Cloud edge collaboration-based electric vehicle intelligent charging safety control method and system, computer device and medium

Abstract

The application relates to an electric vehicle intelligent charging safety control method and system based on cloud edge cooperation, computer equipment and a medium, which comprises the following steps: uploading a vehicle identification code sent by an electric vehicle to a cloud end, so that an AI model in the cloud end generates a first charging control instruction for the electric vehicle and sends the first charging control instruction to a charging pile; when the first charging control instruction is a first charging instruction, electric energy is delivered to the electric vehicle; real-time charging data of the electric vehicle is acquired in the process of delivering the electric energy, and the real-time charging data is detected by an AI controller; when the detection result represents that the charging is normal, repeated detection is performed until a charging termination message is received, and the delivery of the electric energy to the electric vehicle is stopped; when the detection result represents that the charging is abnormal, a second charging control instruction is generated by the AI controller, and when the second charging control instruction is a stop charging instruction, a relay is cut off, and the delivery of the electric energy to the electric vehicle is stopped. The method can reduce risks and avoid safety protection lag.

Description

Technical Field

[0001] This application relates to the field of electric vehicle charging facilities and battery safety management technology, and in particular to a cloud-edge collaborative intelligent charging safety control method, system, computer equipment and medium for electric vehicles. Background Technology

[0002] With the rapid development of the electric vehicle industry, the charging safety of power batteries has become a focus of industry attention. During the charging process, batteries may experience thermal runaway events due to factors such as internal short circuits, overcharging, overheating, or mechanical failure, which can lead to serious safety hazards.

[0003] Currently, traditional DC charging stations primarily convert AC power from the grid into DC power to charge vehicle batteries. Their operation is highly dependent on BMS (Battery Management System) commands, making them essentially passive energy replenishment devices. However, these charging stations generally lack independent sensing and in-depth analysis capabilities regarding battery status, failing to provide effective redundancy protection in case of BMS failure or abnormal commands, resulting in lagging safety protection. Furthermore, existing charging solutions often employ a single method for vehicle charging control, making it difficult to cope with complex and changing real-world conditions, further increasing safety risks. Summary of the Invention

[0004] Therefore, it is necessary to provide a cloud-edge collaborative intelligent charging safety control method, system, computer equipment, and medium for electric vehicles to address the aforementioned technical problems.

[0005] A cloud-edge collaborative intelligent charging safety control method for electric vehicles, the method comprising: S1. Receive the vehicle identification code sent by the electric vehicle via the charging CAN bus, and upload the vehicle identification code to the cloud, so that the cloud can perform risk assessment based on the historical driving data, battery static data and historical charging data associated with the vehicle identification code through an AI model, generate a first charging control command for the electric vehicle, and send the first charging control command to the charging pile. Preferably, the vehicle identification number is the VIN (Vehicle Identification Number) of the electric vehicle. Preferably, the historical charging data includes the electric vehicle's charging voltage / current curve, the rate of change of the individual cell voltage / temperature range, the BMS (Battery Management System) request deviation, and the rate of change of the dynamic insulation monitoring value during the last charging process. Preferably, the historical driving data refers to the voltage, current, energy consumption, temperature, and mileage correlation data of the electric vehicle's battery pack under historical driving conditions. Preferably, the battery static data includes the static voltage drop, self-discharge rate, static insulation resistance, and equalization records of the battery pack. S2. When the first charging control command received is a first charging command, power is supplied to the electric vehicle; S3. During the transmission of electrical energy, the real-time charging data of the electric vehicle is acquired through the AI ​​controller, and the AI ​​model deployed in the AI ​​controller performs detection based on the real-time charging data to obtain the detection result; Preferably, the real-time charging data refers to the dynamic operating parameters that are dynamically collected by the battery management system of the electric vehicle during the charging process, used to characterize the current operating status and safety and health level of the battery pack; the real-time charging data includes the battery pack's real-time highest single-cell voltage, real-time lowest single-cell voltage, real-time highest single-cell temperature, real-time lowest single-cell temperature, real-time charging voltage / current curve, real-time requested current, real-time requested voltage, and real-time insulation resistance. S4. When the detection result indicates that there is no abnormality in charging, repeat S3 until a stop charging message is received from the electric vehicle, and stop supplying power to the electric vehicle; when the detection result indicates that there is an abnormality in charging, use the AI ​​controller to generate a second charging control command based on the detection result; S5. When the second charging control command is a stop charging command, disconnect the relay to stop supplying electrical energy to the electric vehicle; when the second charging control command is a power adjustment command, adjust the charging power of the charging pile based on the power adjustment command.

[0006] In one embodiment, the method further includes: The real-time charging data is preprocessed to obtain preprocessed data; The preprocessed data is sent to the cloud so that the AI ​​model in the cloud can perform a battery risk assessment based on the preprocessed data, the historical driving data uploaded by the electric vehicle, and the battery static data, and obtain a battery test report for the electric vehicle. The battery test report or the health status in the battery test report is then sent to the charging pile.

[0007] Preferably, the preprocessing includes outlier removal and feature value (preprocessed data) calculation operations.

[0008] In one embodiment, the charging pile includes a human-machine interface, and the method further includes: During the process of supplying electrical energy to the electric vehicle and / or when the supply of electrical energy to the electric vehicle is stopped, the battery detection report or the health status is displayed through the human-machine interface; the battery detection report includes at least the health status, the consistency analysis results of the performance parameters of each individual cell in the battery pack of the electric vehicle, and the performance trend prediction results of each performance parameter of each individual cell over time.

[0009] In one embodiment, the method further includes: The real-time charging data is uploaded to the cloud so that the cloud can train the AI ​​model based on the real-time charging data, and then send the trained AI model to the AI ​​controller of the charging pile.

[0010] In one embodiment, step S4 includes: During the process of transmitting electrical energy to the electric vehicle, the following data are acquired: first requested voltage, first requested current, first single-cell voltage difference between the highest and lowest single-cell voltages, first single-cell temperature difference between the highest and lowest single-cell temperatures, first insulation resistance, internal resistance of each single cell in the battery pack, state of charge of each single cell, health status of each single cell, historical charge / discharge cycles, historical anomaly records, and battery pack temperature. Calculate the first voltage difference between the first actual output voltage of the charging pile and the first requested voltage; calculate the first current difference between the first actual output current of the charging pile and the first requested current; determine the temperature rise rate of the battery pack based on the battery pack temperature; determine the internal resistance dispersion based on the internal resistance of each individual cell; determine the battery state of charge deviation between the maximum and minimum battery state of charge based on the battery state of charge of each individual cell. The rate of change of the first cell voltage difference, the rate of change of the first cell temperature difference, the first voltage difference, the first current difference, the temperature rise rate, the internal resistance dispersion, the historical anomaly records, each of the health states, the historical charge-discharge cycles, the rate of change of the first insulation resistance, and the battery state of charge deviation are input into the AI ​​model deployed in the AI ​​controller for risk assessment to obtain the risk level. Based on the risk level, a second charging control command is generated.

[0011] In one embodiment, generating the second charging control command based on the risk level includes: When the risk level is a first preset level, a second charging command is generated to continue supplying electrical energy to the electric vehicle based on the second charging command; When the risk level is the third preset level, a power adjustment command is generated to adjust the charging power of the charging pile based on the power adjustment command; When the risk level is the third preset level, a stop charging command is generated to stop the supply of electrical energy to the electric vehicle based on the stop charging command; the danger level of the first preset level is lower than that of the second preset level, and the danger level of the second preset level is lower than that of the third preset level.

[0012] A cloud-edge collaborative intelligent charging safety control system for electric vehicles, used to execute the above method, the system comprising: The first instruction generation module is used to receive the vehicle identification code sent by the electric vehicle via the charging CAN bus, and upload the vehicle identification code to the cloud, so that the cloud can use an AI model to perform a risk assessment based on the historical driving data, battery static data and historical charging data associated with the vehicle identification code, generate a first charging control instruction for the electric vehicle, and send the first charging control instruction to the charging pile. A power transmission module is used to transmit power to the electric vehicle when the first charging control command received is a first charging command; The detection module is used to acquire real-time charging data of the electric vehicle through the AI ​​controller during the transmission of electrical energy, and to perform detection based on the real-time charging data through the AI ​​model deployed in the AI ​​controller to obtain the detection result; The second instruction generation module is used to repeat the detection when the detection result indicates that there is no abnormality in charging, until a stop charging message is received from the electric vehicle, and to stop the supply of power to the electric vehicle; when the detection result indicates that there is an abnormality in charging, the AI ​​controller is used to generate a second charging control instruction based on the detection result. The charging control module is used to disconnect the relay to stop supplying electrical energy to the electric vehicle when the second charging control command is a stop charging command; and to adjust the charging power of the charging pile based on the power adjustment command when the second charging control command is a power adjustment command.

[0013] A computer device includes a memory and a processor, the memory storing a computer program, the processor executing the computer program to implement the steps of the method described above.

[0014] A computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the above-described method.

[0015] In the aforementioned cloud-edge collaborative intelligent charging safety control method for electric vehicles, during the energy transmission process, an AI controller is used to acquire real-time charging data of the electric vehicle. An AI model deployed in the AI ​​controller performs detection based on this real-time charging data to obtain detection results. If the detection results indicate no charging abnormalities, the detection operation is repeated until a stop-charging message is received from the electric vehicle, at which point the energy transmission to the electric vehicle is stopped. If the detection results indicate a charging abnormality, the AI ​​controller generates a second charging control command based on the real-time charging data. If the second charging control command is a stop-charging command, the relay is disconnected to stop the energy transmission to the electric vehicle. If the second charging control command is a power adjustment command, the charging power of the charging pile is adjusted based on the power adjustment command. This approach minimizes the safety intervention path. Compared to schemes where charging is controlled by commands issued by the electric vehicle's BMS, this application can directly cut off the relays inside the charging pile within milliseconds, physically preventing the transmission of dangerous energy to the electric vehicle. This achieves the most efficient source protection and avoids the problem of delayed safety protection. Furthermore, the first charging control command, the second charging control command, and the electric vehicle's built-in protection system constitute completely independent multi-layered safeguards. This provides effective safety protection for the electric vehicle, greatly reducing the risk of single-point failure and thus lowering overall safety risks. Attached Figure Description

[0016] Figure 1 This is a schematic diagram of an intelligent charging safety control system for electric vehicles based on cloud-edge collaboration in one embodiment; Figure 2 This is a flowchart illustrating a cloud-edge collaborative intelligent charging safety control method for electric vehicles in one embodiment. Figure 3 This is a block diagram illustrating the working principles of the cloud, charging pile, and electric vehicle in one embodiment. Figure 4 This is a schematic diagram of the overall process of a cloud-edge collaborative intelligent charging safety control method for electric vehicles in another embodiment. Detailed Implementation

[0017] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0018] In one embodiment, intelligence, such as Figure 1As shown, a cloud-edge collaborative intelligent charging safety control system for electric vehicles is provided. This system includes a cloud platform, a charging station, and the electric vehicle. The cloud platform is connected to the electric vehicle's T-Box (Telematics Box) and the charging station via a network, while the electric vehicle and the charging station are connected via a wired charging gun. The charging station includes an AI (Artificial Intelligence) controller, a human-machine interface, a rectifier, and a power converter. The human-machine interface is used for voltage selection, current selection, charging time selection, starting charging, and stopping charging. The AI ​​controller generates a second charging control command. The cloud platform generates a first charging control command. The electric vehicle includes a battery pack and a battery management system. The electric vehicle transmits historical driving data and battery idle data to the cloud. The network includes, but is not limited to, 4G, 5G, and Ethernet.

[0019] Furthermore, the human-machine interface of the charging station is also used to display battery test reports.

[0020] Furthermore, the AI ​​controller of the charging station is also used to send pre-processed real-time charging data to the cloud.

[0021] Furthermore, the cloud is also used to generate battery test reports and send them to charging stations.

[0022] In one embodiment, such as Figure 2 As shown, a cloud-edge collaborative intelligent charging safety control method for electric vehicles is provided, which is applied to... Figure 1 Taking the charging pile in the middle as an example, the following steps are included: S1. Receive the vehicle identification code sent by the electric vehicle through the charging CAN bus, and upload the vehicle identification code to the cloud. The cloud then uses an AI model to conduct a risk assessment based on historical driving data, battery static data and historical charging data associated with the vehicle identification code, generate a first charging control command for the electric vehicle, and send the first charging control command to the charging pile. When a charging pile is successfully connected to an electric vehicle, it can receive the vehicle identification code sent by the electric vehicle via the charging CAN (Controller Area Network) bus.

[0023] Historical charging data refers to the charging data of an electric vehicle during its previous charging process. This data includes, but is not limited to, the charging voltage / current curve, the rate of change of individual cell voltage / temperature range, the BMS (Battery Management System) request deviation, and the rate of change of dynamic insulation monitoring values ​​during the previous charging process. Specifically, during the previous charging process, the BMS transmitted the charging voltage / current curve, individual cell voltage, individual cell temperature, requested voltage, requested current, and historical insulation resistance via the charging CAN bus to the AI ​​controller built into the charging pile. The charging pile samples and obtains the actual output voltage and actual output current. The AI ​​controller preprocesses the data to obtain the BMS request deviation, the rate of change of individual cell range, and the rate of change of historical insulation resistance, and integrates these to form historical charging data, which is then uploaded to the cloud. The BMS request deviation includes voltage deviation and current deviation; voltage deviation is the deviation between the requested voltage and the actual output voltage, and current deviation is the deviation between the requested current and the actual output current. Individual cell range includes the difference between the highest and lowest individual cell temperatures, and the difference between the highest and lowest individual cell voltages.

[0024] Historical driving data includes, but is not limited to, voltage, current, energy consumption, temperature, and mileage-related data of the electric vehicle's battery pack under historical driving conditions. Historical driving data can characterize the dynamic performance of the battery pack.

[0025] Battery static data includes, but is not limited to, static voltage drop, self-discharge rate, static insulation resistance, and equalization records of the battery pack. Static insulation resistance is the ability of the insulating materials or components of an electric vehicle to prevent leakage current. Equalization records are operation records of the battery pack equalization operations performed by the electric vehicle's BMS. The equalization operation is the adjustment operation of peak shaving and valley filling for each individual cell within the battery pack. Battery static data can characterize the static consistency of the battery pack.

[0026] The first charging control command is generated by an AI model deployed in the cloud. Specifically, historical driving data, battery idle data, and historical charging data associated with the vehicle identification number stored in the cloud are input into the cloud-deployed AI model for risk assessment, and the first charging control command is output. The AI ​​model includes, but is not limited to, CNN (Convolutional Neural Network), LSTM (Long Short-Term Memory), and Transformer (self-attention mechanism).

[0027] The process of connecting a charging station to an electric vehicle includes: when the user inserts the charging gun of the charging station into the charging port of the electric vehicle, the electric vehicle enters a prohibited driving state; while the electric vehicle is in the prohibited driving state, the charging station detects whether the voltage to ground at point CC1 is within a preset first voltage range, and simultaneously detects whether the resistance value at point CC1 is within a preset resistance range; if the voltage to ground is within the first voltage range or the resistance value at point CC1 is within the preset resistance range, a charger identification message is sent to the electric vehicle so that the electric vehicle can determine the maximum output power of the charging station connected to it and the communication protocol of the charging station; after receiving the charger identification message, the electric vehicle automatically detects the voltage value at point CC2. If the voltage value at point CC2 is within a preset second voltage range, it is determined that the charging station and the electric vehicle are successfully connected. The information carried in the charger identification message includes, but is not limited to, the charging station's number, version number, charging station type (DC / AC), communication protocol, maximum / minimum voltage, maximum / minimum current, and the timestamp of the charging gun being inserted into the electric vehicle's charging port. The charging pile contains pull-up resistors and an ADC (Analog-to-Digital Converter) sampling circuit. When the charging gun is inserted into the charging port, point CC1 will generate the voltage to be measured at ground through the resistance of the electric vehicle (such as an RC resistor). The first preset voltage range may or may not be the same for different types of charging guns. The first preset voltage range may or may not be the same for different cable capacities.

[0028] Furthermore, once the charging station and the electric vehicle are successfully connected, the electric vehicle's BMS closes the battery relay and simultaneously sends a BMS identification message carrying the vehicle identification code to the charging station via the charging CAN bus. The BMS identification message includes, but is not limited to, battery type (ternary / lithium iron phosphate), rated capacity, rated total voltage, maximum allowable charging voltage / current, current battery SOC (State of Charge), BMS version number, and vehicle identification code. The BMS identification message sent to the charging station is a message to be parsed; only by parsing the BMS identification message can the charging station determine the electric vehicle's vehicle identification code.

[0029] The charging station is equipped with an AI controller that monitors the charging CAN bus in real time to detect anomalies promptly. The AI ​​controller monitors the entire process, including the charging handshake phase, normal charging phase, current reduction charging phase, and the final stage before charging ends. Because risks can arise at any time (such as sudden overheating of individual cells or insulation degradation during charging), monitoring must continue throughout the entire connection period. The AI ​​controller only stops monitoring after the charging gun is unplugged and physically disconnected.

[0030] S2. When the first charging control command received is the first charging command, electrical energy is supplied to the electric vehicle; The first charging control command sent from the cloud to the charging pile is one of the following: first charging command, charging prohibition command, and current reduction charging command.

[0031] When the first charging control command is the first charging command, the charging pile delivers electrical energy to the electric vehicle based on the preset normal charging power.

[0032] Furthermore, when the first charging control command is a prohibition charging command, the charging pile is prohibited from supplying electrical energy to the electric vehicle.

[0033] Furthermore, when the first charging control command is a reduced-current charging command, the charging power of the charging pile is reduced so that the charging pile delivers electrical energy to the electric vehicle at the reduced charging power.

[0034] S3. During the transmission of electrical energy, the AI ​​controller acquires real-time charging data of electric vehicles and uses the AI ​​model deployed in the AI ​​controller to perform detection based on the real-time charging data to obtain the detection results. Real-time charging data refers to the real-time data of the electric vehicle's battery pack during the charging process. This data includes, but is not limited to, the battery pack's real-time highest single-cell voltage, real-time lowest single-cell voltage, real-time highest single-cell temperature, real-time lowest single-cell temperature, real-time charging voltage / current curves, real-time requested current, real-time requested voltage, and real-time insulation resistance. Real-time charging data can characterize the charging safety features of electric vehicles.

[0035] The detection mainly involves using an AI model deployed in the AI ​​controller of the charging pile to check whether various parameters of the battery pack are abnormal. The detection can be a continuous or periodic process. For example, if the detection result indicates that there is no abnormality in charging, step S3 is repeated after a preset interval until a stop charging message is received from the electric vehicle; or if the detection result indicates that there is no abnormality in charging, step S3 is repeated directly until a stop charging message is received from the electric vehicle.

[0036] Furthermore, the real-time charging data undergoes a validity check to obtain verified real-time charging data. This verified data is then used by the AI ​​model deployed in the AI ​​controller for detection. This process eliminates invalid and corrupted data caused by communication anomalies, sensor malfunctions, or message errors, thereby improving the accuracy of the detection results.

[0037] S4. If the detection result indicates that there is no abnormality in charging, repeat S3 until a stop charging message is received from the electric vehicle, and stop supplying power to the electric vehicle; if the detection result indicates that there is an abnormality in charging, use the AI ​​controller to generate a second charging control command based on the detection result. S5. When the second charging control command is a stop charging command, disconnect the relay to stop supplying electrical energy to the electric vehicle; when the second charging control command is a power adjustment command, adjust the charging power of the charging pile based on the power adjustment command.

[0038] When the user removes the charging gun from the charging port, the electric vehicle's BMS will send a stop charging message to the charging station to stop the charging station from supplying power to the electric vehicle.

[0039] When the second charging control command is a stop charging command, the relay inside the charging pile is disconnected.

[0040] The second charging control command is generated by the local AI controller of the charging pile based on the detection results.

[0041] In the aforementioned cloud-edge collaborative intelligent charging safety control method for electric vehicles, during the energy transmission process, an AI controller is used to acquire real-time charging data of the electric vehicle. An AI model deployed in the AI ​​controller performs detection based on this real-time charging data to obtain detection results. If the detection results indicate no charging abnormalities, the detection operation is repeated until a stop-charging message is received from the electric vehicle, at which point the energy transmission to the electric vehicle is stopped. If the detection results indicate a charging abnormality, the AI ​​controller generates a second charging control command based on the real-time charging data. If the second charging control command is a stop-charging command, the relay is disconnected to stop the energy transmission to the electric vehicle. If the second charging control command is a power adjustment command, the charging power of the charging pile is adjusted based on the power adjustment command. This approach minimizes the safety intervention path. Compared to schemes where charging is controlled by commands issued by the electric vehicle's BMS, this application can directly cut off the relays inside the charging pile within milliseconds, physically preventing the transmission of dangerous energy to the electric vehicle. This achieves the most efficient source protection and avoids the problem of delayed safety protection. Furthermore, the first charging control command, the second charging control command, and the electric vehicle's built-in protection system constitute completely independent multi-layered safeguards. This provides effective safety protection for the electric vehicle, greatly reducing the risk of single-point failure and thus lowering overall safety risks.

[0042] In one embodiment, the method further includes: Real-time charging data is preprocessed to obtain preprocessed data; The pre-processed data is sent to the cloud so that the AI ​​model in the cloud can perform a battery risk assessment based on the pre-processed data, historical driving data uploaded by the electric vehicle, and battery static data, and obtain a battery test report for the electric vehicle. The battery test report or the health status in the battery test report is then sent to the charging station.

[0043] Historical driving data and battery idle data are uploaded to the cloud by the electric vehicle's T-Box.

[0044] Preprocessing includes outlier removal and feature value (preprocessed data) calculation. Specifically, real-time charging data includes multiple times of the first requested voltage, first requested current, the first cell voltage difference between the highest and lowest voltages of the first cell, the first cell temperature difference between the highest and lowest temperatures of the first cell, the first insulation resistance, the internal resistance of each cell in the battery pack, the battery state of charge of each cell, the health status of each cell, historical charge / discharge cycles, historical anomaly records, and battery pack temperature. The preprocessed data includes the rate of change of the first cell voltage difference, the rate of change of the first cell temperature difference, the first voltage difference, the first current difference, the temperature rise rate, the internal resistance dispersion, historical anomaly records, each health status, historical charge / discharge cycles, the rate of change of the first insulation resistance, and the battery state of charge deviation.

[0045] During each charge, preprocessed data can be sent to the cloud only once, or it can be sent periodically. When an electric vehicle is charging, the preprocessed data sent to the cloud during the previous charge is used as the historical charging data for the current charge, and a battery testing report is generated based on the updated historical charging data.

[0046] The battery test report should include at least the health status, the consistency analysis results of the performance parameters of each individual cell in the battery pack of the electric vehicle, and the performance trend prediction results of each individual cell's performance parameters over time.

[0047] State of Health (SOH) refers to the battery's state of health. Consistency analysis results show the degree of consistency among individual cells within the battery pack in terms of performance parameters such as voltage and internal resistance. Poor consistency is a significant indicator of battery pack aging and its potential for safety hazards. Performance trend prediction results refer to the prediction and analysis of the performance parameters of each individual cell in the battery pack over a future period.

[0048] The health status, consistency analysis results, and performance trend prediction results are all obtained through an AI model deployed in the cloud. Furthermore, preprocessed data, historical driving data uploaded by the electric vehicle, and battery static data are input into the AI ​​model deployed in the cloud, which outputs the health status, consistency analysis results, and performance trend prediction results. Based on these outputs, a battery testing report for the electric vehicle is generated.

[0049] The AI ​​model deployed in the cloud is trained using historical driving data, historical charging data, and battery idle data. The trained AI model is then sent to the AI ​​controller of the charging station via the cloud. This allows the protection capabilities of each charging station to continuously improve over time and with the accumulation of data, achieving collective intelligent evolution of the system.

[0050] In this embodiment, a battery test report for an electric vehicle is obtained based on preprocessed data, historical driving data uploaded by the electric vehicle, and battery static data. This avoids the limitations of relying solely on preprocessed data for battery analysis, making the battery test report more comprehensive and accurate.

[0051] In one embodiment, the charging station includes a human-machine interface, and the method further includes: During and / or when power is supplied to the electric vehicle, a battery test report or health status is displayed through a human-machine interface. The battery test report includes at least the health status, the consistency analysis results of the performance parameters of each individual cell in the battery pack of the electric vehicle, and the performance trend prediction results of each performance parameter of each individual cell over time.

[0052] The battery test report or health status can be displayed automatically in the human-computer interaction interface, or it can be displayed in the human-computer interaction interface in response to the information viewing operation triggered by the user.

[0053] In this embodiment, by displaying battery detection reports or health status on the human-computer interaction interface, users can intuitively observe the battery status of the electric vehicle, simplifying the process for users to obtain the status.

[0054] In one embodiment, the method further includes: Real-time charging data is uploaded to the cloud so that the cloud can train an AI model based on the real-time charging data, and then the trained AI model is sent to the AI ​​controller of the charging pile.

[0055] In this embodiment, by uploading real-time charging data to the cloud, the cloud can train an AI model based on the real-time charging data, and then send the trained AI model to the AI ​​controller of the charging pile. This allows the protection capability of each charging pile to continuously improve over time and with data accumulation, thus realizing the collective intelligent evolution of the system.

[0056] In one embodiment, step S4 includes: During the process of transmitting electrical energy to the electric vehicle, the following data are acquired: the first requested voltage, the first requested current, the voltage difference between the highest and lowest voltages of the first single cell, the temperature difference between the highest and lowest temperatures of the first single cell, the first insulation resistance, the internal resistance of each cell in the battery pack, the state of charge of each cell, the health status of each cell, the historical charge-discharge cycles, historical anomaly records, and the battery pack temperature. Calculate the first voltage difference between the first actual output voltage and the first requested voltage of the charging pile; calculate the first current difference between the first actual output current and the first requested current of the charging pile; determine the temperature rise rate of the battery pack based on the battery pack temperature; determine the internal resistance dispersion based on the internal resistance of each individual cell; determine the battery state of charge deviation between the maximum and minimum battery state of charge based on the battery state of charge of each individual cell. The rate of change of the first cell voltage difference, the rate of change of the first cell temperature difference, the first voltage difference, the first current difference, the temperature rise rate, the internal resistance dispersion, historical anomaly records, various health states, historical charge and discharge cycles, the rate of change of the first insulation resistance, and the battery state of charge deviation are input into the AI ​​model deployed in the AI ​​controller for risk assessment to obtain the risk level. Based on the risk level, a second charging control command is generated.

[0057] Wherein, the first requested voltage is the output voltage of the charging station that the electric vehicle expects during charging. The first requested current is the output current of the charging station that the electric vehicle expects during charging.

[0058] The highest voltage of a single cell is the voltage of the highest-voltage single cell in the battery pack of an electric vehicle. The lowest voltage of a single cell is the voltage of the lowest-voltage single cell in the battery pack of an electric vehicle.

[0059] The highest temperature of the first single cell is the temperature of the hottest single cell in the battery pack of an electric vehicle. The lowest temperature of the first single cell is the temperature of the coldest single cell in the battery pack of an electric vehicle.

[0060] The first insulation resistance is the ability of the insulating materials or components of an electric vehicle to prevent leakage current.

[0061] Historical charge / discharge counts refer to the number of times an electric vehicle has been charged and discharged. Historical anomaly records refer to any abnormal records that have occurred with the electric vehicle.

[0062] Real-time charging data such as the first requested voltage, first requested current, first cell voltage difference, first cell temperature difference, first insulation resistance, and battery pack temperature are continuously acquired. Therefore, the charging pile can obtain the first requested voltage, first requested current, first cell voltage difference between the highest and lowest voltages of the first cell, first cell temperature difference between the highest and lowest temperatures of the first cell, first insulation resistance, and battery pack temperature at multiple times. Thus, the rate of change of the first cell voltage difference, the rate of change of the first cell temperature difference, and the rate of change of the first insulation resistance can be calculated based on the first cell voltage difference, the first cell temperature difference, and the first insulation resistance at multiple times. Based on the battery pack temperature at multiple times, the temperature rise rate of the battery pack can be determined.

[0063] In this embodiment, the risk level can be obtained by inputting the rate of change of the first cell voltage difference, the rate of change of the first cell temperature difference, the first voltage difference, the first current difference, the temperature rise rate, the internal resistance dispersion, historical anomaly records, various health states, historical charge and discharge cycles, the rate of change of the first insulation resistance, and the battery state of charge deviation into the AI ​​model deployed in the AI ​​controller.

[0064] In one embodiment, a second charging control command is generated based on the risk level, including: When the risk level is the first preset level, a second charging command is generated to continue supplying electrical energy to the electric vehicle based on the second charging command; When the risk level is the third preset level, a power adjustment command is generated to adjust the charging power of the charging pile based on the power adjustment command. When the risk level is the third preset level, a stop charging command is generated to stop the supply of electrical energy to the electric vehicle based on the stop charging; the risk level of the first preset level is lower than that of the second preset level, and the risk level of the second preset level is lower than that of the third preset level.

[0065] The first preset level indicates normal charging, the second preset level indicates that charging is risky, and the third preset level indicates that charging is dangerous.

[0066] Power adjustment commands include reducing charging power by 30%-50%.

[0067] In this embodiment, when the risk level is at the first preset level, a second charging command is generated, so that electrical energy can continue to be delivered to the electric vehicle based on the second charging command; when the risk level is at the third preset level, a power adjustment command is generated, so that the charging power of the charging pile can be adjusted based on the power adjustment command, thereby adjusting the electrical energy delivered to the electric vehicle per unit time; when the risk level is at the third preset level, a stop charging command is generated, so that the delivery of electrical energy to the electric vehicle can be stopped based on the stop charging, avoiding safety accidents.

[0068] In one embodiment, step S3 includes: During the process of transmitting electrical energy to the electric vehicle, the first requested voltage, the first requested current, the first individual cell voltage difference between the highest voltage and the lowest voltage of the first individual cell, the first individual cell temperature difference between the highest temperature and the lowest temperature of the first individual cell, and the first insulation resistance of the electric vehicle are obtained. When one or more of the following conditions are met: the first voltage difference between the first actual output voltage and the first requested voltage of the charging pile is greater than the first threshold; the first current difference between the first actual output current and the first requested current of the charging pile is greater than the second threshold; the rate of change of the first individual cell voltage difference is greater than the third threshold; the rate of change of the first individual cell temperature difference is greater than the fourth threshold; or the rate of change of the first insulation resistance is greater than the fifth threshold, a detection result characterizing an abnormal charging of the electric vehicle is obtained. When the first voltage difference is less than or equal to the first threshold, the first current difference is less than or equal to the second threshold, the rate of change of the first individual voltage difference is less than or equal to the third threshold, the rate of change of the first individual temperature difference is less than or equal to the fourth threshold, and the rate of change of the first insulation resistance is less than or equal to the fifth threshold, a detection result indicating that there is no abnormality in the charging of the electric vehicle is obtained.

[0069] Among them, the first threshold, the second threshold, the third threshold, the fourth threshold, the fifth threshold, and the sixth threshold are all preset values.

[0070] The first requested voltage, first requested current, first single-cell voltage difference between the highest and lowest voltages of the first single cell, first single-cell temperature difference between the highest and lowest temperatures of the first single cell, and first insulation resistance of the electric vehicle are all real-time charging data obtained by the charging pile from the electric vehicle via the charging CAN bus.

[0071] In this embodiment, during the process of transmitting electrical energy to the electric vehicle, the first requested voltage, the first requested current, the first single-cell voltage difference between the highest and lowest voltages of the first single-cell, the first single-cell temperature difference between the highest and lowest temperatures of the first single-cell, and the first insulation resistance of the electric vehicle are acquired. Therefore, when one or more of the following conditions are met, a detection result indicating an abnormal charging of the electric vehicle can be obtained: the first voltage difference between the first actual output voltage of the charging pile and the first requested voltage is greater than a first threshold; the first current difference between the first actual output current of the charging pile and the first requested current is greater than a second threshold; the rate of change of the first single-cell voltage difference is greater than a third threshold; the rate of change of the first single-cell temperature difference is greater than a fourth threshold; and the rate of change of the first insulation resistance is greater than a fifth threshold. Conversely, when the first voltage difference is less than or equal to the first threshold; the first current difference is less than or equal to the second threshold; the rate of change of the first single-cell voltage difference is less than or equal to the third threshold; the rate of change of the first single-cell temperature difference is less than or equal to the fourth threshold; and the rate of change of the first insulation resistance is less than or equal to the fifth threshold, a detection result indicating no abnormal charging of the electric vehicle can be obtained.

[0072] In one embodiment, the process of generating the second charging control command in step S4 includes: A power adjustment command is generated when the following conditions are met: the first voltage difference is greater than a first threshold and less than a first stop threshold; the first current difference is greater than a second threshold and less than a second stop threshold; the rate of change of the first individual cell voltage difference is greater than a third threshold and less than a third stop threshold; the rate of change of the first individual cell temperature difference is greater than a fourth threshold and less than a fourth stop threshold; and the rate of change of the first insulation resistance is greater than a fifth threshold and less than a fifth stop threshold. The first threshold is less than the first stop threshold; the second threshold is less than the second stop threshold; the third threshold is less than the third stop threshold; the fourth threshold is less than the fourth stop threshold; and the fifth threshold is less than the fifth stop threshold. The power adjustment command is a second charging control command. A charging stop command is generated when one or more of the following conditions are met: the first voltage difference is greater than or equal to the first stop threshold; the first current difference is greater than or equal to the second stop threshold; the rate of change of the first individual cell voltage difference is greater than or equal to the third stop threshold; the rate of change of the first individual cell temperature difference is greater than or equal to the fourth stop threshold; or the rate of change of the first insulation resistance is greater than or equal to the fifth stop threshold.

[0073] Furthermore, the fifth stopping threshold is a fixed national standard hard threshold; the first threshold, the first stopping threshold, the second threshold, the second stopping threshold, the third threshold, the third stopping threshold, the fourth threshold, the fourth stopping threshold, and the fifth threshold are dynamic AI thresholds issued by the cloud.

[0074] Furthermore, the process of generating the power adjustment command also includes: generating a power adjustment command when the SOC change rate of the electric vehicle's battery pack is greater than a sixth threshold but less than a sixth stop threshold, the first voltage difference is less than a first stop threshold, the first current difference is less than a second stop threshold, the change rate of the first cell voltage difference is less than a third stop threshold, the change rate of the first cell temperature difference is less than a fourth stop threshold, and the change rate of the first insulation resistance is less than a fifth stop threshold; and generating a stop charging command when the SOC change rate is greater than the sixth stop threshold. Here, the SOC change rate refers to the change rate of the battery pack's SOC.

[0075] In this embodiment, a power adjustment command is generated when all of the following conditions are met: a first voltage difference greater than a first threshold and less than a first stop threshold; a first current difference greater than a second threshold and less than a second stop threshold; a rate of change of the first individual cell voltage difference greater than a third threshold and less than a third stop threshold; a rate of change of the first individual cell temperature difference greater than a fourth threshold and less than a fourth stop threshold; and a rate of change of the first insulation resistance greater than a fifth threshold and less than a fifth stop threshold. A charging stop command is generated when one or more of the following conditions are met: a first voltage difference greater than or equal to a first stop threshold; a first current difference greater than or equal to a second stop threshold; a rate of change of the first individual cell voltage difference greater than or equal to a third stop threshold; a rate of change of the first individual cell temperature difference greater than or equal to a fourth stop threshold; and a rate of change of the first insulation resistance greater than or equal to a fifth stop threshold. This avoids simplistic and abrupt power-off operations, minimizing charging interruptions caused by occasional fluctuations while ensuring absolute safety, thereby improving overall charging efficiency and user experience.

[0076] In one embodiment, upon obtaining a detection result characterizing an abnormal charging of an electric vehicle, a power adjustment command is generated. The scenarios for generating the power adjustment command include any one of the following: a first voltage difference greater than or equal to a first stop threshold, a first current difference greater than or equal to a second stop threshold, a rate of change of a first individual cell voltage difference greater than or equal to a third stop threshold, a rate of change of a first individual cell temperature difference greater than or equal to a fourth stop threshold, or a rate of change of a first insulation resistance greater than or equal to a fifth stop threshold. That is, any scenario for generating the power adjustment command satisfies at least one of the following conditions: a first voltage difference greater than a first threshold, a first current difference greater than a second threshold, a rate of change of a first individual cell voltage difference greater than a third threshold, a rate of change of a first individual cell temperature difference greater than a fourth threshold, or a rate of change of a first insulation resistance greater than a fifth threshold.

[0077] In one embodiment, the cloud-edge collaborative electric vehicle intelligent charging safety control method further includes generating a stop charging command when any of the following occurs during the charging process: BMS command anomaly, communication failure, battery historical risk linkage, charging pile hardware failure, or BMS alarm.

[0078] Among them, BMS command abnormality refers to any one of the following: the difference between the charging parameters requested by the BMS and the parameters deviating from the battery's rated parameters is greater than the deviation threshold, the requested current continuously exceeds the battery's upper limit, or the BMS frequently changes the required power without reason.

[0079] Communication failure is caused by the CAN bus of the charging station being disconnected, or the charging pile not receiving valid messages sent by the BMS for an extended period of time.

[0080] Battery history risk linkage means that if the battery SOH of the electric vehicle is too low or there has been a history of frequent overcharging and over-discharging, the battery will be forcibly limited or prohibited from charging after it reaches the preset SOC threshold.

[0081] Hardware failures in the charging station itself include, but are not limited to, power module overheating and sampling circuit failure. The power module is the module used to charge electric vehicles.

[0082] BMS alarms are generated when an electric vehicle sends a BMS message containing fault alarm fields (overvoltage, overtemperature fault codes) to the charging station. The charging station identifies the fault risk based on the fault alarm fields in the BMS message.

[0083] In one embodiment, the cloud-edge collaborative intelligent charging safety control method for electric vehicles further includes generating a power adjustment command when any of the following target conditions occur during the charging process: 1. The voltage difference / temperature difference of the first unit is slowly increasing, and the voltage difference / temperature difference of the first unit exceeds the warning threshold, but has not reached the dangerous shutdown threshold; 2. The first insulation resistance is decreasing slowly. The first insulation resistance is in the warning range, but it is not lower than the national standard shutdown threshold. 3. If the SOH of the electric vehicle is lower than the preset SOH and the SOC of the electric vehicle battery pack is higher than the preset state of charge, then step-wise current reduction will be implemented; 4. The ambient temperature is too high, and the overall battery temperature rises too quickly; 5. If the BMS parameters deviate slightly from the normal value and there is no sudden fault, prioritize reducing the current and observe, rather than directly cutting off the power.

[0084] In one embodiment, step S5 is followed by: In the event that the power supply to the electric vehicle is stopped based on the stop charging command, the second requested voltage, the second requested current, the second cell voltage difference between the second cell's highest voltage and the second cell's lowest voltage, the second cell temperature difference between the second cell's highest temperature and the second cell's lowest temperature, and the second insulation resistance of the electric vehicle are acquired in real time. A third charging command is generated when the second voltage difference between the second actual output voltage and the second requested voltage of the charging pile is less than or equal to the first threshold, the second current difference between the second actual output current and the second requested current of the charging pile is less than or equal to the second threshold, the rate of change of the voltage difference between the two individual cells is less than or equal to the third threshold, the rate of change of the temperature difference between the two individual cells is less than or equal to the fourth threshold, and the rate of change of the second insulation resistance is less than or equal to the fifth threshold. Power is supplied to electric vehicles based on the third charging command.

[0085] The second requested voltage, second requested current, second individual cell voltage difference, second individual cell temperature difference, and second insulation resistance are data acquired after charging is stopped according to the stop charging command.

[0086] The second requested voltage is the output voltage that the electric vehicle expects from the charging station during charging after the charging has stopped according to the stop charging command. The second requested current is the output current that the electric vehicle expects from the charging station during charging after the charging has stopped according to the stop charging command.

[0087] The second highest voltage is the voltage of the highest-voltage individual cell in the electric vehicle's battery pack after charging has stopped according to the stop-charging command. The second lowest voltage is the voltage of the lowest-voltage individual cell in the electric vehicle's battery pack after charging has stopped according to the stop-charging command.

[0088] The second highest temperature is the temperature of the hottest individual cell in the electric vehicle's battery pack after charging has stopped according to the charging stop command. The second lowest temperature is the temperature of the coldest individual cell in the electric vehicle's battery pack after charging has stopped according to the charging stop command.

[0089] The second insulation resistance refers to the ability of the electric vehicle's insulation materials or components to prevent leakage current after charging has stopped according to the stop charging command.

[0090] The second requested voltage, second requested current, second individual cell voltage difference, second individual cell temperature difference, and second insulation resistance are continuously acquired. Therefore, the charging pile can obtain the second requested voltage, second requested current, second individual cell voltage difference, second individual cell temperature difference, and second insulation resistance at multiple times. Based on the second individual cell voltage difference at multiple times, the rate of change of the second individual cell voltage difference is calculated; based on the second individual cell temperature difference at multiple times, the rate of change of the second individual cell temperature difference is calculated; and based on the second insulation resistance at multiple times, the rate of change of the second insulation resistance is calculated.

[0091] The third charging command is the command to start charging.

[0092] In this embodiment, by acquiring the electric vehicle's second requested voltage, second requested current, second individual cell voltage difference between the second highest and lowest individual cell voltages, second individual cell temperature difference between the second highest and lowest individual cell temperatures, and second insulation resistance in real time when the power supply to the electric vehicle is stopped based on a stop charging command, a second charging command is generated and power is supplied to the electric vehicle. This is achieved when the second voltage difference between the charging pile's second actual output voltage and the second requested voltage is less than or equal to a first threshold, the second current difference between the charging pile's second actual output current and the second requested current is less than or equal to a second threshold, the rate of change of the two individual cell voltage differences is less than or equal to a third threshold, the rate of change of the second individual cell temperature differences is less than or equal to a fourth threshold, and the rate of change of the second insulation resistance is less than or equal to a fifth threshold.

[0093] In one embodiment, such as Figure 3 As shown, when an electric vehicle begins charging, real-time charging data is transmitted to the AI ​​controller (equipped with edge computing capabilities) within the charging pile. The charging pile first collects and cleans the data, then performs a comprehensive analysis by combining the current real-time charging data, historical charging data, and the first charging control command generated in the cloud. This process achieves millisecond-level response, providing real-time safety monitoring for the electric vehicle. If an anomaly is detected, the cloud sends a fault alarm to the charging pile, enabling timely handling and the issuance of protective notifications. After charging is complete, the charging pile uploads complete charging data (pre-processed data) associated with user and vehicle information to the cloud. The cloud utilizes big data analytics and model training capabilities to perform in-depth analysis of the data, generating a professional battery testing report and sending it back to the charging pile. Finally, the battery testing report is displayed to the user on the charging pile screen. Furthermore, the entire system relies on cloud-based data storage and synchronous upgrades, along with a rapid offline testing system, forming a complete closed loop from real-time monitoring to in-depth inspection, highlighting the fusion of multi-source data and the bidirectional flow of commands between the cloud and the charging pile.

[0094] In one embodiment, such as Figure 4As shown, after the charging gun of the charging pile is inserted into the charging port, the electric vehicle enters a prohibited driving state. When the electric vehicle is in the prohibited driving state, the charging pile detects whether the voltage to ground at point CC1 is within a preset first voltage range, and simultaneously detects whether the resistance value at point CC1 is within a preset resistance range. If the voltage to ground is within the first voltage range or the resistance value at point CC1 is within the preset resistance range (design conditions), the charging pile sends a charger identification message to the electric vehicle so that the electric vehicle can determine the maximum output power of the charging pile connected to it and the communication protocol of the charging pile. After receiving the charger identification message, the electric vehicle automatically detects the voltage value at point CC2. If the voltage value at point CC2 is within a preset second voltage range (design conditions), it is determined that the charging pile and the electric vehicle are successfully connected. The electric vehicle's BMS closes the battery relay, and at the same time, the electric vehicle sends a BMS identification message carrying the vehicle identification code to the charging pile through the charging CAN bus. The AI ​​controller of the charging pile starts to monitor the charging CAN bus in real time and parses the received BMS identification message. The charging pile uploads the vehicle identification number (VIN) to the cloud. Based on historical driving data, battery idle data, and historical charging data associated with the VIN, the cloud uses an AI model to generate a first charging control command for the electric vehicle (EV), which is then sent to the charging pile. When the received first charging control command is indeed the first charging command, the charging pile supplies power to the EV and acquires real-time charging data during this process. The AI ​​model then performs detection based on this data to obtain a result. If the detection result indicates no charging abnormalities, the charging pile repeats the detection process until it receives a stop-charging message from the EV. At this point, it stops supplying power to the EV, sends a stop-charging message to the EV, disconnects the main positive and negative contactors, the BMS disconnects the battery charging relay, and the electronic unlock is activated. The EV is then fully charged. The EV receives a battery detection report from the cloud and sends the charging result back to the charging pile. When the detection result indicates a charging anomaly, the AI ​​controller in the charging pile generates a second charging control command based on real-time charging data. If the second charging control command is a stop charging command, it disconnects the relay (hard-wire disconnect actuator) to stop supplying electrical energy to the electric vehicle. If the second charging control command is a power adjustment command, the charging pile adjusts the charging power through the power module or relay to adjust the electrical energy supplied to the electric vehicle per unit time. If the charging pile has stopped supplying electrical energy to the electric vehicle based on the stop charging command, it will restart charging through the power module or relay if a second charging command is generated. In addition, the human-machine interface can also display battery detection reports or health status.

[0095] In one specific embodiment, a high-performance, multi-core processor is selected as the core of the AI ​​controller, equipped with sufficient RAM and Flash storage to support the local execution of complex AI algorithms. The AI ​​controller is directly designed onto the main control board of the charging pile, and its CAN controller interface is directly connected to the charging CAN bus inside the charging pile to ensure low latency and high reliability of communication with the electric vehicle's BMS. The charging pile is equipped with high-precision voltage, current, and temperature sampling circuits, with accuracy exceeding national standards, providing a high-quality data foundation for AI analysis. An embedded operating system (such as Linux) is built into the intelligent AI controller, and an AI inference framework is deployed.

[0096] The cloud uses frameworks such as PyTorch or TensorFlow to train models, and converts the trained models into a model format that can run efficiently at the edge, while also sending them to the AI ​​controller of the charging pile through a secure channel.

[0097] The AI ​​controller can run multiple parallel tasks, such as BMS message parsing and verification, real-time data sampling, AI model inference, safety decision-making and power control, and data management for communication with the cloud.

[0098] Data aggregation: During daily operation, the vehicle's VIN-001's T-Box continuously uploads historical driving data (such as voltage drop and energy consumption per 100 kilometers under high-speed conditions) and battery idle data during periods of inactivity to the cloud. Simultaneously, the vehicle's charging data is also recorded.

[0099] In-depth cloud analysis: The cloud platform analyzed the entire lifecycle data of VIN-001. Simultaneously, the cloud-deployed AI model discovered that the State of Harmony (SOH) of the battery pack in vehicle VIN-001 had degraded to 78%, with a significant trend of decreasing consistency. The cloud platform determined that the battery pack in vehicle VIN-001 was of "medium-high risk."

[0100] First charging control command and report generation: Two pieces of information are generated in the cloud: a) First charging control command: When SOC>85%, the charging current is limited to 50% of the rated value; b) Service content: A detailed battery test report is generated by combining real-time charging data. The battery test report includes at least the health status, the consistency analysis results of the performance parameters of each individual cell in the battery pack of the electric vehicle, and the performance trend prediction results of each performance parameter of each individual cell over time.

[0101] Issuance and execution: When the vehicle VIN-001 is charging at any charging station, the charging station AI controller loads the vehicle's first charging control command and automatically performs a current reduction operation when the SOC reaches 85%. At the same time, it receives and stores the vehicle's battery detection report.

[0102] Results Display: After charging is complete, users can view the battery test report on the charging station's human-machine interface. The battery test report visually displays the battery's health status in the form of scores, charts, etc. Additionally, if charging is interrupted due to the first charging control command, the human-machine interface will clearly indicate the reason.

[0103] Data Feedback: After the charging process is completed, the intelligent AI controller will send the full data package of this charging session (including the specific time points of executing power adjustment commands, battery voltage / temperature change curves during the charging process, user interaction records of viewing reports, etc.) back to the cloud. This latest field data is incorporated into the VIN-001's full lifecycle database to optimize the AI ​​analysis model and the first charging control command for the next electric vehicle, achieving a complete closed loop from data acquisition to command optimization.

[0104] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0105] Based on the same inventive concept, this application also provides a cloud-edge collaborative electric vehicle intelligent charging safety control system for implementing the cloud-edge collaborative electric vehicle intelligent charging safety control method described above. The solution provided by this system is similar to the implementation scheme described in the above method. Therefore, the specific limitations of one or more embodiments of the cloud-edge collaborative electric vehicle intelligent charging safety control system provided below can be found in the limitations of the cloud-edge collaborative electric vehicle intelligent charging safety control method described above, and will not be repeated here.

[0106] In one embodiment, a cloud-edge collaborative intelligent charging safety control system for electric vehicles is provided, the system comprising: The first instruction generation module is used to receive the vehicle identification code sent by the electric vehicle via the charging CAN bus, and upload the vehicle identification code to the cloud, so that the cloud can use an AI model to perform a risk assessment based on the historical driving data, battery static data and historical charging data associated with the vehicle identification code, generate a first charging control instruction for the electric vehicle, and send the first charging control instruction to the charging pile. A power transmission module is used to transmit power to the electric vehicle when the first charging control command received is a first charging command; The detection module is used to acquire real-time charging data of the electric vehicle through the AI ​​controller during the transmission of electrical energy, and to perform detection based on the real-time charging data through the AI ​​model deployed in the AI ​​controller to obtain the detection result; The second instruction generation module is used to repeat the detection when the detection result indicates that there is no abnormality in charging, until a stop charging message is received from the electric vehicle, and to stop the supply of power to the electric vehicle; when the detection result indicates that there is an abnormality in charging, the AI ​​controller is used to generate a second charging control instruction based on the detection result. The charging control module is used to disconnect the relay to stop supplying electrical energy to the electric vehicle when the second charging control command is a stop charging command; and to adjust the charging power of the charging pile based on the power adjustment command when the second charging control command is a power adjustment command.

[0107] The modules in the aforementioned cloud-edge collaborative intelligent charging safety control system for electric vehicles can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the computer device's memory as software, so that the processor can call and execute the corresponding operations of each module.

[0108] In one embodiment, a computer device is also provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above method embodiments.

[0109] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon that, when executed by a processor, implements the steps in the above method embodiments.

[0110] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above method embodiments.

[0111] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties.

[0112] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments described above. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0113] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0114] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A cloud-edge collaboration-based intelligent charging safety control method for electric vehicles, characterized in that, The method includes: S1. Receive the vehicle identification code sent by the electric vehicle via the charging CAN bus, and upload the vehicle identification code to the cloud, so that the cloud can perform risk assessment based on the historical driving data, battery static data and historical charging data associated with the vehicle identification code through an AI model, generate a first charging control command for the electric vehicle, and send the first charging control command to the charging pile. S2. When the first charging control command received is a first charging command, power is supplied to the electric vehicle; S3. During the transmission of electrical energy, the real-time charging data of the electric vehicle is acquired through the AI ​​controller, and the AI ​​model deployed in the AI ​​controller performs detection based on the real-time charging data to obtain the detection result; S4. When the detection result indicates that there is no abnormality in charging, repeat S3 until a stop charging message is received from the electric vehicle, and stop supplying power to the electric vehicle; when the detection result indicates that there is an abnormality in charging, use the AI ​​controller to generate a second charging control command based on the detection result; S5. When the second charging control command is a stop charging command, disconnect the relay to stop supplying electrical energy to the electric vehicle; when the second charging control command is a power adjustment command, adjust the charging power of the charging pile based on the power adjustment command.

2. The method of claim 1, wherein, The method further includes: The real-time charging data is preprocessed to obtain preprocessed data; The preprocessed data is sent to the cloud so that the AI ​​model in the cloud can perform a battery risk assessment based on the preprocessed data, the historical driving data uploaded by the electric vehicle, and the battery static data, and obtain a battery test report for the electric vehicle. The battery test report or the health status in the battery test report is then sent to the charging pile.

3. The method of claim 2, wherein, The charging pile includes a human-machine interface, and the method further includes: During the process of supplying electrical energy to the electric vehicle and / or when the supply of electrical energy to the electric vehicle is stopped, the battery detection report or the health status is displayed through the human-machine interface; the battery detection report includes at least the health status, the consistency analysis results of the performance parameters of each individual cell in the battery pack of the electric vehicle, and the performance trend prediction results of each performance parameter of each individual cell over time.

4. The method of claim 1, wherein, The method further includes: The real-time charging data is uploaded to the cloud so that the cloud can train the AI ​​model based on the real-time charging data, and then send the trained AI model to the AI ​​controller of the charging pile.

5. The method of claim 1, wherein, Step S4 includes: During the process of transmitting electrical energy to the electric vehicle, the following data are acquired: first requested voltage, first requested current, first single-cell voltage difference between the highest and lowest single-cell voltages, first single-cell temperature difference between the highest and lowest single-cell temperatures, first insulation resistance, internal resistance of each single cell in the battery pack, state of charge of each single cell, health status of each single cell, historical charge / discharge cycles, historical anomaly records, and battery pack temperature. Calculate the first voltage difference between the first actual output voltage of the charging pile and the first requested voltage; calculate the first current difference between the first actual output current of the charging pile and the first requested current; determine the temperature rise rate of the battery pack based on the battery pack temperature; determine the internal resistance dispersion based on the internal resistance of each individual cell; determine the battery state of charge deviation between the maximum and minimum battery state of charge based on the battery state of charge of each individual cell. The rate of change of the first cell voltage difference, the rate of change of the first cell temperature difference, the first voltage difference, the first current difference, the temperature rise rate, the internal resistance dispersion, the historical anomaly records, each of the health states, the historical charge-discharge cycles, the rate of change of the first insulation resistance, and the battery state of charge deviation are input into the AI ​​model deployed in the AI ​​controller for risk assessment to obtain the risk level. Based on the risk level, a second charging control command is generated.

6. The method of claim 5, wherein, The generation of a second charging control command based on the risk level includes: When the risk level is a first preset level, a second charging command is generated to continue supplying electrical energy to the electric vehicle based on the second charging command; When the risk level is the third preset level, a power adjustment command is generated to adjust the charging power of the charging pile based on the power adjustment command; When the risk level is the third preset level, a stop charging command is generated to stop the supply of electrical energy to the electric vehicle based on the stop charging command; the danger level of the first preset level is lower than that of the second preset level, and the danger level of the second preset level is lower than that of the third preset level.

7. A cloud-edge collaboration based intelligent electric vehicle charging safety control system for performing the method of any one of claims 1-6, characterized in that, The system includes: The first instruction generation module is used to receive the vehicle identification code sent by the electric vehicle via the charging CAN bus, and upload the vehicle identification code to the cloud, so that the cloud can use an AI model to perform a risk assessment based on the historical driving data, battery static data and historical charging data associated with the vehicle identification code, generate a first charging control instruction for the electric vehicle, and send the first charging control instruction to the charging pile. A power transmission module is used to transmit power to the electric vehicle when the first charging control command received is a first charging command; The detection module is used to acquire real-time charging data of the electric vehicle through the AI ​​controller during the transmission of electrical energy, and to perform detection based on the real-time charging data through the AI ​​model deployed in the AI ​​controller to obtain the detection result; The second instruction generation module is used to repeat the detection when the detection result indicates that there is no abnormality in charging, until a stop charging message is received from the electric vehicle, and to stop the supply of power to the electric vehicle; when the detection result indicates that there is an abnormality in charging, the AI ​​controller is used to generate a second charging control instruction based on the detection result. The charging control module is used to disconnect the relay to stop supplying electrical energy to the electric vehicle when the second charging control command is a stop charging command; and to adjust the charging power of the charging pile based on the power adjustment command when the second charging control command is a power adjustment command.

8. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, It stores a computer program that, when executed by a processor, implements the steps of the method according to any one of claims 1 to 6.

Images