Car charging safety system and charging method based on big data and algorithm model

Abstract

The application provides a car charging safety system and a charging method based on big data and an algorithm model, which comprises a charging pile and a user end; the charging pile is used for identifying a risk device before charging a to-be-charged device when the to-be-charged device is connected, monitoring an exception in real time during the charging process, and evaluating a comprehensive charging safety index when the charging is normally completed; the user end is used for recommending a charging pile, detecting a battery health, giving a risk warning, and giving a charging safety guidance based on a charging habit of a user and information of a to-be-charged vehicle; and the problems that the prior art is limited to the interaction of hardware, provides a single safety monitoring service, and lacks a systematic safety management service are solved.

Description

Technical Field

[0001] This invention relates to the field of system design architecture, and more specifically to a vehicle charging safety system and charging method based on big data and algorithm models. Background Technology

[0002] During the charging process of electric vehicles, factors such as temperature management, battery aging, and overcharging can jeopardize the lifespan of the power battery and even cause charging safety accidents. Based on currently available information, the main methods used by industry and academia to address these issues include:

[0003] 1. Calculate the capacity retention rate by analyzing the changes in SOC (State of Charge) during the charging process. Then, based on historical charging data, use a sequence model to calculate the RUL (Relative Lifetime) of the power battery.

[0004] 2. Guide users to set a full charge SOC (remaining battery capacity) threshold to reduce the number of times the battery is fully charged or overcharged;

[0005] 3. During the charging process, the temperature rise of individual battery cells is monitored in real time, and the charging power is flexibly controlled according to the temperature.

[0006] The above solutions assess risks based on rules, relying solely on data exchanged between hardware components. They provide single-use security monitoring services but lack systematic security management services. Summary of the Invention

[0007] To address the shortcomings of existing solutions that rely on rules to assess risk, with their core basis limited to data exchanged between hardware devices, providing only one-time safety monitoring services and lacking systematic safety management services, this invention provides a vehicle charging safety system based on big data and algorithm models, including: charging piles and user terminals;

[0008] The charging pile is used to identify risky devices before charging when the device to be charged is connected, monitor abnormalities in real time during charging, and evaluate the comprehensive charging safety index when charging ends normally.

[0009] The user terminal is used to recommend charging stations, perform battery health checks, issue risk warnings, and provide charging safety guidance based on the user's charging habits and the information of the vehicle to be charged.

[0010] Preferably, the charging pile includes:

[0011] The risk detection module is used to perform risk assessment and prediction on the device to be charged when it is connected, and to actively terminate high-risk devices, while sending alarm information to the user terminal.

[0012] The monitoring module is used to detect abnormalities in the device being charged during the charging process. When an abnormality occurs, it will actively cut off the power and activate an automatic alarm mechanism.

[0013] The safety index assessment module is used to comprehensively evaluate battery health, battery safety, and battery value by combining charging process data when the device to be charged finishes charging normally.

[0014] Preferably, the risk detection module is specifically used for:

[0015] When a device to be charged is connected, the model and vehicle condition information of the device to be charged are obtained, and it is determined whether the device is a high-risk device based on the model and vehicle condition information of the device to be charged.

[0016] When a device is detected as high-risk, it will automatically cut off the power and activate the automatic alarm and fire suppression mechanism in extreme situations, while also reminding the user to send an alarm message.

[0017] The extreme situations mentioned include: the charging gun overheating and the equipment catching fire.

[0018] Preferably, the user terminal includes:

[0019] The settings module is used to set the user's charging habits and charging plans, and transmit the charging habits and charging plans to the security module;

[0020] The safety module is used to recommend charging stations, perform battery health checks, issue risk warnings, and provide charging safety guidance for the vehicle to be charged based on the information of the device to be charged, the charging habits, and the charging plan.

[0021] Preferably, the security module is specifically used for:

[0022] Based on the power information, location information, charging habits, and charging plan of the device to be charged, the charging route of the vehicle to be charged is planned, and charging stations are recommended;

[0023] Based on charging data from historical charging processes, the battery health status is predicted using a pre-built battery degradation model and an internal resistance model. The battery health status is then assessed based on the degradation prediction and internal resistance prediction structures, and a risk warning is determined based on the assessment results.

[0024] The battery degradation model is constructed by analyzing the capacity change data during the historical charging and discharging of the battery using an algorithm.

[0025] The internal resistance model is constructed by analyzing historical charging current, voltage, and temperature variation data using an algorithm.

[0026] Preferably, the algorithm includes: Kalman filtering, Fourier transform, multivariate regression, or recurrent neural network.

[0027] Preferably, the system further includes: a merchant terminal, used to obtain charging data and information of the device to be charged from the charging pile, and to obtain charging habits and battery health status assessment results of the vehicle to be charged from the user terminal.

[0028] Furthermore, this invention also provides a method for safe charging of automobiles based on big data and algorithm models, including:

[0029] When a device is connected to a charging station, the charging station identifies potential risks before charging, monitors anomalies in real time during charging, and evaluates the overall charging safety index when charging is completed normally.

[0030] Based on user charging habits and information about vehicles to be charged, the system recommends charging stations, performs battery health checks, issues risk warnings, and provides charging safety guidance.

[0031] Preferably, the method of using a charging pile to identify potential risks before charging the device is connected, to monitor anomalies in real time during charging, and to evaluate the comprehensive charging safety index when charging is completed normally, includes:

[0032] When a charging pile's risk detection module is connected, it performs a risk assessment and prediction on the device to be charged, proactively terminates high-risk devices, and sends alarm information to the user's end.

[0033] The charging pile's monitoring module detects abnormalities in the charging equipment during the charging process. When an abnormality is detected, the power is automatically cut off and an automatic alarm mechanism is activated.

[0034] The charging pile's safety index assessment module comprehensively evaluates battery health, battery safety, and battery value by combining charging process data when the device to be charged finishes charging normally.

[0035] Preferably, the step of using the user terminal to recommend charging stations, perform battery health checks, issue risk warnings, and provide charging safety guidance based on the user's charging habits and the information of the vehicle to be charged includes:

[0036] The user's charging habits and charging plans are set using the user terminal's settings module, and then transmitted to the security module.

[0037] The user-side security module uses information about the device to be charged, the user's charging habits, and the charging plan to recommend charging stations, perform battery health checks, issue risk warnings, and provide charging safety guidance.

[0038] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0039] The present invention provides a vehicle charging safety system based on big data and algorithm models, comprising a charging pile and a user terminal. The charging pile is used to identify potential risks to the device before charging when it is connected, monitor anomalies in real time during charging, and evaluate the comprehensive charging safety index when charging is completed normally. The user terminal is used to recommend charging piles, perform battery health checks, provide risk warnings, and offer charging safety guidance based on the user's charging habits and the information of the vehicle to be charged. This solves the problem that existing technologies are limited to data exchange between hardware, providing only single-time safety monitoring services and lacking systematic safety management services. Attached Figure Description

[0040] Figure 1 This is a diagram of the automotive charging safety system architecture based on big data and algorithm models of the present invention.

[0041] Figure 2 This is a flowchart of the charging safety system of the present invention. Detailed Implementation

[0042] This invention discloses a vehicle charging safety system based on big data and algorithm models, aiming to provide a safety management system with data and algorithms at its core. Through a three-layer framework of data algorithm layer, service layer, and application layer, it provides more accurate, stable, and comprehensive charging safety protection.

[0043] Example 1: A car charging safety system based on big data and algorithm models, such as Figure 1 As shown, it includes: charging piles and user terminals;

[0044] The charging pile is used to identify risky devices before charging when the device to be charged is connected, monitor abnormalities in real time during charging, and evaluate the comprehensive charging safety index when charging ends normally.

[0045] The user terminal is used to recommend charging stations, perform battery health checks, issue risk warnings, and provide charging safety guidance based on the user's charging habits and the information of the vehicle to be charged.

[0046] Preferably, the charging pile includes:

[0047] The risk detection module is used to perform risk assessment and prediction on the device to be charged when it is connected, and to actively terminate high-risk devices, while sending alarm information to the user terminal.

[0048] The monitoring module is used to detect abnormalities in the device being charged during the charging process. When an abnormality occurs, it will actively cut off the power and activate an automatic alarm mechanism.

[0049] The safety index assessment module is used to comprehensively evaluate battery health, battery safety, and battery value by combining charging process data when the device to be charged finishes charging normally.

[0050] Preferably, the risk detection module is specifically used for:

[0051] When a device to be charged is connected, the model and vehicle condition information of the device to be charged are obtained, and it is determined whether the device is a high-risk device based on the model and vehicle condition information of the device to be charged.

[0052] When a device is detected as high-risk, it will automatically cut off the power and activate the automatic alarm and fire suppression mechanism in extreme situations, while also reminding the user to send an alarm message.

[0053] The extreme situations mentioned include: the charging gun overheating and the equipment catching fire.

[0054] Preferably, the user terminal includes:

[0055] The settings module is used to set the user's charging habits and charging plans, and transmit the charging habits and charging plans to the security module;

[0056] The safety module is used to recommend charging stations, perform battery health checks, issue risk warnings, and provide charging safety guidance for the vehicle to be charged based on the information of the device to be charged, the charging habits, and the charging plan.

[0057] Preferably, the security module is specifically used for:

[0058] Based on the power information, location information, charging habits, and charging plan of the device to be charged, the charging route of the vehicle to be charged is planned, and charging stations are recommended;

[0059] Based on charging data from historical charging processes, the battery health status is predicted using a pre-built battery degradation model and an internal resistance model. The battery health status is then assessed based on the degradation prediction and internal resistance prediction structures, and a risk warning is determined based on the assessment results.

[0060] The battery degradation model is based on the capacity change data during the historical charging and discharging of the battery. It is constructed and optimized using an algorithm model to obtain battery degradation prediction.

[0061] The internal resistance model is constructed and optimized using an algorithm model based on historical charging current, voltage, and temperature change data to obtain battery internal resistance prediction.

[0062] Preferably, the algorithm includes: Kalman filtering, Fourier transform, multivariate regression, or recurrent neural network.

[0063] Preferably, the system further includes: a merchant terminal, used to obtain charging data and information of the device to be charged from the charging pile, and to obtain charging habits and battery health status assessment results of the vehicle to be charged from the user terminal.

[0064] The above describes the invention from the perspective of the implementing entities: charging piles, user terminals, and merchant terminals. Below, we will provide a detailed introduction to the system's architecture:

[0065] This invention employs a combination of software, hardware, and AI algorithms to construct a smart vehicle-charging pile data-driven, full-platform battery risk assessment, early warning, and management detection system. From an overall architectural perspective, this invention comprises a service layer and an application layer, from bottom to top, such as... Figure 1 As shown.

[0066] Service Layer: Responsible for external data access, data layer model deployment, and application layer service support. Furthermore, it ensures stability through edge control, microservices, transaction control, and caching technologies. It possesses open charging safety service capabilities, connecting people, devices, data, and models to achieve charging safety and full battery lifecycle management. It also performs battery degradation prediction using a battery degradation model, internal resistance prediction using an internal resistance model, risk assessment prediction using a risk assessment model, and vehicle-charging station matching recommendation using a vehicle-charging station matching model.

[0067] Application Layer: Based on the capabilities of the platform and data layers, it enables multi-level connectivity among charging piles, users, vehicles, and services, creating a multi-dimensional charging safety service system and achieving comprehensive protection for users and charging infrastructure, such as... Figure 2 As shown:

[0068] The process of charging mainly includes awareness, preparation, and prevention. The following is a detailed introduction to each part:

[0069] "Cognition" refers to the matching analysis of the vehicle and charging station before charging, and recommending charging stations with high compatibility. Here, compatibility is analyzed based on the vehicle's location, remaining battery power, and user's travel plans to recommend charging stations that are more suitable for the user.

[0070] The process of identifying risky devices / vehicles before charging after the user plugs in the charging gun refers to analyzing the information of the connected vehicle and the charging pile to determine whether there are any vehicles that exceed the standard or have been illegally modified. Vehicles that exceed the standard or have been illegally modified are considered high-risk vehicles. The process also analyzes whether there are any issues with the charging pile equipment, such as leakage or overheating. If any of these issues are found, the charging pile equipment is also considered high-risk equipment. The high-risk equipment or vehicle is then proactively terminated, and the user is notified.

[0071] During the charging process, a vehicle / equipment abnormality warning mechanism is monitored in real time. If an abnormality occurs, the power will be automatically cut off. In extreme cases, an automatic alarm and automatic fire extinguishing mechanism will be activated. Here, extreme cases refer to high-risk situations such as excessively high charging gun temperature or equipment fire.

[0072] Once charging is complete and the charging process ends normally, the battery health / safety / value assessment model will combine charging process data to evaluate a comprehensive charging safety index, summarize and evaluate charging behavior, and positively guide standardized charging practices. Furthermore, integrated with product design, features such as charging plan reminders, charging safety lessons, charging safety guidelines, and emergency assistance are included to provide users with more intuitive operation guidance, reduce operational difficulty, and enhance the user experience.

[0073] The system implements high-risk pile monitoring, thermal runaway early warning, emergency power outage control, and automatic alarm mechanisms on the pile side; it provides vehicle-pile matching recommendations, battery health detection, high-risk early warning, and charging safety guidance on the user side; and it integrates vehicle charging data, battery status data, and open data into the data layer on the merchant side.

[0074] The overall architecture of this invention also includes a data layer;

[0075] Data Layer: Composed of big data clusters, offline / online computing tools, and AI intelligent algorithms, it uses distributed computing capabilities to construct charging safety indicators and create early warning models. Simultaneously, the model continuously learns and improves through updates to historical data.

[0076] The data integrates charging voltage, charging current, charging temperature, charging frequency, charging alarms, and other data. It uses algorithms such as Kalman filtering, Fourier transform, multiple regression, and recurrent neural networks to process data features and build algorithm models, including thermal runaway early warning models, SOH (state of health of the battery) early warning models, battery degradation models, internal resistance models, risk assessment models, and vehicle-charging station matching models.

[0077] Compared with current multi-system charging safety technologies, this invention has the advantages of systematicity, flexibility, personalization, and self-learning capabilities. The service content is not only safety monitoring for a single charge, but also establishes a charging health record for each charging vehicle, realizing differentiated and personalized charging safety management services for different vehicles, and understanding the safety status of electric vehicles better than the users.

[0078] Example 2

[0079] Based on the same inventive concept, this invention also provides a method for safe charging of automobiles based on big data and algorithm models, including:

[0080] When a device is connected to a charging station, the charging station identifies potential risks before charging, monitors anomalies in real time during charging, and evaluates the overall charging safety index when charging is completed normally.

[0081] Based on user charging habits and information about vehicles to be charged, the system recommends charging stations, performs battery health checks, issues risk warnings, and provides charging safety guidance.

[0082] Furthermore, the method of using a charging pile to identify potential risks before charging a device is connected, to monitor anomalies in real time during charging, and to evaluate the comprehensive charging safety index when charging is completed normally, including:

[0083] When a charging pile's risk detection module is connected, it performs a risk assessment and prediction on the device to be charged, proactively terminates high-risk devices, and sends alarm information to the user's end.

[0084] The charging pile's monitoring module detects abnormalities in the charging equipment during the charging process. When an abnormality is detected, the power is automatically cut off and an automatic alarm mechanism is activated.

[0085] The charging pile's safety index assessment module comprehensively evaluates battery health, battery safety, and battery value by combining charging process data when the device to be charged finishes charging normally.

[0086] Furthermore, the risk detection module of the charging pile performs a risk assessment and prediction on the device to be charged when it is connected, and actively terminates high-risk devices, while sending alarm information to the user terminal, including:

[0087] When a device to be charged is connected, the model and vehicle condition information of the device to be charged are obtained, and it is determined whether the device is a high-risk device based on the model and vehicle condition information of the device to be charged.

[0088] When a device is detected as high-risk, it will automatically cut off the power and activate the automatic alarm and fire suppression mechanism in extreme situations, while also reminding the user to send an alarm message.

[0089] The extreme situations mentioned include: the charging pile overheating or the charging equipment catching fire.

[0090] Furthermore, the method of utilizing the user's charging habits and information about the vehicle to be charged to recommend charging stations, perform battery health checks, issue risk warnings, and provide charging safety guidance includes:

[0091] The user's charging habits and charging plans are set using the user terminal's settings module, and then transmitted to the security module.

[0092] The user-side security module uses information about the device to be charged, the user's charging habits, and the charging plan to recommend charging stations, perform battery health checks, issue risk warnings, and provide charging safety guidance.

[0093] Furthermore, the user-side security module utilizes information about the device to be charged, the stated charging habits, and the charging plan to recommend charging stations, perform battery health checks, issue risk warnings, and provide charging safety guidance, including:

[0094] Based on the power information, location information, charging habits, and charging plan of the device to be charged, the charging route of the vehicle to be charged is planned, and charging stations are recommended;

[0095] Based on charging data from historical charging processes, the battery health status is predicted using a pre-built battery degradation model and an internal resistance model. The battery health status is then assessed based on the degradation prediction and internal resistance prediction structures, and a risk warning is determined based on the assessment results.

[0096] The battery degradation model is constructed by analyzing the capacity change data during the historical charging and discharging of the battery using an algorithm.

[0097] The internal resistance model is constructed by analyzing historical charging current, voltage, and temperature variation data using an algorithm.

[0098] Algorithms include: Kalman filtering, Fourier transform, multivariate regression, or recurrent neural networks.

[0099] The safe charging method for automobiles based on big data and algorithm models also includes:

[0100] The merchant terminal obtains charging data and information of the devices to be charged from the charging pile, and obtains charging habits and battery health status assessment results of the vehicles to be charged from the user terminal.

[0101] Both the battery degradation model and the internal resistance model are constructed by combining historical charging data and vehicle data obtained from the merchant's end with algorithms.

[0102] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0103] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0104] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0105] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0106] The above are merely embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention are included within the scope of the claims of the present invention pending approval.

Claims

1. A vehicle charging safety system based on big data and algorithm models, characterized in that, include: Charging stations and user terminals; The charging pile is used to identify risky devices before charging when the device to be charged is connected, monitor abnormalities in real time during charging, and evaluate the comprehensive charging safety index when charging ends normally. The user terminal is used to recommend charging stations, perform battery health checks, issue risk warnings, and provide charging safety guidance based on the user's charging habits and the information of the vehicle to be charged. The charging pile includes: The risk detection module is used to perform risk assessment and prediction on the device to be charged when it is connected, and to actively terminate high-risk devices, while sending alarm information to the user terminal. The monitoring module is used to detect abnormalities in the device being charged during the charging process. When an abnormality occurs, it will actively cut off the power and activate an automatic alarm mechanism. The safety index assessment module is used to comprehensively assess battery health, battery safety, and battery value by combining charging process data when the device to be charged finishes charging normally. The risk detection module is specifically used for: When a device to be charged is connected, the model and vehicle condition information of the device to be charged are obtained, and it is determined whether the device is a high-risk device based on the model and vehicle condition information of the device to be charged. When a device is detected as high-risk, it will automatically cut off the power and activate the automatic alarm and fire suppression mechanism in extreme situations, while also reminding the user to send an alarm message. The extreme situations mentioned include: the charging gun overheating or the charging equipment catching fire. The user terminal includes: The settings module is used to set the user's charging habits and charging plans, and transmit the charging habits and charging plans to the security module; The safety module is used to recommend charging stations, perform battery health checks, issue risk warnings, and provide charging safety guidance for the vehicle to be charged based on the information of the device to be charged, the charging habits, and the charging plan. The security module is specifically used for: Based on the power information, location information, charging habits, and charging plan of the device to be charged, the charging route of the vehicle to be charged is planned, and charging stations are recommended; Based on charging data from historical charging processes, the battery health status is predicted using a pre-built battery degradation model and an internal resistance model. The battery health status is then assessed based on the degradation prediction and internal resistance prediction structures, and a risk warning is determined based on the assessment results. The battery degradation model is constructed by analyzing the capacity change data during the historical charging and discharging of the battery using an algorithm. The internal resistance model is constructed by analyzing historical charging current, voltage, and temperature variation data using an algorithm.

2. The system as described in claim 1, characterized in that, The algorithms include: Kalman filtering, Fourier transform, multivariate regression, or recurrent neural networks.

3. The system as described in claim 1, characterized in that, The system also includes: a merchant terminal, used to obtain charging data and information of the devices to be charged from the charging pile, and to obtain charging habits and battery health status assessment results of the vehicles to be charged from the user terminal.

4. A charging method for a vehicle safety charging system based on big data and algorithm models as described in any one of claims 1-3, characterized in that, include: When a device is connected to a charging station, the charging station identifies potential risks before charging, monitors anomalies in real time during charging, and evaluates the overall charging safety index when charging is completed normally. Based on user charging habits and information about vehicles to be charged, the system recommends charging stations, performs battery health checks, issues risk warnings, and provides charging safety guidance.

5. The method as described in claim 4, characterized in that, The process of using a charging pile to identify potential risks before charging a device is connected, monitor anomalies in real time during charging, and evaluate the overall charging safety index when charging is completed normally, including: When a charging pile's risk detection module is connected, it performs a risk assessment and prediction on the device to be charged, proactively terminates high-risk devices, and sends alarm information to the user's end. The charging pile's monitoring module detects abnormalities in the charging equipment during the charging process. When an abnormality is detected, the power is automatically cut off and an automatic alarm mechanism is activated. The charging pile's safety index assessment module comprehensively evaluates battery health, battery safety, and battery value by combining charging process data when the device to be charged finishes charging normally.

6. The method as described in claim 4, characterized in that, The method utilizes the user's charging habits and vehicle information to recommend charging stations, perform battery health checks, issue risk warnings, and provide charging safety guidance, including: The user's charging habits and charging plans are set using the user terminal's settings module, and then transmitted to the security module. The user-side security module uses information about the device to be charged, the user's charging habits, and the charging plan to recommend charging stations, perform battery health checks, issue risk warnings, and provide charging safety guidance.

Images