A charging pile communication self-repair control system and self-repair method

Abstract

The present invention relates to the technical field of charging pile communication control systems, and more specifically, to a charging pile communication self-repairing control system and self-repairing method. The charging pile communication self-repairing control system described in the present invention is based on a deep learning model of CNN and LSTM, which can simultaneously capture local features (such as abnormal data packet formats) and timing dependencies (such as periodic interference) of communication data. The diagnostic accuracy is improved by 30% to 50% compared with traditional methods, significantly reducing misjudgments and missed judgments. Secondly, through the fault self-repair strategy module, the system can automatically reload the configuration for software protocol errors and adjust communication parameters for electromagnetic interference, shortening the average repair time from 4 hours to within 30 minutes, significantly reducing the need for manual intervention. Secondly, the deep learning model supports online updates and can learn normal and abnormal modes under new communication protocols, ensuring that the system maintains high stability during protocol iterations or environmental changes.

Description

Technical Field

[0001] The present invention relates to the technical field of charging pile communication control systems, and in particular to a charging pile communication self-repairing control system and a self-repairing method. Background Art

[0002] During electric vehicle charging, the stability of vehicle-to-pile communication directly impacts charging efficiency and user experience. Existing charging pile-to-pile communication systems commonly suffer from the following issues: First, fault detection relies on simple communication status judgments (such as timeout retries), making it difficult to accurately identify the fault type (such as a short circuit, protocol conflict, or electromagnetic interference). Second, fault repair relies heavily on manual troubleshooting, requiring maintenance personnel to individually check hardware connections and protocol configurations, taking an average of four hours. This results in prolonged charging pile downtime and high operational and maintenance costs. Furthermore, traditional systems lack adaptability and are unable to adapt to diverse communication protocol updates, leading to frequent compatibility issues with new protocols. As vehicle-to-pile communication protocols diversify, the limitations of existing systems become increasingly prominent. Summary of the Invention

[0003] The purpose of the present invention is to provide a charging pile communication self-repairing control system and self-repairing method to improve the problem that the above-mentioned traditional system lacks adaptive ability and cannot adapt to the update of diversified communication protocols, resulting in frequent compatibility issues with new protocols.

[0004] In order to achieve the above objectives, the embodiments of the present application provide the following technical solutions:

[0005] On the one hand, an embodiment of the present application provides a charging pile communication self-repair control system, the system including: a data acquisition module, for collecting communication data in real time through sensors deployed at the communication interface between the charging pile and the electric vehicle, the communication data including communication status, data transmission rate, number of error data packets and communication protocol interaction information, and cleaning and normalizing the communication data; a fault diagnosis module, composed of a fusion of a convolutional neural network and a long short-term memory network, the convolutional neural network is used to extract local features of the preprocessed communication data, the long short-term memory network is used to analyze time series dependencies and output a fault type diagnosis result; a fault self-repair module, which performs repair operations according to the fault type diagnosis result: if it is a software communication fault, the communication protocol stack is automatically reloaded or the protocol parameter configuration is adjusted; if it is a hardware communication fault, an early warning is triggered and switched to a backup communication line; if it is an electromagnetic interference fault, the communication line is adjusted or anti-interference measures are enhanced.

[0006] Optionally, the convolutional neural network in the fault diagnosis model includes three convolutional layers and three pooling layers for extracting local features of different scales, and the long short-term memory network includes a two-layer network for capturing long-term temporal dependencies;

[0007] The fault self-repair module automatically compares the current communication protocol with the preset protocol library for protocol conflict faults, and dynamically updates the protocol configuration parameters.

[0008] Optionally, it also includes a communication coordination module for coordinating the operation processes of the data acquisition and preprocessing module, the deep learning fault diagnosis model and the fault self-repair strategy module, and communicating with the charging control module and the management platform of the charging pile, uploading fault information and receiving remote instructions in real time, and when the communication is unstable, sending instructions to the charging control module to reduce the charging power until the communication is restored to stability.

[0009] In a second aspect, this embodiment provides a self-repair method based on a charging pile communication self-repair control system, the method comprising:

[0010] In response to the user's order instruction, the data acquisition module sends a communication request to the BMS of the current new energy vehicle, so that the BMS can feedback the vehicle information of the current new energy vehicle, including the vehicle model and vehicle battery information;

[0011] The data acquisition module sends the vehicle information to the fault diagnosis module, so that the fault diagnosis module detects whether there is a charging power curve consistent with the vehicle model in the charging power preset operation library. If not, it is determined that a communication abnormality has occurred with the BMS, and a communication abnormality instruction indicating that the vehicle model cannot be matched is generated. The communication abnormality instruction is sent to the fault self-repair module, so that the fault diagnosis model retrieves the vehicle battery information and generates a charging power curve that matches the vehicle model based on the vehicle battery information; and a new communication protocol is established with the BMS based on the charging power curve, so that the charging pile charges the new energy vehicle according to the charging power curve.

[0012] Optionally, generating a charging power curve that matches the vehicle model based on vehicle battery information includes:

[0013] Parse the vehicle battery information to obtain cell voltage, cell temperature, and battery type. Based on the voltage difference between the cell voltage and the standard voltage, construct a pressure difference distribution map corresponding to the battery module. Determine the thermal resistance coefficient of the cell based on the battery type. The thermal resistance coefficient is provided by the battery supplier of the new energy vehicle and burned into the vehicle battery information.

[0014] Sort multiple cell voltages based on voltage values, and then construct a voltage amplitude curve. Select multiple basic voltage cells based on a preset fluctuation slope, with the starting point of the fluctuation slope coinciding with the starting point of the voltage amplitude curve. Starting from the starting point of the voltage amplitude curve, select multiple consecutive cell voltages whose voltage values are below the set fluctuation slope, and mark the selected cell voltages as basic voltage cells.

[0015] Calculating a first mean voltage of a plurality of basic voltage monomers, constructing a plurality of voltage threshold ranges based on a difference between the first mean voltage and a standard voltage, and constructing a monomer distribution population corresponding to each voltage threshold range in a voltage difference distribution diagram based on the plurality of voltage threshold ranges;

[0016] A distance-based clustering algorithm constructs a core cluster in each monomer distribution population. The core clusters corresponding to multiple monomer distribution populations do not overlap with each other. The second mean voltage corresponding to each core cluster is calculated. Based on the difference between the second mean voltage and the standard voltage, the number of monomers in the core cluster, and the shape of the monomer distribution in the core cluster, a time-heat accumulation diagram of the core cluster during the charging process is constructed.

[0017] A temperature cloud map is constructed based on the cell temperature, and the time-heat accumulation map is superimposed on the temperature cloud map to obtain a first battery heat change cloud map of the battery module during the charging process. The dynamic heat dissipation distribution map of the first battery heat change cloud map is calculated based on the current ambient temperature and battery type. The second battery heat change cloud map of the battery module during the charging process is obtained by superimposing the first battery heat change cloud map and the corresponding dynamic heat dissipation distribution map. The corresponding charging power curve is formulated based on the second battery heat change cloud map, and the vehicle model, charging power curve, pressure difference distribution map and ambient temperature are entered into the big data storage server as training data for the neural network model used for subsequent charging power matching.

[0018] Optionally, calculating a dynamic heat dissipation distribution map of the first battery heat change cloud map based on the current ambient temperature and battery type includes:

[0019] Constructing an ambient temperature field based on the current ambient temperature, and performing normalization processing on the first battery heat change cloud map and the ambient temperature field in sequence;

[0020] Two layers of 3D convolutional layers are used to extract the spatiotemporal local features of the normalized first battery heat change cloud map. The multi-head self-attention mechanism is used to capture the global dependencies in the time dimension and generate time-series enhanced features.

[0021] The normalized ambient temperature field is bilinearly interpolated to a resolution corresponding to the first battery heat change cloud map, and channel-joined with the time series enhancement feature to form a fusion feature;

[0022] The fusion features are input into a preset physical constraint model, and then a corresponding dynamic heat dissipation distribution map is generated according to the time sequence.

[0023] The physical constraint model constructs the heat dissipation of the local area in the following way:

[0024] Extract the ambient temperature channel from the fusion feature and generate a temperature sensitivity coefficient matrix. Multiply the temperature sensitivity coefficient matrix by the convolution kernel weight element by element to obtain the initial heat dissipation.

[0025] The battery temperature is extracted from the fusion features, and the directional consistency threshold is adjusted based on the temperature difference between the battery temperature and the ambient temperature. The gradient-corrected heat dissipation is calculated through the loss function based on the directional consistency threshold. Then, multiple heat dissipation distribution maps are constructed frame by frame based on the gradient-corrected heat dissipation to form a dynamic heat dissipation distribution map.

[0026] Optionally, formulating a corresponding charging power curve based on the second battery heat change cloud map includes:

[0027] A first safety temperature reference surface is constructed based on the preset safety charging temperature threshold, and the preset charging power at a certain moment is reduced based on the volume of the part of the second battery heat change cloud map that protrudes from the first safety temperature reference surface, thereby obtaining a corrected preset charging power. Based on the current voltage consistency fluctuation graph, the entire corrected preset charging power is further reduced to obtain a charging power curve.

[0028] Optionally, the voltage consistency fluctuation graph is constructed as follows:

[0029] The basic voltage is calculated by a weighted algorithm based on the mean voltage and number of monomers corresponding to the monomer distribution population with the lowest voltage threshold range, combined with the mean voltage corresponding to the voltage difference distribution diagram, to obtain the basic voltage, and then construct the basic voltage base;

[0030] The basic voltage base is fitted to the voltage difference distribution diagram, so that the basic voltage base portion is deducted from the voltage difference distribution diagram to obtain a voltage consistency fluctuation diagram, which is used to characterize the voltage fluctuation of multiple cells in the battery module.

[0031] In a third aspect, an embodiment of the present application provides a device for identifying the type of partial discharge of high-voltage electrical equipment, the device comprising a memory and a processor.

[0032] The memory is used to store computer programs; the processor is used to implement the steps of the above-mentioned charging pile communication self-repairing control system when executing the computer program.

[0033] In a fourth aspect, an embodiment of the present application provides a medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of the above-mentioned charging pile communication self-repairing control system are implemented.

[0034] The beneficial effects of the present invention are:

[0035] The charging pile communication self-repair control system described in this invention, based on a deep learning model of CNN and LSTM, can simultaneously capture local features of communication data (such as abnormal data packet formats) and timing dependencies (such as periodic interference). It improves diagnostic accuracy by 30% to 50% compared to traditional methods, significantly reducing misjudgments and missed judgments.

[0036] Secondly, through the fault self-repair strategy module, the system can automatically reload the configuration for software protocol errors and adjust communication parameters for electromagnetic interference, shortening the average repair time from 4 hours to 30 minutes, significantly reducing the need for manual intervention.

[0037] Secondly, the deep learning model supports online updates and can learn normal and abnormal patterns under new communication protocols, ensuring that the system remains highly stable during protocol iterations or environmental changes.

[0038] Other features and advantages of the present invention will be described in the following description, and in part will become apparent from the description, or understood by practicing the embodiments of the present invention. The purposes and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the written description, claims, and drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments. It should be understood that the following drawings only illustrate certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other relevant drawings can be obtained based on these drawings without paying any creative work.

[0040] Figure 1 It is a flowchart of a self-repair method for a charging pile communication failure described in an embodiment of the present invention. DETAILED DESCRIPTION

[0041] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. The components of the embodiments of the present invention generally described and shown in the drawings herein can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present invention provided in the drawings is not intended to limit the scope of the claimed invention, but merely represents selected embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0042] It should be noted that similar reference numerals or letters represent similar items in the following drawings. Therefore, once an item is defined in one drawing, it does not need to be further defined or explained in subsequent drawings. At the same time, in the description of the present invention, the terms "first", "second", etc. are only used to distinguish the description and should not be understood as indicating or implying relative importance.

[0043] Example 1: This embodiment provides a charging pile communication self-repair control system, the system comprising:

[0044] A data acquisition module is used to collect communication data in real time through sensors deployed at the communication interface between the charging pile and the electric vehicle. The communication data includes communication status, data transmission rate, number of error data packets and communication protocol interaction information, and to clean and normalize the communication data;

[0045] The fault diagnosis module is composed of a fusion of a convolutional neural network and a long short-term memory network. The convolutional neural network is used to extract local features of preprocessed communication data, and the long short-term memory network is used to analyze time series dependencies and output fault type diagnosis results. The convolutional neural network in the fault diagnosis model contains three convolutional layers and three pooling layers to extract local features at different scales. The long short-term memory network contains two layers to capture long-term temporal dependencies. Secondly, the fault self-repair module automatically compares the current communication protocol with the preset protocol library for protocol conflict faults and dynamically updates the protocol configuration parameters (for example, in the absence of a complete charging protocol for the corresponding vehicle model, it constructs a corresponding charging power curve based on the specific parameters of the vehicle battery information).

[0046] A fault self-repair module performs repair operations based on the fault type diagnosis results: if it is a software communication fault, it automatically reloads the communication protocol stack or adjusts the protocol parameter configuration; if it is a hardware communication fault, it triggers an early warning and switches to a backup communication line; if it is an electromagnetic interference fault, it adjusts the communication line or enhances anti-interference measures;

[0047] The communication coordination module is used to coordinate the operation processes of the data acquisition and preprocessing module, the deep learning fault diagnosis model and the fault self-repair strategy module, and communicate with the charging control module and management platform of the charging pile to upload fault information and receive remote commands in real time. When the communication is unstable, it sends instructions to the charging control module to reduce the charging power until the communication is restored to stability.

[0048] The charging pile communication self-repair control system described in this embodiment is based on the deep learning model of CNN and LSTM, which can simultaneously capture the local features of communication data (such as abnormal data packet formats) and timing dependencies (such as periodic interference). The diagnostic accuracy is improved by 30% to 50% compared with traditional methods, significantly reducing misjudgments and missed judgments. Secondly, through the fault self-repair strategy module, the system can automatically reload the configuration for software protocol errors and adjust communication parameters for electromagnetic interference, shortening the average repair time from 4 hours to within 30 minutes, significantly reducing the need for manual intervention. At the same time, the deep learning model supports online updates and can learn normal and abnormal modes under the new communication protocol, ensuring that the system maintains high stability during protocol iterations or environmental changes.

[0049] Example 2: Figure 1 As shown, this embodiment is based on Example 1 and is used to illustrate a specific self-repair method for communication failures, including:

[0050] Before explaining the principle, a brief background is given: new energy vehicle models are updated very quickly, and the corresponding charging protocols are also varied, which increases the difficulty of adapting universal charging piles. This embodiment provides a method for repairing communication failures by constructing a new charging power curve based on the basic battery module information sent by the BMS in the absence of a complete charging protocol for the corresponding vehicle model (lack of a preset charging power curve).

[0051] Step S100: In response to a user order instruction, the data acquisition module sends a communication request to the BMS of the current new energy vehicle, so that the BMS feeds back vehicle information of the current new energy vehicle, the vehicle information including vehicle model and vehicle battery information;

[0052] Step S200: The data acquisition module sends the vehicle information to the fault diagnosis module, so that the fault diagnosis module detects whether there is a charging power curve consistent with the vehicle model in the charging power preset operation library. If not, it is determined that a communication abnormality occurs with the BMS, and a communication abnormality instruction that the vehicle model cannot be matched is generated. The communication abnormality instruction is sent to the fault self-repair module, so that the fault diagnosis model retrieves the vehicle battery information and generates a charging power curve that matches the vehicle model based on the vehicle battery information; and a new communication protocol is established with the BMS based on the charging power curve, so that the charging pile charges the new energy vehicle according to the charging power curve.

[0053] Generating a charging power curve matching the vehicle model based on vehicle battery information in step S200 includes:

[0054] Step S210: Parse the vehicle battery information to obtain the cell voltage, cell temperature, and battery type. Based on the pressure difference between the cell voltage and the standard voltage, construct a pressure difference distribution map corresponding to the battery module (a three-dimensional map consisting of multiple pressure difference columns distributed in a matrix). Determine the thermal resistance coefficient of the cell based on the battery type. The thermal resistance coefficient is provided by the battery supplier of the new energy vehicle and burned into the vehicle battery information for later calculation of the heat generation of the cell during charging.

[0055] Step S220: Sort multiple cell voltages based on voltage values, and then construct a voltage amplitude curve. Select multiple basic voltage cells based on a preset fluctuation slope, where the starting point of the fluctuation slope coincides with the starting point of the voltage amplitude curve. Starting from the starting point of the voltage amplitude curve, select multiple consecutive cell voltages with voltage values below the set fluctuation slope, and mark the selected cell voltages as basic voltage cells. The basic voltage cell has a lower voltage value and is used as the lower limit of the voltage threshold range for subsequent population division. This method is different from the conventional method of using the lowest cell voltage as the lower limit of the voltage threshold range. This method ensures the number of low-voltage cells and makes the division of multiple voltage threshold ranges more reasonable.

[0056] Step S230: Calculate a first mean voltage of the plurality of basic voltage cells, construct a plurality of voltage threshold ranges based on a difference between the first mean voltage and the standard voltage, and construct a cell distribution population corresponding to each voltage threshold range in a voltage difference distribution diagram based on the plurality of voltage threshold ranges;

[0057] Step S240, a distance-based clustering algorithm is used to construct a core clustering area in each monomer distribution population (in actual use, the battery performance degradation in the battery module is regionalized, that is, after a battery has abnormal performance, its surrounding batteries will also be affected during long-term use, resulting in a certain performance degradation, which is reflected in the pressure difference distribution diagram as a whole. The core clustering areas corresponding to multiple monomer distribution populations do not overlap with each other, and the second mean voltage corresponding to each core clustering area is calculated, and based on the difference between the second mean voltage and the standard voltage, the number of monomers in the core clustering area and the distribution shape of the monomers in the core clustering area, a time-heat accumulation diagram of the core clustering area during the charging process is constructed.

[0058] Compared to the conventional method of calculating the heat accumulation of each battery cell during the charging process, this embodiment uses Ohm's law to calculate the instantaneous heat generation based on the average voltage and thermal resistance coefficient of the core cluster area, and calculates the cumulative heat by time integration to obtain the time-heat accumulation corresponding to this area. Compared with the conventional method of calculating the time-heat accumulation diagram corresponding to the entire battery module based on a single cell, the method described in this embodiment greatly reduces the computing power required and shortens the abnormal repair response time of the charging pile.

[0059] Step S250: construct a temperature cloud map based on the cell temperature, and superimpose the time-heat accumulation map on the temperature cloud map, thereby obtaining a first battery heat change cloud map of the battery module during the charging process, and calculate the dynamic heat dissipation distribution map of the first battery heat change cloud map based on the current ambient temperature and battery type, obtain a second battery heat change cloud map of the battery module during the charging process by superimposing the first battery heat change cloud map and the corresponding dynamic heat dissipation distribution map, formulate a corresponding charging power curve based on the second battery heat change cloud map, and enter the vehicle model, charging power curve, pressure difference distribution map and ambient temperature into the big data storage server as training data for the neural network model for subsequent charging power matching.

[0060] Secondly, the calculation of the dynamic heat dissipation distribution map of the first battery heat change cloud map based on the current ambient temperature and battery type in step S250 includes:

[0061] Step S251: constructing an ambient temperature field based on the current ambient temperature, and performing normalization processing on the first battery heat change cloud map and the ambient temperature field in sequence to facilitate feature recognition and extraction by the subsequent convolutional neural network;

[0062] Step S252: extracting the spatiotemporal local features of the normalized first battery heat change cloud map through two 3D convolutional layers, and capturing the global dependency in the time dimension through a multi-head self-attention mechanism to generate time series enhanced features;

[0063] Step S253: bilinearly interpolate the normalized ambient temperature field to a resolution corresponding to the first battery heat change cloud map (the pixel correspondence in the resolution facilitates subsequent channel stitching. It should be noted that the resolution of the ambient temperature field here is not exactly the same as the resolution of the first battery heat change cloud map, and there is a certain scaling ratio between them, that is, the resolution of the first battery heat change cloud map is an integer multiple of the ambient temperature field, preferably 4 times). Then, channel stitching is performed on the time series enhancement features to form a fusion feature.

[0064] Step S254: input the fusion features into a preset physical constraint model, and then generate a corresponding dynamic heat dissipation distribution map according to the time sequence.

[0065] The physical constraint model constructs the heat dissipation of the local area in the following way:

[0066] Step S2541: extract the ambient temperature channel from the fusion feature, generate a temperature sensitivity coefficient matrix, and multiply the temperature sensitivity coefficient matrix by the convolution kernel weight element-wise to obtain the initial heat dissipation;

[0067] Step S2542: extract the battery temperature from the fusion feature, and adjust the heat loss direction consistency threshold based on the temperature difference between the battery temperature and the ambient temperature. Calculate the gradient-corrected heat dissipation through the loss function based on the direction consistency threshold, and then construct multiple heat dissipation distribution maps frame by frame based on the gradient-corrected heat dissipation to form a dynamic heat dissipation distribution map.

[0068] Formulating a corresponding charging power curve based on the second battery heat change cloud map in step S250 includes:

[0069] Step S255: construct a first safety temperature reference surface based on the preset safety charging temperature threshold, and reduce the preset charging power at a corresponding moment based on the volume of the portion of the second battery heat change cloud graph that protrudes from the first safety temperature reference surface at a certain moment, thereby obtaining a revised preset charging power. Based on the current voltage consistency fluctuation graph, further reduce the entire revised preset charging power to obtain a charging power curve.

[0070] The voltage consistency fluctuation graph in step S255 is constructed as follows:

[0071] Step S2551: Calculate the basic voltage using a weighted algorithm based on the mean voltage and number of cells corresponding to a cell distribution population with the lowest voltage threshold range and the mean voltage corresponding to the voltage difference distribution diagram, thereby constructing a basic voltage base.

[0072] Step S2552: Fit the basic voltage base to the pressure difference distribution diagram, so as to obtain a voltage consistency fluctuation diagram by deducting the basic voltage base portion from the pressure difference distribution diagram. The voltage consistency fluctuation diagram is used to characterize the voltage fluctuation of multiple cells in the battery module.

[0073] The foregoing description is merely a preferred embodiment of the present invention and is not intended to limit the present invention. Those skilled in the art will readily appreciate that various modifications and variations of the present invention are possible. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of the present invention shall be included within the scope of protection of the present invention.

Claims

1. A charging pile communication self-repair control system, characterized in that: The system comprises: A data acquisition module is used to collect communication data in real time through sensors deployed at the communication interface between the charging pile and the electric vehicle. The communication data includes communication status, data transmission rate, number of error data packets and communication protocol interaction information, and to clean and normalize the communication data. The fault diagnosis module is composed of a fusion of a convolutional neural network and a long short-term memory network. The convolutional neural network is used to extract local features of pre-processed communication data, and the long short-term memory network is used to analyze time series dependencies and output fault type diagnosis results. A fault self-repair module performs repair operations based on the fault type diagnosis results: if it is a software communication fault, it automatically reloads the communication protocol stack or adjusts the protocol parameter configuration; if it is a hardware communication fault, it triggers an early warning and switches to a backup communication line; if it is an electromagnetic interference fault, it adjusts the communication line or enhances anti-interference measures; Secondly, the convolutional neural network in the fault diagnosis model contains three convolutional layers and three pooling layers for extracting local features of different scales. The long short-term memory network contains two layers for capturing long-term temporal dependencies. The fault self-repair module automatically compares the current communication protocol with the preset protocol library for protocol conflict faults, and dynamically updates the protocol configuration parameters.

2. The charging pile communication self-repair control system according to claim 1, characterized in that: It also includes a communication coordination module for coordinating the operating processes of the data acquisition and preprocessing module, the deep learning fault diagnosis model and the fault self-repair strategy module, and communicating with the charging control module and the management platform of the charging pile, uploading fault information and receiving remote instructions in real time, and sending instructions to the charging control module to reduce the charging power when the communication is unstable until the communication is restored to stability.

3. A self-repair method based on the charging pile communication self-repair control system according to claim 1, characterized in that: The method comprises: In response to the user's order instruction, the data acquisition module sends a communication request to the BMS of the current new energy vehicle, so that the BMS can feedback the vehicle information of the current new energy vehicle, including the vehicle model and vehicle battery information; The data acquisition module sends the vehicle information to the fault diagnosis module, so that the fault diagnosis module detects whether there is a charging power curve consistent with the vehicle model in the charging power preset operation library. If not, it is determined that a communication abnormality has occurred with the BMS, and a communication abnormality instruction indicating that the vehicle model cannot be matched is generated. The communication abnormality instruction is sent to the fault self-repair module, so that the fault diagnosis model retrieves the vehicle battery information and generates a charging power curve that matches the vehicle model based on the vehicle battery information; and a new communication protocol is established with the BMS based on the charging power curve, so that the charging pile charges the new energy vehicle according to the charging power curve.

4. The self-repair method according to claim 3, characterized in that: Generating a charging power curve that matches the vehicle model based on vehicle battery information, including: Parse the vehicle battery information to obtain the cell voltage, cell temperature, and battery type. Based on the voltage difference between the cell voltage and the standard voltage, construct a pressure difference distribution map corresponding to the battery module. Determine the thermal resistance coefficient of the cell based on the battery type. The thermal resistance coefficient is provided by the battery supplier of the new energy vehicle and burned into the vehicle battery information. Sort multiple cell voltages based on voltage values, and then construct a voltage amplitude curve. Select multiple basic voltage cells based on a preset fluctuation slope, with the starting point of the fluctuation slope coinciding with the starting point of the voltage amplitude curve. Starting from the starting point of the voltage amplitude curve, select multiple consecutive cell voltages whose voltage values are below the set fluctuation slope, and mark the selected cell voltages as basic voltage cells. Calculating a first mean voltage of a plurality of basic voltage monomers, constructing a plurality of voltage threshold ranges based on a difference between the first mean voltage and a standard voltage, and constructing a monomer distribution population corresponding to each voltage threshold range in a voltage difference distribution diagram based on the plurality of voltage threshold ranges; A distance-based clustering algorithm constructs a core cluster in each monomer distribution population. The core clusters corresponding to multiple monomer distribution populations do not overlap with each other. The second mean voltage corresponding to each core cluster is calculated. Based on the difference between the second mean voltage and the standard voltage, the number of monomers in the core cluster, and the shape of the monomer distribution in the core cluster, a time-heat accumulation diagram of the core cluster during the charging process is constructed. A temperature cloud map is constructed based on the cell temperature, and the time-heat accumulation map is superimposed on the temperature cloud map to obtain a first battery heat change cloud map of the battery module during the charging process. The dynamic heat dissipation distribution map of the first battery heat change cloud map is calculated based on the current ambient temperature and battery type. The second battery heat change cloud map of the battery module during the charging process is obtained by superimposing the first battery heat change cloud map and the corresponding dynamic heat dissipation distribution map. The corresponding charging power curve is formulated based on the second battery heat change cloud map, and the vehicle model, charging power curve, pressure difference distribution map and ambient temperature are entered into the big data storage server as training data for the neural network model used for subsequent charging power matching.

5. The self-repairing method according to claim 4, characterized in that: A dynamic heat dissipation distribution diagram of the first battery heat change cloud diagram is calculated based on the current ambient temperature and battery type, including: Constructing an ambient temperature field based on the current ambient temperature, and performing normalization processing on the first battery heat change cloud map and the ambient temperature field in sequence; Two layers of 3D convolutional layers are used to extract the spatiotemporal local features of the normalized first battery heat change cloud map. The multi-head self-attention mechanism is used to capture the global dependencies in the time dimension and generate time-series enhanced features. The normalized ambient temperature field is bilinearly interpolated to a resolution corresponding to the first battery heat change cloud map, and channel-joined with the time series enhancement feature to form a fusion feature; Input the fusion features into a preset physical constraint model, and then generate a corresponding dynamic heat dissipation distribution map according to the time sequence; The physical constraint model constructs the heat dissipation of the local area in the following way: Extract the ambient temperature channel from the fusion feature and generate a temperature sensitivity coefficient matrix. Multiply the temperature sensitivity coefficient matrix by the convolution kernel weight element by element to obtain the initial heat dissipation. The battery temperature is extracted from the fusion features, and the heat loss direction consistency threshold is adjusted based on the temperature difference between the battery temperature and the ambient temperature. The gradient-corrected heat dissipation is calculated through the loss function based on the direction consistency threshold. Then, multiple heat dissipation distribution maps are constructed frame by frame based on the gradient-corrected heat dissipation to form a dynamic heat dissipation distribution map.

6. The self-repairing method according to claim 5, characterized in that: A corresponding charging power curve is formulated based on the second battery heat change cloud map, including: A first safety temperature reference surface is constructed based on the preset safety charging temperature threshold, and the preset charging power at a certain moment is reduced based on the volume of the part of the second battery heat change cloud map that protrudes from the first safety temperature reference surface, thereby obtaining a corrected preset charging power. Based on the current voltage consistency fluctuation graph, the entire corrected preset charging power is further reduced to obtain a charging power curve.

7. The self-repairing method according to claim 6, characterized in that: The voltage consistency fluctuation diagram is constructed as follows: The basic voltage is calculated by a weighted algorithm based on the mean voltage and number of monomers corresponding to the monomer distribution population with the lowest voltage threshold range, combined with the mean voltage corresponding to the voltage difference distribution diagram, to obtain the basic voltage, and then construct the basic voltage base; The basic voltage base is fitted to the voltage difference distribution diagram, so that the basic voltage base portion is deducted from the voltage difference distribution diagram to obtain a voltage consistency fluctuation diagram, which is used to characterize the voltage fluctuation of multiple cells in the battery module.

Images