Electric vehicle charging safety online evaluation method and system based on big data

Abstract

The invention discloses an electric vehicle charging safety online evaluation method and system based on big data, and relates to the field of charging safety, and the method comprises the steps: obtaining the fixed parameter information of a battery, and building a multi-type battery fixed parameter data set; analyzing the influence of the charging cycle number on the battery life, and establishing a battery cycle life loss coefficient; analyzing the influence of different charging modes on the battery life in a fixed environment, and establishing a mode influence battery life loss coefficient; analyzing the influence of different environmental factors on the battery life, and establishing an environmental influence battery life loss coefficient; establishing a charging safety evaluation model, and online judging whether the charging of the electric vehicle is safe or not; historical charging information and environment information of the battery are obtained, a man-machine interaction platform is established, and charging information of the electric vehicle is monitored on line. The method has the advantages that the service life of the battery of the electric vehicle and the change of fixed parameters are effectively and comprehensively evaluated, and the accuracy and reliability of battery charging safety monitoring are improved.

Description

Technical Field

[0001] The present invention relates to the field of charging safety, and in particular to an online evaluation method and system for charging safety of electric vehicles based on big data. Background Art

[0002] With the rapid development of new energy vehicles, they are strongly supported by the country and society. Electric vehicles are an important part of new energy vehicles, and the most important part of electric vehicles is to ensure the normal operation of batteries. Therefore, ensuring the safety of electric vehicle charging is an important basis for protecting the safety of users' lives, property and social security. With the development of big data technology, using a large amount of data in big data to analyze the battery life loss of electric vehicle batteries during the charging process and the changes in fixed standard parameters is of great significance to the analysis of electric vehicle charging safety. Since electric vehicles are affected by many factors during the charging process, and these influences on the battery life are mostly irreversible, with the increase in the number of charging times, the battery life and fixed standard parameters will change, resulting in deviations between the actual parameter information of the battery and the fixed standard parameter information. Therefore, focusing on analyzing the impact of different influencing factors on battery life and fixed standard parameters is of great significance to improving the safety of electric vehicle charging safety assessment.

[0003] The existing technology has some deficiencies in the specific level of analysis of electric vehicle charging safety, and the analysis of factors affecting electric vehicle battery charging is not comprehensive enough. For example, Chinese patent CN114397577A discloses "a new energy vehicle lithium battery health status assessment method based on ASTUKF-GRA-LSTM model". This assessment method is a method that uses adaptive Kalman filtering to enhance the historical data of lithium battery charging, uses gray correlation analysis to achieve accurate extraction of health performance indicators, and combines with LSTM neural network to obtain historical data of new energy electric vehicles based on the comprehensive energy service platform to achieve accurate assessment of lithium battery SOH. However, this assessment method is not comprehensive enough in the analysis of the historical charging of electric vehicle batteries, lacks analysis of specific influencing factors, and easily leads to inaccurate assessment of electric vehicle charging safety, thereby causing electric vehicle charging safety and resulting in loss of life and property of users. Summary of the invention

[0004] In order to solve the above technical problems, a method and system for online evaluation of electric vehicle charging safety based on big data are provided. This technical solution solves the problem that the existing technology proposed in the above background technology has some shortcomings in the analysis of the specific level of electric vehicle charging safety, the analysis of factors affecting electric vehicle battery charging is not comprehensive enough, and there is a lack of analysis of specific influencing factors, which can easily lead to inaccurate evaluation of electric vehicle charging safety, thereby causing problems with electric vehicle charging safety and resulting in loss of life and property of users.

[0005] In order to achieve the above purpose, the technical solution adopted by the present invention is:

[0006] An online evaluation method for electric vehicle charging safety based on big data, characterized by comprising:

[0007] According to the battery model and product information, obtain the fixed parameter information of the battery and establish a fixed parameter data set for multiple types of batteries;

[0008] Based on the fixed parameter data sets of multiple types of batteries, the impact of charging cycles on battery life is analyzed, and the battery cycle life loss coefficient is established;

[0009] Use simulation software to analyze the impact of different charging methods on battery life under fixed conditions, and establish the impact of different charging methods on battery life loss coefficient;

[0010] Analyze the impact of different environmental factors on battery life and establish the environmental impact battery life loss coefficient;

[0011] According to the battery cycle life loss coefficient, the battery life loss coefficient affected by the mode and the battery life loss coefficient affected by the environment, a charging safety assessment model is established to determine online whether the charging of electric vehicles is safe;

[0012] By using Internet of Things technology, the battery charging history information and environmental information are obtained through multiple sets of sensors. According to the charging safety assessment model, a human-computer interaction platform is established to monitor the charging information of electric vehicles online.

[0013] Preferably, the obtaining of fixed parameter information of the battery according to the battery model and product information, and establishing a fixed parameter data set of multiple types of batteries specifically includes:

[0014] Based on big data, obtain fixed parameter information of different types of batteries according to the existing electric vehicle battery models and product information on the market;

[0015] Classify and organize the fixed parameter information of different types of batteries, and establish a fixed parameter information set for multiple types of batteries;

[0016] Quantify and standardize the data in the fixed parameter information set of multiple types of batteries and establish a fixed parameter data set for multiple types of batteries;

[0017] Among them, the fixed parameter data sets of multiple types of batteries include: voltage, battery capacity, cold start current, maximum output current, rated capacity, self-discharge rate, energy density, power density and charging rate.

[0018] Preferably, analyzing the influence of the number of charging cycles on the battery life according to the fixed parameter data sets of multiple types of batteries and establishing the battery cycle life loss coefficient specifically includes:

[0019] Using simulation software and test experiments, the parameter changes of multiple types of battery fixed parameter data sets during battery cycle charging are obtained under fixed environment and charging mode.

[0020] According to the changes of parameters, the loss coefficient of each parameter under cyclic charging is calculated respectively;

[0021] According to the loss coefficient of each parameter under cyclic charging, a battery cycle life loss coefficient and a battery cycle life loss coefficient matrix are established;

[0022] The loss coefficient expressions of the parameters under cyclic charging are as follows:

[0023] ,

[0024] In the formula, is the loss coefficient of each parameter under cyclic charging, is the parameter loss factor under cycle charging, is a constant, is the functional relationship between the number of battery charging cycles and the parameter loss value, For the The parameter loss value of the charge cycle is For the Parameter monitoring data of the sub-cycle, These are standard fixed parameter values ​​when the battery is produced.

[0025] Preferably, the use of simulation software to analyze the impact of different charging methods on battery life under a fixed environment and establish the impact of charging methods on battery life loss coefficient specifically includes:

[0026] Using simulation software and test experiments, different charging methods are adopted under fixed environment to obtain the parameter changes in the fixed parameter data set of multiple types of batteries after charging is completed;

[0027] Among them, different charging methods include: fast charging, slow charging, normal charging, overcharging, disconnected charging, and power loss;

[0028] According to the parameter changes, the loss coefficient of each parameter under different charging modes is calculated;

[0029] According to the loss coefficients of various parameters under different charging modes, a matrix of loss coefficients of battery life affected by charging mode and loss coefficients of battery life affected by charging mode is established;

[0030] Using fixed parameter data sets of multiple types of batteries, the battery charging method is determined based on the charging time, charging rate, voltage stability and battery capacity of electric vehicle batteries;

[0031] The loss coefficient expressions of the parameters under different charging modes are as follows:

[0032] ,

[0033] In the formula, is the loss coefficient of each parameter under different charging modes, is the parameter loss factor under different charging modes, is the number of different charging methods, For the The weight of each charging mode, For the The number of occurrences under each charging mode, For the Charging mode The monitoring values ​​of each parameter are For the The average value of each parameter monitoring value under each charging mode;

[0034] The battery charging mode determination method is specifically as follows:

[0035] According to the fixed parameter data set of multiple types of batteries, the standard voltage value range and threshold value when the battery is fully charged are set;

[0036] According to the fixed parameter data set of multiple types of batteries, set the current value change range and threshold during the charging process of the battery;

[0037] According to the fixed parameter data set of multiple types of batteries, set the charging time, charging rate range, and set the highest and lowest thresholds;

[0038] Determine whether the battery voltage exceeds the standard voltage value threshold. If so, it means that the battery is overcharged. If not, determine whether the voltage during power failure is within the standard voltage value range. If so, it means that the battery is charged normally. If not, it means that the battery is low on power.

[0039] Determine whether the battery charging time and charging rate exceed the maximum threshold. If so, it means that the battery uses fast charging. If not, determine whether the battery charging time and charging rate are lower than the minimum threshold. If so, it means that the battery uses slow charging. If not, it means that the battery uses normal charging.

[0040] It is determined whether the battery current value exceeds the threshold value multiple times during the charging process, or even the current value is 0. If so, it indicates that the battery charging is interrupted. If not, it indicates that the battery is not interrupted.

[0041] Preferably, analyzing the impact of different environmental factors on battery life and establishing the environmental impact battery life loss coefficient specifically includes:

[0042] Using simulation software and test experiments, different environmental data are set, and the changes of fixed parameter data of multiple types of batteries under different environmental factors are obtained through the control variable method;

[0043] Filter and standardize the parameter change data, and establish a parameter loss training set;

[0044] According to different environmental types, a linear regression equation of parameter loss under different environmental factors is established;

[0045] Based on the traditional linear regression machine learning model, the data in the parameter loss training set is trained and learned;

[0046] Based on the historical data of different environmental factors, the parameter loss sequence matrix under different environmental factors is established through the calculation results of the traditional linear regression machine learning model;

[0047] Among them, the parameter loss sequence matrix under different environmental factors is used to combine the parameter loss amount under different environmental factors for each charging since use;

[0048] According to the parameter loss sequence matrix under different environmental factors, the cumulative amount of parameter loss under different environmental factors is calculated, and the environmental impact battery life loss coefficient and the environmental impact battery life loss coefficient matrix are established;

[0049] The parameter loss linear regression equation under different environmental factors is:

[0050] ,

[0051] In the formula, is the parameter loss value under different environmental factors, is the equilibrium error constant term, is the number of different environmental factors, For the Monitoring data of environmental factors, For the Parameters of environmental factors;

[0052] The expression for calculating the cumulative amount of parameter loss under different environmental factors is:

[0053] ,

[0054] In the formula, is the cumulative amount of parameter loss under different environmental factors, is the parameter loss factor under different environmental factors, The number of times the battery has been charged.

[0055] Preferably, the establishment of a charging safety assessment model based on the battery cycle life loss coefficient, the mode-affected battery life loss coefficient and the environment-affected battery life loss coefficient, and online determination of whether the electric vehicle charging is safe specifically includes:

[0056] Draw a battery life loss change curve according to the battery cycle life loss coefficient matrix, the mode-affected battery life loss coefficient matrix and the environment-affected battery life loss coefficient matrix;

[0057] According to the changing trend of the curve graph and based on big data analysis, the weights of different nodes of each life loss coefficient are set;

[0058] According to the weights of different nodes of each life loss coefficient, a charging safety assessment model is established;

[0059] According to the charging safety assessment model, set the abnormal alarm threshold of each parameter;

[0060] Determine whether the real-time collection result value of the charging safety assessment model exceeds the threshold. If so, it means that there is a safety hazard in this charging, and the charging is automatically disconnected and the abnormal parameter type is fed back. If not, it means that there is no safety hazard in this charging;

[0061] The charging safety assessment model expression is:

[0062] ,

[0063] In the formula, is the comprehensive standard value of charging safety assessment parameters, , , are the weights of battery cycle life loss coefficient, battery life loss coefficient affected by mode, and battery life loss coefficient affected by environment, respectively. These are standard fixed parameter values ​​when the battery is produced.

[0064] Preferably, the use of Internet of Things technology to obtain battery charging history information and environmental information through multiple sets of sensors, based on a charging safety assessment model, and establishing a human-computer interaction platform, online monitoring of electric vehicle charging information specifically includes:

[0065] Using IoT technology, multiple sets of sensors are used to record and obtain battery charging history information and environmental information;

[0066] A human-computer interaction platform is established to receive and record electric vehicle charging information and charging safety assessment model evaluation results, and to display abnormal information and abnormal alarms through the platform interface.

[0067] Furthermore, this solution proposes an online evaluation system for electric vehicle charging safety based on big data, which is used to implement the above-mentioned online evaluation method for electric vehicle charging safety based on big data, including:

[0068] A data acquisition module, which is used to obtain fixed parameter information of the battery according to the battery model and product information, and to establish a fixed parameter data set for multiple types of batteries;

[0069] A safety assessment module, the safety assessment module is used to analyze the impact of the number of charging cycles on the battery life according to a fixed parameter data set of multiple types of batteries, and establish a battery cycle life loss coefficient; use simulation software to analyze the impact of different charging methods on the battery life under a fixed environment, and establish a method-effect battery life loss coefficient; analyze the impact of different environmental factors on the battery life, and establish an environmental-effect battery life loss coefficient; establish a charging safety assessment model based on the battery cycle life loss coefficient, the method-effect battery life loss coefficient, and the environmental-effect battery life loss coefficient, and determine online whether the electric vehicle is safe to charge;

[0070] The online monitoring module is used to utilize the Internet of Things technology to obtain the battery charging history information and environmental information through multiple sets of sensors, and to establish a human-computer interaction platform based on the charging safety assessment model to monitor the electric vehicle charging information online.

[0071] Preferably, the security assessment module specifically includes:

[0072] A charging cycle evaluation unit, the charging cycle evaluation unit is used to analyze the impact of the number of charging cycles on the battery life according to the fixed parameter data set of multiple types of batteries, and establish a battery cycle life loss coefficient;

[0073] A charging mode evaluation unit, the charging mode evaluation unit is used to analyze the impact of different charging modes on battery life under a fixed environment by using simulation software, and establish a battery life loss coefficient affected by the mode;

[0074] An environmental factor evaluation unit, the environmental factor evaluation unit is used to analyze the impact of different environmental factors on battery life and establish an environmental impact battery life loss coefficient;

[0075] The safety assessment unit is used to establish a charging safety assessment model based on the battery cycle life loss coefficient, the mode-affected battery life loss coefficient and the environment-affected battery life loss coefficient, and to determine online whether the electric vehicle is safe to charge.

[0076] Compared with the prior art, the present invention has the following beneficial effects:

[0077] By analyzing the impact of battery charging cycles, charging methods and environmental factors on battery life and fixed standard parameters, the battery cycle life loss coefficient, the charging method impact battery life loss coefficient and the environment impact battery life loss coefficient were established successively. On this basis, a charging safety assessment model was proposed to determine whether electric vehicle charging is safe online, thereby achieving an effective and comprehensive assessment of electric vehicle battery life and changes in its fixed parameters, and improving the accuracy and reliability of battery charging safety monitoring. BRIEF DESCRIPTION OF THE DRAWINGS

[0078] Figure 1 This is a flow chart of an online evaluation method for electric vehicle charging safety based on big data of the present invention;

[0079] Figure 2 The present invention analyzes the influence of the number of charging cycles on the battery life according to the fixed parameter data set of multiple types of batteries, and establishes a battery cycle life loss coefficient flow chart;

[0080] Figure 3 The present invention utilizes simulation software to analyze the impact of different charging methods on battery life under a fixed environment, and establishes a flow chart of the impact of charging methods on battery life loss coefficient;

[0081] Figure 4 Analyze the impact of different environmental factors on battery life for the present invention, and establish a flow chart of environmental impact battery life loss coefficient;

[0082] Figure 5 The present invention establishes a charging safety assessment model based on the battery cycle life loss coefficient, the mode-affected battery life loss coefficient and the environment-affected battery life loss coefficient, and online determines whether the charging of an electric vehicle is safe. DETAILED DESCRIPTION

[0083] The following description is used to disclose the present invention so that those skilled in the art can implement the present invention. The preferred embodiments described below are only examples, and those skilled in the art may think of other obvious variations.

[0084] Reference Figure 1 As shown, an online evaluation method for electric vehicle charging safety based on big data includes:

[0085] According to the battery model and product information, obtain the fixed parameter information of the battery and establish a fixed parameter data set for multiple types of batteries;

[0086] Based on the fixed parameter data sets of multiple types of batteries, the impact of charging cycles on battery life is analyzed, and the battery cycle life loss coefficient is established;

[0087] Use simulation software to analyze the impact of different charging methods on battery life under fixed conditions, and establish the impact of different charging methods on battery life loss coefficient;

[0088] Analyze the impact of different environmental factors on battery life and establish the environmental impact battery life loss coefficient;

[0089] According to the battery cycle life loss coefficient, the battery life loss coefficient affected by the mode and the battery life loss coefficient affected by the environment, a charging safety assessment model is established to determine online whether the charging of electric vehicles is safe;

[0090] By using Internet of Things technology, multiple sets of sensors are used to obtain the battery's charging history and environmental information. Based on the charging safety assessment model, a human-computer interaction platform is established to monitor electric vehicle charging information online.

[0091] It is understandable that electric vehicles are affected by many factors during the charging process, and these influences on the battery life are mostly irreversible. As the number of charging times increases, the battery life and fixed standard parameters will change, resulting in deviations between the actual battery parameter information and the fixed standard parameter information. Therefore, evaluating the charging safety of electric vehicles through product information is not accurate enough and is prone to misjudgment. This solution analyzes the impact of battery charging cycles, charging methods, and environmental factors on battery life and fixed standard parameters, and successively establishes battery cycle life loss coefficients, method-effect battery life loss coefficients, and environmental-effect battery life loss coefficients. On this basis, a charging safety assessment model is proposed to determine whether electric vehicle charging is safe online, thereby achieving an effective and comprehensive assessment of the battery life of electric vehicles and changes in their fixed parameters, and improving the accuracy and reliability of battery charging safety monitoring.

[0092] Reference Figure 2 As shown, the fixed parameter data set of multiple types of batteries analyzes the impact of the number of charging cycles on the battery life and establishes the battery cycle life loss coefficient, which specifically includes:

[0093] Using simulation software and test experiments, the parameter changes of multiple types of battery fixed parameter data sets during battery cycle charging are obtained under fixed environment and charging mode.

[0094] According to the changes of parameters, the loss coefficient of each parameter under cyclic charging is calculated respectively;

[0095] According to the loss coefficient of each parameter under cyclic charging, a battery cycle life loss coefficient and a battery cycle life loss coefficient matrix are established;

[0096] The loss coefficient expressions of the parameters under cyclic charging are as follows:

[0097] ,

[0098] In the formula, is the loss coefficient of each parameter under cyclic charging, is the parameter loss factor under cycle charging, is a constant, is the functional relationship between the number of battery charging cycles and the parameter loss value, For the The parameter loss value of the charge cycle is: For the Parameter monitoring data of the sub-cycle, These are standard fixed parameter values ​​when the battery is produced.

[0099] It is understandable that during the battery charging cycle, the battery performance will decrease with the increase in the number of charging times, which will cause the fixed standard parameters of the battery to change. Therefore, this solution obtains the parameter data loss generated under different charging times through big data or test experiments, and establishes a battery cycle life loss coefficient and a battery cycle life loss coefficient matrix, thereby providing the loss component of battery life under cyclic charging conditions.

[0100] Reference Figure 3 As shown, the use of simulation software to analyze the impact of different charging methods on battery life under a fixed environment and establish the impact of different charging methods on battery life loss coefficients specifically includes:

[0101] Using simulation software and test experiments, different charging methods are adopted under fixed environment to obtain the parameter changes in the fixed parameter data set of multiple types of batteries after charging is completed;

[0102] Among them, different charging methods include: fast charging, slow charging, normal charging, overcharging, disconnected charging, and power loss;

[0103] According to the parameter changes, the loss coefficient of each parameter under different charging modes is calculated;

[0104] According to the loss coefficients of various parameters under different charging modes, a matrix of loss coefficients of battery life affected by charging mode and loss coefficients of battery life affected by charging mode is established;

[0105] Using fixed parameter data sets of multiple types of batteries, the battery charging method is determined based on the charging time, charging rate, voltage stability and battery capacity of electric vehicle batteries;

[0106] The loss coefficient expressions of the parameters under different charging modes are as follows:

[0107] ,

[0108] In the formula, is the loss coefficient of each parameter under different charging modes, is the parameter loss factor under different charging modes, is the number of different charging methods, For the The weight of each charging mode, For the The number of occurrences under each charging mode, For the Charging mode The monitoring values ​​of each parameter are For the The average value of each parameter monitoring value under each charging mode;

[0109] The battery charging mode determination method is specifically as follows:

[0110] According to the fixed parameter data set of multiple types of batteries, the standard voltage value range and threshold value when the battery is fully charged are set;

[0111] According to the fixed parameter data set of multiple types of batteries, set the current value change range and threshold during the charging process of the battery;

[0112] According to the fixed parameter data set of multiple types of batteries, set the charging time, charging rate range, and set the highest and lowest thresholds;

[0113] Determine whether the battery voltage exceeds the standard voltage value threshold. If so, it means that the battery is overcharged. If not, determine whether the voltage during power failure is within the standard voltage value range. If so, it means that the battery is charged normally. If not, it means that the battery is low on power.

[0114] Determine whether the battery charging time and charging rate exceed the maximum threshold. If so, it means that the battery uses fast charging. If not, determine whether the battery charging time and charging rate are lower than the minimum threshold. If so, it means that the battery uses slow charging. If not, it means that the battery uses normal charging.

[0115] It is determined whether the battery current value exceeds the threshold value multiple times during the charging process, or even the current value is 0. If so, it indicates that the battery charging is interrupted. If not, it indicates that the battery is not interrupted.

[0116] It is understandable that different charging methods include: fast charging, slow charging, normal charging, overcharging, disconnected charging, and power loss. Different charging methods for a long time will cause the battery life to be shortened and the fixed standard parameters of the battery to change. This solution analyzes the cumulative impact of different charging methods on battery life and the changes in the fixed standard parameters of the battery, establishes the coefficient of battery life loss affected by the method and the matrix of battery life loss coefficients affected by the method, and judges the battery charging method through the charging time, charging rate, voltage stability and battery capacity data in the fixed parameter data set of multiple types of batteries, thereby providing the loss component of battery life under different charging methods.

[0117] Reference Figure 4 As shown, the analysis of the impact of different environmental factors on battery life and establishing the environmental impact battery life loss coefficient specifically includes:

[0118] Using simulation software and test experiments, different environmental data are set, and the changes of fixed parameter data of multiple types of batteries under different environmental factors are obtained through the control variable method;

[0119] Filter and standardize the parameter change data, and establish a parameter loss training set;

[0120] According to different environmental types, a linear regression equation of parameter loss under different environmental factors is established;

[0121] Based on the traditional linear regression machine learning model, the data in the parameter loss training set is trained and learned;

[0122] Based on the historical data of different environmental factors, the parameter loss sequence matrix under different environmental factors is established through the calculation results of the traditional linear regression machine learning model;

[0123] Among them, the parameter loss sequence matrix under different environmental factors is used to combine the parameter loss amount under different environmental factors for each charging since use;

[0124] According to the parameter loss sequence matrix under different environmental factors, the cumulative amount of parameter loss under different environmental factors is calculated, and the environmental impact battery life loss coefficient and the environmental impact battery life loss coefficient matrix are established;

[0125] The parameter loss linear regression equation under different environmental factors is:

[0126] ,

[0127] In the formula, is the parameter loss value under different environmental factors, is the equilibrium error constant term, is the number of different environmental factors, For the Monitoring data of environmental factors, For the Parameters of environmental factors;

[0128] The expression for calculating the cumulative amount of parameter loss under different environmental factors is:

[0129] ,

[0130] In the formula, is the cumulative amount of parameter loss under different environmental factors, is the parameter loss factor under different environmental factors, The number of times the battery has been charged.

[0131] It is understandable that different environmental factors, especially under high or low temperature conditions, have a greater impact on battery charging. Charging under different environments will also lead to a decline in battery performance, reduce the battery life and cause changes in the battery's fixed standard parameters. This solution uses a traditional linear regression machine learning model to establish a functional relationship between different environmental factors and the battery's fixed standard parameter losses through a linear regression equation, and through model learning and training, obtains the parameter loss sequence under different environmental factors, calculates the cumulative parameter loss under different environmental factors, and establishes the environmental impact battery life loss coefficient and the environmental impact battery life loss coefficient matrix, thereby providing the loss component of battery life under different environmental factors.

[0132] Reference Figure 5 As shown, the charging safety assessment model is established based on the battery cycle life loss coefficient, the mode-affected battery life loss coefficient and the environment-affected battery life loss coefficient, and the online determination of whether the electric vehicle charging is safe specifically includes:

[0133] Draw a battery life loss change curve according to the battery cycle life loss coefficient matrix, the mode-affected battery life loss coefficient matrix and the environment-affected battery life loss coefficient matrix;

[0134] According to the changing trend of the curve graph and based on big data analysis, the weights of different nodes of each life loss coefficient are set;

[0135] According to the weights of different nodes of each life loss coefficient, a charging safety assessment model is established;

[0136] According to the charging safety assessment model, set the abnormal alarm threshold of each parameter;

[0137] Determine whether the real-time collection result value of the charging safety assessment model exceeds the threshold. If so, it means that there is a safety hazard in this charging, and the charging is automatically disconnected and the abnormal parameter type is fed back. If not, it means that there is no safety hazard in this charging;

[0138] The charging safety assessment model expression is:

[0139] ,

[0140] In the formula, is the comprehensive standard value of charging safety assessment parameters, , , are the weights of battery cycle life loss coefficient, battery life loss coefficient affected by mode, and battery life loss coefficient affected by environment, respectively. These are standard fixed parameter values ​​when the battery is produced.

[0141] It can be understood that according to the battery cycle life loss coefficient, the battery life loss coefficient affected by the mode and the battery life loss coefficient affected by the environment, the weight values ​​of different coefficients can be set to judge the comprehensive impact of different coefficients on charging safety at different nodes, and then the charging safety can be evaluated by comparing the abnormal alarm thresholds of the parameters. Among them, the weights of different coefficients for different nodes can be manually set and assigned through the slope of the curve in the battery life loss change curve diagram combined with big data analysis, and corrected and optimized according to the actual experimental test results.

[0142] Further, based on the same inventive concept as the above-mentioned method for online evaluation of electric vehicle charging safety based on big data, this solution proposes an online evaluation system for electric vehicle charging safety based on big data, including:

[0143] A data acquisition module, which is used to obtain fixed parameter information of the battery according to the battery model and product information, and to establish a fixed parameter data set for multiple types of batteries;

[0144] A safety assessment module, the safety assessment module is used to analyze the impact of the number of charging cycles on the battery life according to a fixed parameter data set of multiple types of batteries, and establish a battery cycle life loss coefficient; use simulation software to analyze the impact of different charging methods on the battery life under a fixed environment, and establish a method-effect battery life loss coefficient; analyze the impact of different environmental factors on the battery life, and establish an environmental-effect battery life loss coefficient; establish a charging safety assessment model based on the battery cycle life loss coefficient, the method-effect battery life loss coefficient, and the environmental-effect battery life loss coefficient, and determine online whether the electric vehicle is safe to charge;

[0145] An online monitoring module, which is used to utilize the Internet of Things technology to obtain the battery charging history information and environmental information through multiple sets of sensors, and to establish a human-computer interaction platform based on a charging safety assessment model to monitor the electric vehicle charging information online;

[0146] The security assessment module specifically includes:

[0147] A charging cycle evaluation unit, the charging cycle evaluation unit is used to analyze the impact of the number of charging cycles on the battery life according to the fixed parameter data set of multiple types of batteries, and establish a battery cycle life loss coefficient;

[0148] A charging mode evaluation unit, the charging mode evaluation unit is used to analyze the impact of different charging modes on battery life under a fixed environment by using simulation software, and establish a battery life loss coefficient affected by the mode;

[0149] An environmental factor evaluation unit, the environmental factor evaluation unit is used to analyze the impact of different environmental factors on battery life and establish an environmental impact battery life loss coefficient;

[0150] The safety assessment unit is used to establish a charging safety assessment model based on the battery cycle life loss coefficient, the mode-affected battery life loss coefficient and the environment-affected battery life loss coefficient, and to determine online whether the electric vehicle is safe to charge.

[0151] In summary, the advantages of the present invention are: by analyzing the impact of battery charging cycles, charging methods and environmental factors on battery life and fixed standard parameters, the battery cycle life loss coefficient, the method-effect battery life loss coefficient and the environment-effect battery life loss coefficient are established successively, and on this basis, a charging safety assessment model is proposed to determine online whether the charging of electric vehicles is safe, thereby achieving an effective and comprehensive assessment of the battery life of electric vehicles and changes in their fixed parameters, and improving the accuracy and reliability of battery charging safety monitoring.

[0152] The above shows and describes the basic principles, main features and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The above embodiments and descriptions only describe the principles of the present invention. The present invention may be subject to various changes and improvements without departing from the spirit and scope of the present invention. These changes and improvements fall within the scope of the present invention. The scope of protection claimed by the present invention is defined by the attached claims and their equivalents.

Claims

1. An online evaluation method for electric vehicle charging safety based on big data, characterized in that: include: According to the battery model and product information, obtain the fixed parameter information of the battery and establish a fixed parameter data set for multiple types of batteries; Based on the fixed parameter data sets of multiple types of batteries, the impact of charging cycles on battery life is analyzed, and the battery cycle life loss coefficient is established; Use simulation software to analyze the impact of different charging methods on battery life under fixed conditions, and establish the impact of different charging methods on battery life loss coefficient; Analyze the impact of different environmental factors on battery life and establish the environmental impact battery life loss coefficient; According to the battery cycle life loss coefficient, the battery life loss coefficient affected by the mode and the battery life loss coefficient affected by the environment, a charging safety assessment model is established to determine online whether the charging of electric vehicles is safe; By using Internet of Things technology, the battery charging history information and environmental information are obtained through multiple sets of sensors. According to the charging safety assessment model, a human-computer interaction platform is established to monitor the charging information of electric vehicles online.

2. According to the big data-based online evaluation method for electric vehicle charging safety according to claim 1, it is characterized in that: The method of obtaining fixed parameter information of the battery according to the battery model and product information and establishing a fixed parameter data set of multiple types of batteries specifically includes: Based on big data, obtain fixed parameter information of different types of batteries according to the existing electric vehicle battery models and product information on the market; Classify and organize the fixed parameter information of different types of batteries, and establish a fixed parameter information set for multiple types of batteries; Quantify and standardize the data in the fixed parameter information set of multiple types of batteries and establish a fixed parameter data set for multiple types of batteries; Among them, the fixed parameter data sets of multiple types of batteries include: voltage, battery capacity, cold start current, maximum output current, rated capacity, self-discharge rate, energy density, power density and charging rate.

3. According to claim 2, a method for online evaluation of electric vehicle charging safety based on big data is characterized in that: The method of analyzing the influence of the number of charging cycles on the battery life according to the fixed parameter data sets of multiple types of batteries and establishing the battery cycle life loss coefficient specifically includes: Using simulation software and test experiments, the parameter changes of multiple types of battery fixed parameter data sets during battery cycle charging are obtained under fixed environment and charging mode. According to the changes of parameters, the loss coefficient of each parameter under cyclic charging is calculated respectively; According to the loss coefficient of each parameter under cyclic charging, a battery cycle life loss coefficient and a battery cycle life loss coefficient matrix are established; The loss coefficient expressions of the parameters under cyclic charging are as follows: ， In the formula, is the loss coefficient of each parameter under cyclic charging, is the parameter loss factor under cycle charging, is a constant, is the functional relationship between the number of battery charging cycles and the parameter loss value, For the The parameter loss value of the charge cycle is For the Parameter monitoring data of the sub-cycle, These are standard fixed parameter values ​​when the battery is produced.

4. According to the big data-based online evaluation method for electric vehicle charging safety according to claim 3, it is characterized in that: The use of simulation software to analyze the impact of different charging methods on battery life under a fixed environment and establish the impact of different charging methods on battery life loss coefficients specifically includes: Using simulation software and test experiments, different charging methods are adopted under fixed environment to obtain the parameter changes in the fixed parameter data set of multiple types of batteries after charging is completed; Among them, different charging methods include: fast charging, slow charging, normal charging, overcharging, disconnected charging, and power loss; According to the parameter changes, the loss coefficient of each parameter under different charging modes is calculated; According to the loss coefficients of various parameters under different charging modes, a matrix of loss coefficients of battery life affected by charging mode and loss coefficients of battery life affected by charging mode is established; Using fixed parameter data sets of multiple types of batteries, the battery charging method is determined based on the charging time, charging rate, voltage stability and battery capacity of electric vehicle batteries; The loss coefficient expressions of the parameters under different charging modes are as follows: ， In the formula, is the loss coefficient of each parameter under different charging modes, is the parameter loss factor under different charging modes, is the number of different charging methods, For the The weight of each charging mode, For the The number of occurrences under each charging mode, For the Charging mode The monitoring values ​​of each parameter are For the The average value of each parameter monitoring value under each charging mode; The battery charging mode determination method is specifically as follows: According to the fixed parameter data set of multiple types of batteries, the standard voltage value range and threshold value when the battery is fully charged are set; According to the fixed parameter data set of multiple types of batteries, set the current value change range and threshold during the charging process of the battery; According to the fixed parameter data set of multiple types of batteries, set the charging time, charging rate range, and set the highest and lowest thresholds; Determine whether the battery voltage exceeds the standard voltage value threshold. If so, it means that the battery is overcharged. If not, determine whether the voltage during power failure is within the standard voltage value range. If so, it means that the battery is charged normally. If not, it means that the battery is low on power. Determine whether the battery charging time and charging rate exceed the maximum threshold. If so, it means that the battery uses fast charging. If not, determine whether the battery charging time and charging rate are lower than the minimum threshold. If so, it means that the battery uses slow charging. If not, it means that the battery uses normal charging. It is determined whether the battery current value exceeds the threshold value multiple times during the charging process, or even the current value is 0. If so, it indicates that the battery charging is interrupted. If not, it indicates that the battery is not interrupted.

5. The method for online evaluation of electric vehicle charging safety based on big data according to claim 4 is characterized in that: The analysis of the impact of different environmental factors on battery life and establishing the environmental impact battery life loss coefficient specifically includes: Using simulation software and test experiments, different environmental data are set, and the changes of fixed parameter data of multiple types of batteries under different environmental factors are obtained through the control variable method; Filter and standardize the parameter change data, and establish a parameter loss training set; According to different environmental types, a linear regression equation of parameter loss under different environmental factors is established; Based on the traditional linear regression machine learning model, the data in the parameter loss training set is trained and learned; Based on the historical data of different environmental factors, the parameter loss sequence matrix under different environmental factors is established through the calculation results of the traditional linear regression machine learning model; Among them, the parameter loss sequence matrix under different environmental factors is used to combine the parameter loss amount under different environmental factors for each charging since use; According to the parameter loss sequence matrix under different environmental factors, the cumulative amount of parameter loss under different environmental factors is calculated, and the environmental impact battery life loss coefficient and the environmental impact battery life loss coefficient matrix are established; The parameter loss linear regression equation under different environmental factors is: ， In the formula, is the parameter loss value under different environmental factors, is the equilibrium error constant term, is the number of different environmental factors, For the Monitoring data of environmental factors, For the Parameters of environmental factors; The expression for calculating the cumulative amount of parameter loss under different environmental factors is: ， In the formula, is the cumulative amount of parameter loss under different environmental factors, is the parameter loss factor under different environmental factors, The number of times the battery has been charged.

6. The method for online evaluation of electric vehicle charging safety based on big data according to claim 5 is characterized in that: The method of establishing a charging safety assessment model based on the battery cycle life loss coefficient, the battery life loss coefficient affected by the mode and the battery life loss coefficient affected by the environment, and determining online whether the charging of the electric vehicle is safe specifically includes: Draw a battery life loss change curve according to the battery cycle life loss coefficient matrix, the mode-affected battery life loss coefficient matrix and the environment-affected battery life loss coefficient matrix; According to the changing trend of the curve graph and based on big data analysis, the weights of different nodes of each life loss coefficient are set; According to the weights of different nodes of each life loss coefficient, a charging safety assessment model is established; According to the charging safety assessment model, set the abnormal alarm threshold of each parameter; Determine whether the real-time collection result value of the charging safety assessment model exceeds the threshold. If so, it means that there is a safety hazard in this charging, and the charging is automatically disconnected and the abnormal parameter type is fed back. If not, it means that there is no safety hazard in this charging; The charging safety assessment model expression is: ， In the formula, is the comprehensive standard value of charging safety assessment parameters, , , are the weights of battery cycle life loss coefficient, battery life loss coefficient affected by mode, and battery life loss coefficient affected by environment, respectively. These are standard fixed parameter values ​​when the battery is produced.

7. The method for online evaluation of electric vehicle charging safety based on big data according to claim 6 is characterized in that: The use of Internet of Things technology to obtain battery charging history information and environmental information through multiple sets of sensors, based on the charging safety assessment model, and establish a human-computer interaction platform, online monitoring of electric vehicle charging information specifically includes: Using IoT technology, multiple sets of sensors are used to record and obtain battery charging history information and environmental information; A human-computer interaction platform is established to receive and record electric vehicle charging information and charging safety assessment model evaluation results, and to display abnormal information and abnormal alarms through the platform interface.

8. An online evaluation system for electric vehicle charging safety based on big data, characterized in that: The method for online evaluation of electric vehicle charging safety based on big data according to any one of claims 1 to 7 comprises: A data acquisition module, which is used to obtain fixed parameter information of the battery according to the battery model and product information, and to establish a fixed parameter data set for multiple types of batteries; A safety assessment module, the safety assessment module is used to analyze the impact of the number of charging cycles on the battery life according to a fixed parameter data set of multiple types of batteries, and establish a battery cycle life loss coefficient; use simulation software to analyze the impact of different charging methods on the battery life under a fixed environment, and establish a method-effect battery life loss coefficient; analyze the impact of different environmental factors on the battery life, and establish an environmental-effect battery life loss coefficient; establish a charging safety assessment model based on the battery cycle life loss coefficient, the method-effect battery life loss coefficient, and the environmental-effect battery life loss coefficient, and determine online whether the electric vehicle is safe to charge; The online monitoring module is used to utilize the Internet of Things technology to obtain the battery charging history information and environmental information through multiple sets of sensors, and to establish a human-computer interaction platform based on the charging safety assessment model to monitor the electric vehicle charging information online.

9. The electric vehicle charging safety online assessment system based on big data according to claim 8 is characterized in that: The security assessment module specifically includes: A charging cycle evaluation unit, the charging cycle evaluation unit is used to analyze the impact of the number of charging cycles on the battery life according to the fixed parameter data set of multiple types of batteries, and establish a battery cycle life loss coefficient; A charging mode evaluation unit, the charging mode evaluation unit is used to analyze the impact of different charging modes on battery life under a fixed environment by using simulation software, and establish a battery life loss coefficient affected by the mode; An environmental factor evaluation unit, the environmental factor evaluation unit is used to analyze the impact of different environmental factors on battery life and establish an environmental impact battery life loss coefficient; The safety assessment unit is used to establish a charging safety assessment model based on the battery cycle life loss coefficient, the mode-affected battery life loss coefficient and the environment-affected battery life loss coefficient, and to determine online whether the electric vehicle is safe to charge.

Images