether the charging gun is leaking electricity based on the abnormal parameters and the leakage factor, and send a second control signal to the detection device; Detect the status relationship between the charging gun and the charging pile. When the charging gun is hung on the charging pile, check the leakage status of the charging gun based on the temperature parameters and detection cycle of the charging gun.

[0006] In the present invention, a discreteness analysis is performed based on abnormal parameters and leakage factors to obtain an offset error. If the offset error is greater than a preset value, the risk of leakage of the charging gun is high. If the offset error is less than or equal to the preset value, the risk of leakage of the charging gun is small.

[0007] In the present invention, the detection device is connected to the cloud database, and the operation data of the charging pile includes the real-time output current value, input voltage value, charging status, etc. of the charging pile, and these data are stored in the cloud for statistics and interaction.

[0008] In the present invention, the electrical signals in one or more cycles are recorded to obtain an abnormal feature set, an insulation abnormality rate is generated according to the abnormal feature set, the service life of the insulating component is evaluated, and the evaluation content and results are sent to the end user.

[0009] In the present invention, the detection device generates a charging monitoring request for each charging gun based on one or more operating data, wherein the detection device confirms the wired communication path between the gateway of the target charging station and the charging gun, and then the detection device generates a charging monitoring request for each charging gun according to the wired communication path and multiple charging gun operating data.

[0010] In the present invention, the magnetic field parameters include magnetic induction intensity and magnetic field intensity. The magnetic induction intensity and magnetic field intensity at the output end of the charging gun can be collected by a sensor to indirectly obtain the current data and current change law at the output end, thereby obtaining leakage current data.

[0011] In the present invention, the tolerance ranges of current and power are set to ΔI and ΔP. , Generate an index set based on two change values; The detection device performs feature fusion on the current tolerance range ΔI and the power tolerance range ΔP according to the comprehensive correlation coefficient to obtain a target feature index set.

[0012] In the present invention, the detection device performs matrix conversion on the target feature index set to generate a target feature matrix, inputs the target feature matrix into a preset charging gun performance analysis model, calculates the performance index of the target feature matrix through the charging gun performance analysis model, and obtains abnormal parameters.

[0013] Another computer-readable storage medium of the present invention stores a computer program, which, when executed by a processor, implements the steps of the charging gun intelligent leakage detection method described in the above technical solution.

[0014] Another execution device of the present invention includes an execution device body and a controller, wherein the controller includes a processor and a computer program stored in a memory and executable on the processor, and when the processor executes the program, the steps of the intelligent leakage detection method for a charging gun described in the above technical solution are implemented.

[0015] (III) Beneficial effects Compared with the prior art, the present invention has the following beneficial effects: The present invention obtains various data such as the current value, magnetic field parameters and temperature value at the output end of the charging gun in real time, combines the operating data and parameter information of the charging pile, and performs comprehensive analysis and processing. It can accurately determine whether the charging gun has leakage, thereby greatly improving the precision and accuracy of detection.

[0016] The present invention adopts advanced sensor technology and data processing algorithms, which can collect and process the working data of the charging gun in real time, promptly discover and report leakage, and provide strong support for timely handling of safety hazards.

[0017] The present invention not only detects the leakage of the charging gun, but also comprehensively evaluates the working status of the charging gun by monitoring the temperature parameters, output current and power of the charging gun, thereby providing rich data support for the maintenance and management of the charging facilities. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0019] Figure 1 It is a logic diagram of the intelligent leakage detection method of the charging gun; Figure 2 This is a schematic diagram of the abnormal parameter analysis process; Figure 3 Schematic diagram of the framework structure of the execution equipment.

[0020] 60. Processor, 61. Memory, 62. Communication interface, 63. Communication bus. DETAILED DESCRIPTION

[0021] The technical solution of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0022] Example 1

[0023] Reference Figure 1 A charging gun intelligent leakage detection method is disclosed, which mainly includes the following steps: S100, identify the charging within the range of the identification detection device, retrieve the operation data, charging pile parameter information and charging pile operation status information of each charging pile, and send a first control signal to the detection device when the charging gun is separated from the charging pile to determine whether the charging gun is leaking electricity at this time.

[0024] The detection device can be an independent device or a unit module installed in a charging pile or charging gun. It is mainly used to receive data collected by a collector or sensor in real time, and then retrieve, store, process and transmit the data, such as an embedded system, detection equipment, etc.

[0025] Specifically, the detection device obtains multiple charging gun operation data of the target charging station. When obtaining the charging gun operation data, the detection device first matches the target charging station with an information storage database to determine the information storage database corresponding to the target charging station. Furthermore, the detection device collects operation data through the information storage database to obtain multiple charging gun operation data of the target charging station. Furthermore, the detection device generates a charging monitoring request for each charging gun based on the multiple charging gun operation data, wherein the detection device confirms the wired communication path between the gateway and the charging gun of the target charging station, and then the detection device generates a charging monitoring request for each charging gun based on the wired communication path and the multiple charging gun operation data.

[0026] If the charging pile reports that the removed charging gun is leaking electricity, the user will be notified through a physical alarm and the power supply to the charging gun will be stopped to prevent safety accidents; if the removed charging gun is not leaking electricity, proceed to the next step.

[0027] S200, obtaining the current value of the output end of the charging gun and the magnetic field parameters of the output end in real time to obtain the leakage factor.

[0028] The second control signal is used for the charging pile to stop supplying power to the charging gun that reaches the leakage threshold. In particular, the magnetic field parameter includes magnetic induction intensity and magnetic field intensity. In this embodiment, the current value at the output end of the charging gun and the magnetic field parameter at the output end are collected by using a fluxgate sensor or a similar high-precision sensor.

[0029] The principle of fluxgate sensor to obtain leakage current is mainly based on fluxgate effect and the characteristics of magnetic sensitive materials. When the detected current flows through the conductor, a magnetic field of a certain size and direction will be generated around it. The fluxgate sensor uses the nonlinear relationship between the magnetic induction intensity and the magnetic field intensity of the high permeability magnetic core in the measured magnetic field under the saturation excitation of the alternating magnetic field to measure this magnetic field, thereby indirectly measuring the current.

[0030] The leakage factor is obtained by integrating the current swing amplitude and the magnetic field parameters, and then it is preliminarily determined that the charging gun is in a leakage state. A second control signal is sent to the charging pile through the detection device to disconnect the connection between the charging pile and the abnormal charging gun, that is, to stop supplying power to the charging gun.

[0031] Specifically, the detection device is connected to the cloud database, and the operation data of the charging pile includes the real-time output current value, input voltage value, charging status, etc. of the charging pile, and these data are stored in the cloud for statistics and interaction. Step S200 also includes: S201. Obtain the output current value, voltage value and temperature value of the charging gun at the current time point in real time, calculate the theoretical output current and theoretical output power of the charging gun by analyzing the charging pile parameter information, compare the theoretical output current and theoretical output power with the actual output current and actual output power, and obtain abnormal parameters.

[0032] S202, generating a charging index curve according to the abnormal parameters and the leakage factor, recording the abnormal values ​​in the charging index curve, generating an analysis report according to the distribution ratio of the abnormal values, and transmitting the analysis report to the terminal user.

[0033] Install high-precision current sensors, voltage sensors and temperature sensors on the charging pile to ensure that these sensors can accurately collect the output current value of the charging gun in real time. , voltage value And the temperature value at the current time Theoretical output power , actual output power ,in Obtained through the parameter information of the charging gun. According to the technical specifications and application requirements of the charging pile, set the tolerance range of current and power ΔI and ΔP, , Generates a set of indices based on two changing values.

[0034] Specifically, the detection device counts the correlation coefficients of different indicators and calculates the rank correlation coefficient matrix of the indicator set. Finally, the detection device calculates the comprehensive correlation coefficient between the current tolerance range ΔI and the power tolerance range ΔP according to the rank correlation coefficient matrix. Furthermore, the detection device performs feature fusion on the current tolerance range ΔI and the power tolerance range ΔP according to the comprehensive correlation coefficient to obtain a target feature indicator set. Specifically, the detection device calculates the feature index in sequence, and then determines the corresponding target feature indicator set according to the feature index. Finally, the detection device performs matrix conversion on the target feature indicator set to generate a target feature matrix, and inputs the target feature matrix into a preset charging gun performance analysis model, wherein the charging gun performance analysis model includes: a bidirectional long short-term memory network (BiLSTM), a bidirectional gated recurrent network (BiGRU) and a fully connected network (FCN). The performance index of the target feature matrix is ​​calculated by the charging gun performance analysis model to obtain abnormal parameters.

[0035] Specifically, to detect abnormal parameters in data through a bidirectional long short-term memory network or a bidirectional gated recurrent unit, the following steps can be followed: S201a, pre-processing theoretical output current, theoretical output power, actual output current, and actual output power.

[0036] First, the theoretical output current and the actual output current form the first comparison set, and the theoretical output power and the actual output power form the second comparison set. The missing values ​​in the first comparison set and the second comparison set are removed by cleaning the data. Useful features for anomaly detection are extracted from the first comparison set and the second comparison set. Finally, data of different dimensions are converted into a unified dimension to facilitate model training.

[0037] S201b, select a bidirectional long short-term memory network or a bidirectional gated recurrent unit or a fully connected network to train the first comparison set and the second comparison set and output a first result, analyze the first result through the fully connected network and output abnormal parameters.

[0038] The bidirectional LSTM network is a variant of LSTM that takes into account both past and future information and can better capture contextual relationships in sequence data. The bidirectional LSTM network layer consists of two LSTM networks, one that processes sequence data from front to back and the other from back to front. The outputs of the two LSTM networks are concatenated to form the final bidirectional hidden state.

[0039] The bidirectional gated recurrent network is a bidirectional version of the GRU. Similar to the bidirectional long short-term memory network, it also considers both past and future information. The bidirectional gated recurrent network layer consists of two GRU networks, one that processes the sequence data from front to back and the other from back to front. The outputs of the two GRU networks are also connected together.

[0040] Fully connected networks are usually used to further process and classify the output of the previous network layer. In anomaly detection tasks, a fully connected network can receive the output of BiLSTM or BiGRU, and extract higher-level features through a series of fully connected layers, and finally output anomaly parameters.

[0041] First, the first comparison set and the second comparison set are divided into a training set, a validation set, and a test set. According to the task requirements, a suitable loss function and optimizer are selected to optimize the data. In particular, in this embodiment, the loss function can adopt the cross entropy loss, and the optimizer adopts the Adam optimizer. The specific processing process is the prior art and will not be described in detail here. The model is trained using the training set data, and the performance of the model is monitored by the validation set. During the training process, an early stopping strategy can be used to prevent overfitting. The test set data is input into the trained model to obtain the probability or score of the abnormal parameter. A threshold is set according to actual needs, and samples whose probability or score exceeds the threshold are marked as abnormal parameters.

[0042] Based on the abnormal parameters and the leakage factor, the detection device uses a preset curve fitting function to establish a charging index curve for each charging gun, records the abnormal values ​​in the charging index curve, and constructs a target average curve based on the charging index curve of each charging gun. Furthermore, the detection device performs an offset error analysis on the charging index curve of each charging gun and the target average curve to obtain the offset error of each charging gun.

[0043] It should be noted that when the detection device performs offset error analysis on the charging index curve and the target average curve, it performs discrete analysis on the abnormal parameters and leakage factors, and uses the median absolute deviation algorithm or the local outlier factor algorithm to eliminate significant outliers in the charging index curve. The offset error of each charging gun is obtained through the discrete analysis results, and the offset error of each charging gun is compared with the preset target value. If the offset error is greater than or equal to the preset target value, the leakage risk monitoring result of the charging gun is determined to be that there is a leakage risk. If the offset error is less than the preset target value, the leakage risk monitoring result of the charging gun is determined to be that there is no leakage risk.

[0044] The analysis of the leakage factor and the abnormal parameters is performed simultaneously, and only when the offset error reflected by the two is greater than a preset value, a second control signal is sent to the detection device to block the charging pile from supplying power to the charging gun.

[0045] S300, detecting the status relationship between the charging gun and the charging pile, and checking the leakage status of the charging gun based on the temperature parameters and detection cycle of the charging gun when the charging gun is hung on the charging pile.

[0046] The state relationship between the charging gun and the charging pile is obtained through the interrelated position sensors or contact sensors to determine whether the charging gun is located on the charging pile. When the charging gun is on the charging pile and the temperature of the output end of the charging gun is lower than the preset temperature, the self-test mechanism is activated. The preset detection cycle can be 30 minutes for self-test once or more. In this embodiment, the preset temperature is 30°C, that is, when the temperature of the output end of the charging gun is lower than 30°C, partial discharge is performed to the insulating part of the charging gun every 30 minutes, and the electrical signal transmitted on the insulating part is collected.

[0047] The electrical signals in one or more cycles are recorded to obtain an abnormal feature set, and the insulation abnormality rate is generated according to the abnormal feature set to evaluate the service life of the insulating parts.

[0048] Specifically, the frequency of abnormal discharge is obtained based on the abnormal feature set and the defined cycle, and the abnormal frequency threshold is preset. When the frequency of abnormal discharge is greater than the abnormal frequency threshold, the charging pile and the charging gun are kept disconnected, and further self-checking is performed in the next cycle. When the frequency of abnormal discharge is less than the abnormal frequency threshold, it means that the degree of aging of the insulating parts is moderate, and the insulating parts can be replaced in time to ensure the reliability of the charging gun.

[0049] Example 2

[0050] An embodiment of the present invention provides a computer-readable storage medium.

[0051] The computer-readable storage medium provided in the embodiment of the present invention stores a computer program, and when the computer program is executed by a processor, the steps of any one of the above-mentioned intelligent leakage detection methods for charging guns can be implemented.

[0052] The computer-readable storage medium may include: a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and other media that can store program codes.

[0053] For an introduction to the computer-readable storage medium provided in an embodiment of the present invention, please refer to the above method embodiment, and the present invention will not elaborate on it here.

[0054] The various embodiments in the specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referred to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part description.

[0055] Professionals may further appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in the above description according to function. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians may 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 invention.

[0056] The steps of the method or algorithm described in conjunction with the embodiments disclosed herein may be implemented directly using hardware, a software module executed by a processor, or a combination of the two. The software module may be placed in a random access memory (RAM), a memory, a read-only memory (ROM), an electrically programmable ROM, an electrically erasable programmable ROM, a register, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.

[0057] Example 3

[0058] An embodiment of the present invention provides an execution device.

[0059] Please refer to Figure 3 , Figure 3 This is a schematic diagram of the structure of an execution device provided by the present invention, and the execution device may include: Memory for storing computer programs; The processor can implement the steps of any of the above-mentioned charging gun intelligent leakage detection methods when executing a computer program.

[0060] like Figure 3 As shown, it is a schematic diagram of the composition structure of the execution device, and the execution device may include: a processor 60, a memory 61, a communication interface 62 and a communication bus 63. The processor 60, the memory 61, and the communication interface 62 all communicate with each other through the communication bus 63.

[0061] In the embodiment of the present invention, the processor 60 may be a central processing unit (CPU), an application specific integrated circuit, a digital signal processor, a field programmable gate array or other programmable logic devices.

[0062] The processor 60 may call a program stored in the memory 61 . Specifically, the processor 60 may execute the operations in the embodiment of the push button switch fault detection method.

[0063] The memory 61 is used to store one or more programs, which may include program codes, and the program codes include computer operation instructions. In the embodiment of the present invention, the memory 61 at least stores programs for implementing the following functions: The charging within the range of the identification detection device is identified, and the operation data, charging pile parameter information and operation status information of each charging pile are retrieved. When the charging gun is separated from the charging pile, a first control signal is sent to the detection device to determine whether the charging gun is leaking electricity at this time; Obtain the current value and magnetic field parameters of the output end of the charging gun in real time to obtain the leakage factor; Obtain the output current value, voltage value and temperature value of the charging gun at the current time point in real time, calculate the theoretical output current and theoretical output power of the charging gun by analyzing the charging pile parameter information, compare the theoretical output current and theoretical output power with the actual output current and output power, and obtain abnormal parameters; Determine whether the charging gun is leaking electricity based on the abnormal parameters and the leakage factor, and send a second control signal to the detection device; Detect the status relationship between the charging gun and the charging pile. When the charging gun is hung on the charging pile, check the leakage status of the charging gun based on the temperature parameters and detection cycle of the charging gun.

[0064] In a possible implementation, the memory 61 may include a program storage area and a data storage area, wherein the program storage area may store an operating system and an application required for at least one function, etc.; the data storage area may store data created during use.

[0065] In addition, the memory 61 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device or other volatile solid-state storage device.

[0066] The communication interface 62 may be an interface of a communication module, and is used to connect to other devices or systems.

[0067] Of course, it should be noted that Figure 3 The structure shown does not constitute a limitation on the execution device in the embodiment of the present invention. In actual applications, the execution device may include Figure 3 More or fewer components than shown, or combinations of certain components.

[0068] Finally, the evaluation results and evaluation content are sent to the end user and the cloud for data storage.

[0069] The above-described embodiments are merely descriptions of preferred implementations of the present invention, and are not intended to limit the concept and scope of the present invention. Without departing from the design concept of the present invention, various modifications and improvements made by ordinary persons in the art to the technical solution of the present invention should fall within the protection scope of the present invention, and the technical contents for which protection is sought in the present invention have been fully recorded in the claims.

Claims

1. A charging gun intelligent leakage detection method, characterized in that: The leakage detection method comprises: The charging within the range of the identification detection device is identified, and the operation data, charging pile parameter information and operation status information of each charging pile are retrieved. When the charging gun is separated from the charging pile, a first control signal is sent to the detection device to determine whether the charging gun is leaking electricity at this time; Obtain the current value and magnetic field parameters of the output end of the charging gun in real time to obtain the leakage factor; Obtain the output current value, voltage value and temperature value of the charging gun at the current time point in real time, calculate the theoretical output current and theoretical output power of the charging gun by analyzing the charging pile parameter information, compare the theoretical output current and theoretical output power with the actual output current and output power, and obtain abnormal parameters; Determine whether the charging gun is leaking electricity based on the abnormal parameters and the leakage factor, and send a second control signal to the detection device; Detect the status relationship between the charging gun and the charging pile. When the charging gun is hung on the charging pile, check the leakage status of the charging gun based on the temperature parameters and detection cycle of the charging gun.

2. The intelligent leakage detection method for a charging gun according to claim 1, characterized in that: Based on the discreteness analysis of abnormal parameters and leakage factors, the offset error is obtained. If the offset error is greater than the preset value, the risk of leakage of the charging gun is high. If the offset error is less than or equal to the preset value, the risk of leakage of the charging gun is small.

3. The intelligent leakage detection method for a charging gun according to claim 2, characterized in that: The detection device is connected to the cloud database. The operating data of the charging pile includes the real-time output current value, input voltage value, and charging status of the charging pile. These data are stored in the cloud for statistics and interaction.

4. The intelligent leakage detection method for a charging gun according to claim 3 is characterized in that: The electrical signals in one or more cycles are recorded to obtain an abnormal feature set, an insulation abnormality rate is generated based on the abnormal feature set, the service life of the insulating parts is evaluated, and the evaluation content and results are sent to the end user.

5. The intelligent leakage detection method for a charging gun according to claim 1 or 4, characterized in that: The detection device generates a charging monitoring request for each charging gun based on one or more operating data, wherein the detection device confirms the wired communication path between the gateway of the target charging station and the charging gun, and then the detection device generates a charging monitoring request for each charging gun according to the wired communication path and multiple charging gun operating data.

6. The intelligent leakage detection method for a charging gun according to claim 5, characterized in that: The magnetic field parameters include magnetic induction intensity and magnetic field intensity. The sensor can be used to collect the magnetic induction intensity and magnetic field intensity at the output end of the charging gun to indirectly obtain the current data and current change law at the output end, and obtain the leakage current data.

7. The intelligent leakage detection method for a charging gun according to claim 6, characterized in that: Set the tolerance range of current and power ΔI and ΔP, , Generate an index set based on two change values; The detection device performs feature fusion on the current tolerance range ΔI and the power tolerance range ΔP according to the comprehensive correlation coefficient to obtain a target feature index set.

8. The intelligent leakage detection method for a charging gun according to claim 7, characterized in that: The detection device performs matrix conversion on the target feature index set to generate a target feature matrix, inputs the target feature matrix into a preset charging gun performance analysis model, calculates the performance index of the target feature matrix through the charging gun performance analysis model, and obtains abnormal parameters.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps of the charging gun intelligent leakage detection method according to any one of claims 1 to 8 are implemented.

10. An execution device, comprising an execution device body and a controller, characterized in that: The controller includes a processor and a computer program stored in a memory and executable on the processor. When the processor executes the program, the steps of the intelligent leakage detection method for a charging gun according to any one of claims 1 to 8 are implemented.

Images