WO2022143903A1 - 车用电池的安全评估方法、系统、设备及可读存储介质 - Google Patents

车用电池的安全评估方法、系统、设备及可读存储介质 Download PDF

Info

Publication number
WO2022143903A1
WO2022143903A1 PCT/CN2021/143092 CN2021143092W WO2022143903A1 WO 2022143903 A1 WO2022143903 A1 WO 2022143903A1 CN 2021143092 W CN2021143092 W CN 2021143092W WO 2022143903 A1 WO2022143903 A1 WO 2022143903A1
Authority
WO
WIPO (PCT)
Prior art keywords
battery
safety evaluation
real
time
battery safety
Prior art date
Application number
PCT/CN2021/143092
Other languages
English (en)
French (fr)
Inventor
姚林
Original Assignee
奥动新能源汽车科技有限公司
上海电巴新能源科技有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 奥动新能源汽车科技有限公司, 上海电巴新能源科技有限公司 filed Critical 奥动新能源汽车科技有限公司
Publication of WO2022143903A1 publication Critical patent/WO2022143903A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
    • G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
    • G01R31/36—Arrangements for testing, measuring or monitoring the electrical condition of accumulators or electric batteries, e.g. capacity or state of charge [SoC]
    • G01R31/367—Software therefor, e.g. for battery testing using modelling or look-up tables
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
    • G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
    • G01R31/36—Arrangements for testing, measuring or monitoring the electrical condition of accumulators or electric batteries, e.g. capacity or state of charge [SoC]
    • G01R31/392—Determining battery ageing or deterioration, e.g. state of health
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00—Computer-aided design [CAD]
    • G06F30/20—Design optimisation, verification or simulation
    • G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0635—Risk analysis of enterprise or organisation activities
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/10—Services
    • G06Q50/26—Government or public services
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/10—Services
    • G06Q50/26—Government or public services
    • G06Q50/265—Personal security, identity or safety

Definitions

  • the invention belongs to the field of battery evaluation, and in particular relates to a safety evaluation method, system, device and readable storage medium for a vehicle battery.
  • the technical problem to be solved by the present invention is to overcome the lack of effective methods in the prior art to monitor the safety of vehicle batteries in real time, and to provide a safety assessment method, system, and safety hazard for vehicle batteries.
  • Devices and readable storage media are used to store and retrieve data.
  • a safety evaluation method for a vehicle battery comprising:
  • the battery safety evaluation model is obtained by training the sample battery safety evaluation variables of the sample vehicle battery as input, and the battery safety evaluation model outputs the predicted safety evaluation quantification result of the sample vehicle battery during training.
  • the sample battery safety evaluation variables of the sample vehicle batteries are used to train the battery safety evaluation model in advance, so that the battery safety evaluation model learns the ability to perform battery safety evaluation based on the battery safety evaluation variables, and then based on the trained battery safety evaluation model.
  • Real-time monitoring of vehicle batteries obtaining real-time battery safety evaluation variables and inputting the battery safety evaluation model to output the quantitative results of real-time safety evaluation.
  • the battery safety of any electric vehicle at any point in time can be assessed based on the quantitative results of real-time safety evaluation. The performance is evaluated to achieve effective monitoring of the safety performance of the battery.
  • the real-time battery safety assessment variables include multiple real-time variables corresponding to multiple battery safety assessment parameters;
  • the step of inputting the real-time battery safety evaluation variable into the battery safety evaluation model, and outputting the real-time safety evaluation quantification result of the target vehicle battery through the battery safety evaluation model specifically includes:
  • the multiple real-time variables are processed based on the weights corresponding to each battery safety evaluation parameter to obtain processing results, and the real-time safety evaluation quantitative results of the target vehicle battery are obtained according to all the processing results. and output.
  • the real-time battery safety evaluation variables include multiple real-time variables corresponding to multiple battery safety evaluation parameters, so that the battery safety evaluation can be performed from multiple data dimensions, and the accuracy of the battery safety evaluation can be improved;
  • the battery safety assessment parameters of the data dimension it is also considered that the battery safety assessment parameters of different data dimensions have different influences on the battery safety assessment, and multiple real-time variables are processed based on the weights corresponding to each battery safety assessment parameter to further improve The accuracy and reliability of the battery safety assessment are improved.
  • the safety assessment method further includes a training step of the battery safety assessment model, and the training step includes:
  • sample battery safety assessment variables include a plurality of sample variables corresponding to the plurality of battery safety assessment parameters;
  • the plurality of sample variables are processed based on the weights corresponding to each battery safety evaluation parameter to obtain a quantitative result of the predicted safety evaluation of the sample vehicle battery.
  • the influence of different battery safety evaluation parameters on battery safety is comprehensively considered, and during training, the weight coefficient of each battery safety evaluation parameter is trained and optimized to improve the accuracy of the battery safety evaluation model.
  • the step of collecting the sample battery safety assessment variables of the sample vehicle battery specifically includes:
  • the battery safety evaluation model is trained by comprehensively using the data in the laboratory failure scenario and the real application scenario.
  • the safety evaluation method further includes:
  • noise reduction and/or deviation correction processing is performed on the data to remove the interference data.
  • normalization processing or floating point processing is performed on the data. Process or scale to ensure data uniformity.
  • the quantified result of the real-time safety assessment is the real-time battery thermal runaway probability
  • the battery safety assessment model specifically processes the real-time battery safety assessment variables according to the following formula to obtain the real-time battery thermal runaway probability, which specifically includes:
  • y i is the real-time battery thermal runaway probability at the ith second or minute, is the normalized or floating point or scaled value of the nth real-time variable at the ith second or minute, is the weight of the nth battery safety evaluation parameter at the ith second or minute.
  • a method for calculating the real-time battery thermal runaway probability in a specific scenario is provided, so that the calculation relationship of the real-time battery thermal runaway probability is clear, and the calculation result is more convincing.
  • the battery safety evaluation model is applied to a vehicle controller and/or a battery management system, and the safety evaluation method further includes:
  • the quantification result of the real-time safety assessment can be judged through a threshold value to determine whether the target vehicle battery is abnormal. Users can perform inspection or maintenance in a timely manner.
  • a safety evaluation system for a vehicle battery comprising:
  • the real-time variable acquisition module is used to acquire the real-time battery safety assessment variables of the target vehicle battery
  • An evaluation result output module for inputting the real-time battery safety evaluation variable into a battery safety evaluation model, and outputting the real-time safety evaluation quantification result of the target vehicle battery through the battery safety evaluation model;
  • the battery safety evaluation model is obtained by training the sample battery safety evaluation variables of the sample vehicle battery as input, and the battery safety evaluation model outputs the predicted safety evaluation quantification result of the sample vehicle battery during training.
  • the sample battery safety evaluation variables of the sample vehicle batteries are used to train the battery safety evaluation model in advance, so that the battery safety evaluation model learns the ability to perform battery safety evaluation based on the battery safety evaluation variables, and then based on the trained battery safety evaluation model.
  • Real-time monitoring of vehicle batteries obtaining real-time battery safety evaluation variables and inputting them into the battery safety evaluation model, and outputting real-time safety evaluation quantification results.
  • the battery safety of any electric vehicle at any point in time can be assessed. The performance is evaluated to achieve effective monitoring of the safety performance of the battery.
  • the real-time battery safety assessment variables include multiple real-time variables corresponding to multiple battery safety assessment parameters;
  • the evaluation result output module is used to input a plurality of the real-time variables into the battery safety evaluation model; Perform processing to obtain processing results, and obtain and output the quantitative results of real-time safety assessment of the target vehicle battery according to all processing results.
  • the real-time battery safety evaluation variables include multiple real-time variables corresponding to multiple battery safety evaluation parameters, so that the battery safety evaluation can be performed from multiple data dimensions, and the accuracy of the battery safety evaluation can be improved;
  • the battery safety evaluation parameters of the data dimension it also takes into account that the battery safety evaluation parameters of different data dimensions have different influences on the battery safety evaluation.
  • Multiple real-time variables are processed based on the weights corresponding to each battery safety evaluation parameter to further improve the The accuracy and reliability of the battery safety assessment are improved.
  • the security assessment system further includes a training module, and the training module specifically includes:
  • the evaluation parameter selection unit is used to select multiple battery safety evaluation parameters
  • a collection unit configured to collect sample battery safety assessment variables of a sample vehicle battery;
  • the sample battery safety assessment variables include a plurality of sample variables corresponding to the plurality of battery safety assessment parameters;
  • a weight acquisition unit configured to train the battery safety evaluation model by using the sample battery safety evaluation variable as input data to obtain a weight corresponding to each battery safety evaluation parameter in the battery safety evaluation model
  • An evaluation result output unit configured to process the plurality of sample variables based on a weight corresponding to each battery safety evaluation parameter, to obtain a quantitative result of the predicted safety evaluation of the sample vehicle battery.
  • the influence of different battery safety evaluation parameters on battery safety is comprehensively considered, and during training, the weight coefficient of each battery safety evaluation parameter is trained and optimized to improve the accuracy of the battery safety evaluation model.
  • the collection unit is used to obtain experimental data of a sample vehicle battery in a laboratory failure scenario, and extract battery characteristic data from the experimental data to generate the sample battery safety assessment variable;
  • the collection unit is used for acquiring historical data of a sample vehicle battery in a real application scenario, and extracting battery characteristic data from the historical data to generate the sample battery safety evaluation variable.
  • the battery safety evaluation model is trained by comprehensively using the data in the laboratory failure scenario and the real application scenario.
  • the security assessment method further includes a data preprocessing module
  • the data preprocessing module is configured to perform noise reduction and/or deviation correction processing on the real-time battery safety assessment variables
  • the data preprocessing module is configured to perform normalization processing, floating point processing or scaling processing on the real-time battery safety assessment variables.
  • noise reduction and/or deviation correction processing is performed on the data to remove the interference data.
  • normalization processing or floating point processing is performed on the data. Process or scale to ensure data uniformity.
  • the quantified result of the real-time safety assessment is the real-time battery thermal runaway probability
  • the battery safety assessment model specifically processes the real-time battery safety assessment variables according to the following formula to obtain the real-time battery thermal runaway probability, which specifically includes:
  • y i is the real-time battery thermal runaway probability at the ith second or minute, is the normalized or floating point or scaled value of the nth real-time variable at the ith second or minute, is the weight of the nth battery safety evaluation parameter at the ith second or minute.
  • a method for calculating the real-time battery thermal runaway probability in a specific scenario is provided, so that the calculation relationship of the real-time battery thermal runaway probability is clear, and the calculation result is more convincing.
  • the battery safety evaluation model is applied to a vehicle controller and/or a battery management system, and the safety evaluation system further includes:
  • An alarm module configured to issue an alarm signal when the quantitative result of the real-time safety assessment indicates that the target vehicle battery is abnormal.
  • the quantification result of the real-time safety assessment can be judged through a threshold value to determine whether the target vehicle battery is abnormal. Users can perform inspection or maintenance in a timely manner.
  • An electronic device includes a memory, a processor, and a computer program stored in the memory and running on the processor, the processor implementing the above-mentioned method for evaluating the safety of a vehicle battery when the computer program is executed.
  • the positive improvement effect of the present invention is that: the present application performs real-time monitoring on the vehicle battery based on the trained battery safety evaluation model, obtains the real-time battery safety evaluation variable and then inputs the battery safety evaluation model, and outputs the real-time safety evaluation quantification result, and further, can Based on the quantitative results of real-time safety assessment, the battery safety performance of any electric vehicle at any point in time is evaluated to effectively monitor the safety performance of the battery.
  • FIG. 1 is a flowchart of a safety evaluation method for a vehicle battery according to Embodiment 1 of the present invention.
  • FIG. 2 is a flowchart of step 20 in the safety assessment method for a vehicle battery according to Embodiment 1 of the present invention.
  • FIG. 3 is a flowchart of a safety assessment method for a vehicle battery according to Embodiment 2 of the present invention.
  • FIG. 4 is a schematic block diagram of a safety evaluation system for a vehicle battery according to Embodiment 3 of the present invention.
  • FIG. 5 is a schematic block diagram of a safety evaluation system for a vehicle battery according to Embodiment 4 of the present invention.
  • FIG. 6 is a structural entity diagram of an electronic device according to Embodiment 5 of the present invention.
  • a safety evaluation method for a vehicle battery as shown in Figure 1, the safety evaluation method includes:
  • Step 10 obtaining real-time battery safety assessment variables of the target vehicle battery
  • Step 20 Input the real-time battery safety evaluation variable into the battery safety evaluation model, and output the quantitative result of the real-time safety evaluation of the target vehicle battery through the battery safety evaluation model;
  • the battery safety evaluation model is trained with the sample battery safety evaluation variables of the sample vehicle battery as input, and the battery safety evaluation model outputs the quantitative results of the predicted safety evaluation of the sample vehicle battery during training.
  • the raw data from which the real-time battery safety assessment variables are derived can be collected through the battery management system, and the raw data from which the sample battery safety assessment variables are derived can also be collected through the battery management system.
  • the battery safety evaluation model can be stored in the electric vehicle, such as the battery management system or the vehicle controller, so that the safety evaluation method of the vehicle battery can be implemented in the electric vehicle;
  • the edge computing server of the power station so that the safety assessment method of the vehicle battery can be executed at the power station;
  • the battery safety assessment model can also be stored in the cloud, such as a data center server, so that the safety assessment method of the vehicle battery can be executed in the cloud.
  • data can be collected through the vehicle's own battery management system (BMS), on the one hand, it is used for local calculation to obtain quantitative results of real-time safety assessment, on the other hand, the data can be aggregated to a remote data center, Further, based on the big data basic platform, the data can be used to continuously optimize the model and improve the prediction accuracy.
  • BMS battery management system
  • the real-time battery safety assessment variables include multiple real-time variables corresponding to multiple battery safety assessment parameters.
  • the battery safety evaluation parameter is a parameter based on which the battery safety evaluation is based, and the specific value of the parameter is a variable.
  • the battery safety assessment parameters include at least one of voltage, temperature, humidity, current, smoke, salt spray, vibration, and altitude, and correspondingly, the real-time variables include voltage value, temperature value, humidity value, current value, smoke value, salt spray value , at least one of a vibration value, and an altitude value.
  • step 20 specifically includes:
  • Step 201 inputting multiple real-time variables into the battery safety assessment model
  • Step 202 Process multiple real-time variables based on a weight corresponding to each battery safety evaluation parameter through a battery safety evaluation model to obtain a processing result; wherein each battery safety evaluation parameter corresponds to a real-time variable, and each battery safety evaluation parameter corresponds to a real-time variable. corresponds to a weight.
  • Step 203 obtaining and outputting a quantitative result of the real-time safety assessment of the target vehicle battery according to all the processing results.
  • the quantified result of the real-time safety assessment is the real-time battery thermal runaway probability
  • the battery safety assessment model specifically processes the real-time battery safety assessment variables according to the following formula to obtain the real-time battery thermal runaway probability, which specifically includes:
  • y i is the real-time battery thermal runaway probability at the ith second or minute, is the normalized or floating point or scaled value of the nth real-time variable at the ith second or minute, is the weight of the nth battery safety evaluation parameter at the ith second or minute.
  • the security assessment method in order to remove possible inaccurate data or interference data in the data, noise reduction and/or deviation correction processing is performed on the data to remove the interference data.
  • normalization processing or floating point processing is performed on the data. Processing or scaling to ensure data uniformity, see Figure 1, after step 10, the security assessment method also includes:
  • Step 11 Perform noise reduction and/or deviation correction processing on the real-time battery safety assessment variables
  • Step 12 perform normalization processing, floating point processing or scaling processing on the real-time battery safety evaluation variables.
  • the quantification result of the real-time safety assessment can be judged by a threshold value to determine whether the target vehicle battery is abnormal.
  • the user performs inspection or maintenance in time, and the battery safety evaluation model is applied to the vehicle controller and/or the battery management system. See Figure 1.
  • the safety evaluation method further includes:
  • Step 30 When the quantitative result of the real-time safety assessment indicates that the target vehicle battery is abnormal, an alarm signal is issued.
  • the warning can be provided by a vehicle instrument.
  • the alarm information is sent to the vehicle controller of the electric vehicle, and the vehicle instrument panel is used for warning through the vehicle controller.
  • the alarm information can be sent to the monitoring platform, and the warning can be displayed on the monitoring screen through the monitoring platform.
  • the vehicle battery is monitored in real time based on the trained battery safety evaluation model, the real-time battery safety evaluation variables are obtained and then input to the battery safety evaluation model, and the real-time safety evaluation quantification result is output.
  • Results The battery safety performance of any electric vehicle at any point in time was evaluated in order to effectively monitor the safety performance of the battery.
  • the safety evaluation method for a vehicle battery in this embodiment is further improved on the basis of Example 1.
  • the influence of different battery safety evaluation parameters on battery safety is comprehensively considered.
  • the weight coefficient of each battery safety evaluation parameter is calculated
  • the training is optimized to improve the accuracy of the battery safety evaluation model.
  • the safety evaluation method also includes the training steps of the battery safety evaluation model, including:
  • Step 13 select multiple battery safety evaluation parameters
  • Step 14 collecting sample battery safety assessment variables of the sample vehicle battery;
  • the sample battery safety assessment variables include multiple sample variables corresponding to multiple battery safety assessment parameters;
  • Step 15 using the sample battery safety evaluation variables as input data to train the battery safety evaluation model to obtain the weight corresponding to each battery safety evaluation parameter in the battery safety evaluation model;
  • Step 16 Process a plurality of sample variables based on the weight corresponding to each battery safety evaluation parameter to obtain a quantitative result of the predicted safety evaluation of the sample vehicle battery.
  • the training set is used to obtain the model, and then each model is verified with the verification set to determine the error of the model.
  • the model parameters can be adjusted by means of information entropy to further improve the accuracy of the model.
  • you can use the cross-validation method to select the model use the training set data to estimate the parameters of all candidate models, and then use the validation set as the test sample, then calculate the forecast mean square error, compare the forecast mean square errors of each model, and select the forecast mean square.
  • the fitted model with the smallest error is the selection model.
  • Step 14 specifically includes:
  • sample data is trained based on the deep learning algorithm, and the data in the laboratory failure scenario and the real application scenario are comprehensively used to obtain a more accurate battery safety evaluation model.
  • the data center server in the cloud is used to train the battery safety evaluation model.
  • the battery safety evaluation model can be directly applied on the data center server; It can be used in vehicle controller or battery management system application; it can also be sent to the edge computing server of the power exchange station, and applied in the edge computing server.
  • the data center server in the cloud can continuously obtain the variables of the battery safety evaluation parameters after training the battery safety evaluation model, and update the battery safety evaluation when the accuracy of the battery safety evaluation model is lower than the preset threshold. evaluating the model; or, updating the battery safety evaluation model when the usage duration of the battery safety evaluation model is longer than a preset time duration. In this way, the timeliness of the battery safety evaluation model can be guaranteed and the accuracy of the battery safety evaluation model can be improved.
  • a safety evaluation system for a vehicle battery as shown in Figure 4, the safety evaluation system includes:
  • the real-time variable acquisition module 1 is used to acquire real-time battery safety assessment variables of the target vehicle battery
  • the evaluation result output module 2 is used to input the real-time battery safety evaluation variables into the battery safety evaluation model, and output the real-time safety evaluation quantitative results of the target vehicle battery through the battery safety evaluation model;
  • the battery safety evaluation model is trained with the sample battery safety evaluation variables of the sample vehicle battery as input, and the battery safety evaluation model outputs the quantitative results of the predicted safety evaluation of the sample vehicle battery during training.
  • the raw data from which the real-time battery safety assessment variables are derived can be collected through the battery management system, and the raw data from which the sample battery safety assessment variables are derived can also be collected through the battery management system.
  • the battery safety evaluation model can be stored in the electric vehicle, such as the battery management system or the vehicle controller, so that the safety evaluation method of the vehicle battery can be implemented in the electric vehicle;
  • the edge computing server of the power station so that the safety assessment method of the vehicle battery can be executed at the power station;
  • the battery safety assessment model can also be stored in the cloud, such as a data center server, so that the safety assessment method of the vehicle battery can be executed in the cloud.
  • data can be collected through the vehicle's own battery management system (BMS), on the one hand, it is used for local calculation to obtain quantitative results of real-time safety assessment, and on the other hand, the data is aggregated to a remote data center, Further, based on the big data basic platform, the data can be used to continuously optimize the model and improve the prediction accuracy.
  • BMS battery management system
  • the real-time battery safety assessment variable includes a plurality of real-time variables corresponding to a plurality of battery safety assessment parameters.
  • the battery safety evaluation parameter is a parameter based on which the battery safety evaluation is based, and the specific value of the parameter is a variable.
  • the battery safety assessment parameters include at least one of voltage, temperature, humidity, current, smoke, salt spray, vibration, and altitude, and correspondingly, the real-time variables include voltage value, temperature value, humidity value, current value, smoke value, salt spray value , at least one of a vibration value, and an altitude value.
  • the evaluation result output module 2 is used to input multiple real-time variables into the battery safety evaluation model, and through the battery safety evaluation model, the multiple real-time variables are processed based on the weights corresponding to each battery safety evaluation parameter to obtain the processing results, and according to all The processing result obtains the real-time safety assessment quantification result of the target vehicle battery and outputs it.
  • the quantified result of the real-time safety assessment is the real-time battery thermal runaway probability
  • the battery safety assessment model specifically processes the real-time battery safety assessment variables according to the following formula to obtain the real-time battery thermal runaway probability, which specifically includes:
  • y i is the real-time battery thermal runaway probability at the ith second or minute, is the normalized or floating point or scaled value of the nth real-time variable at the ith second or minute, is the weight of the nth battery safety evaluation parameter at the ith second or minute.
  • the security assessment system also includes a data preprocessing module 3;
  • the data preprocessing module 3 is used to perform noise reduction and/or deviation correction processing on the real-time battery safety assessment variables
  • the data preprocessing module 3 is also used to perform normalization processing, floating point processing or scaling processing on the real-time battery safety assessment variables.
  • the quantification result of the real-time safety assessment can be judged by a threshold value to determine whether the target vehicle battery is abnormal.
  • the user performs inspection or maintenance in time, and the battery safety evaluation model is applied to the vehicle controller and/or battery management system.
  • the safety evaluation system also includes:
  • the alarm module 4 is configured to issue an alarm signal when the quantitative result of the real-time safety assessment indicates that the target vehicle battery is abnormal.
  • the warning can be provided by a vehicle instrument.
  • the alarm information is sent to the vehicle controller of the electric vehicle, and the vehicle instrument panel is used for warning through the vehicle controller.
  • the alarm information can be sent to the monitoring platform, and the warning can be displayed on the monitoring screen through the monitoring platform.
  • the vehicle battery is monitored in real time based on the trained battery safety evaluation model, the real-time battery safety evaluation variables are obtained and then input to the battery safety evaluation model, and the real-time safety evaluation quantification result is output.
  • Results The battery safety performance of any electric vehicle at any point in time was evaluated in order to effectively monitor the safety performance of the battery.
  • the safety assessment system for vehicle batteries in this embodiment is further improved on the basis of Embodiment 3, and comprehensively considers the impact of different battery safety assessment parameters on battery safety.
  • the weight coefficient of each battery safety assessment parameter is calculated
  • the training is optimized to improve the accuracy of the battery safety evaluation model.
  • the safety evaluation system also includes a training module 5.
  • the training module 5 specifically includes:
  • the evaluation parameter selection unit 51 is used to select a plurality of battery safety evaluation parameters
  • a collection unit 52 configured to collect sample battery safety assessment variables of the sample vehicle battery;
  • the sample battery safety assessment variables include a plurality of sample variables corresponding to a plurality of battery safety assessment parameters;
  • the weight obtaining unit 53 is used to train the battery safety evaluation model by using the sample battery safety evaluation variable as input data, so as to obtain the weight corresponding to each battery safety evaluation parameter in the battery safety evaluation model;
  • the evaluation result output unit 54 is configured to process a plurality of sample variables based on the weight corresponding to each battery safety evaluation parameter, so as to obtain a quantitative result of the predicted safety evaluation of the sample vehicle battery.
  • the training set is used to obtain the model, and then the validation set is used to verify each model to determine the error of the model.
  • the model parameters can be adjusted by means of information entropy to further improve the accuracy of the model.
  • you can use the cross-validation method to select the model use the training set data to estimate the parameters of all candidate models, and then use the validation set as the test sample, then calculate the forecast mean square error, compare the forecast mean square errors of each model, and select the forecast mean square.
  • the fitted model with the smallest error is the selection model.
  • the battery safety evaluation model is trained using the data from laboratory failure scenarios and real application scenarios;
  • the collection unit 52 is used to obtain the experimental data of the sample vehicle battery under the laboratory failure scenario, and extract the battery characteristic data from the experimental data to generate the sample battery safety evaluation variable;
  • the collection unit 52 is further configured to acquire historical data of the sample vehicle battery in a real application scenario, and extract battery characteristic data from the historical data to generate a sample battery safety evaluation variable.
  • the sample data is trained based on the deep learning algorithm, and the data in the laboratory failure scenario and the real application scenario are used comprehensively to obtain a more accurate battery safety evaluation model.
  • the data center server in the cloud is used to train the battery safety evaluation model.
  • the battery safety evaluation model can be directly applied on the data center server; It can be used in vehicle controller or battery management system application; it can also be sent to the edge computing server of the power exchange station, and applied in the edge computing server.
  • the data center server in the cloud can continuously obtain the variables of the battery safety evaluation parameters after training the battery safety evaluation model, and update the battery safety evaluation when the accuracy of the battery safety evaluation model is lower than the preset threshold. evaluating the model; or, updating the battery safety evaluation model when the usage duration of the battery safety evaluation model is longer than a preset time duration. In this way, the timeliness of the battery safety evaluation model can be guaranteed and the accuracy of the battery safety evaluation model can be improved.
  • An electronic device comprising a memory, a processor and a computer program stored on the memory and running on the processor, when the processor executes the computer program, the safety of the vehicle battery described in Embodiment 1 or 2 is realized assessment method.
  • FIG. 6 is a schematic structural diagram of an electronic device provided in this embodiment.
  • Figure 6 shows a block diagram of an exemplary electronic device 90 suitable for use in implementing embodiments of the present invention.
  • the electronic device 90 shown in FIG. 6 is only an example, and should not impose any limitations on the function and scope of use of the embodiments of the present invention.
  • the electronic device 90 may take the form of a general-purpose computing device, for example, it may be a server device.
  • Components of the electronic device 90 may include, but are not limited to, at least one processor 91 , at least one memory 92 , a bus 93 connecting different system components (including the memory 92 and the processor 91 ).
  • the bus 93 includes a data bus, an address bus and a control bus.
  • Memory 92 may include volatile memory, such as random access memory (RAM) 921 and/or cache memory 922 , and may further include read only memory (ROM) 923 .
  • RAM random access memory
  • ROM read only memory
  • Memory 92 may also include program tools 925 having a set (at least one) of program modules 924 including, but not limited to, an operating system, one or more application programs, other program modules, and program data, in these examples Each or some combination of may include an implementation of a network environment.
  • the processor 91 executes various functional applications and data processing by executing computer programs stored in the memory 92 .
  • the electronic device 90 may also communicate with one or more external devices 94 (eg, keyboards, pointing devices, etc.). Such communication may take place through input/output (I/O) interface 95 . Also, the electronic device 90 may communicate with one or more networks (eg, a local area network (LAN), a wide area network (WAN), and/or a public network such as the Internet) through a network adapter 96 . Network adapter 96 communicates with other modules of electronic device 90 via bus 93 . It should be understood that, although not shown, other hardware and/or software modules may be used in conjunction with electronic device 90, including but not limited to: microcode, device drivers, redundant processors, external disk drive arrays, RAID (array of disks) systems, tape drives, and data backup storage systems.
  • RAID array of disks
  • the readable storage medium may include, but is not limited to, a portable disk, a hard disk, a random access memory, a read-only memory, an erasable programmable read-only memory, an optical storage device, a magnetic storage device, or any of the above suitable combination.
  • the present invention can also be implemented in the form of a program product, which includes program codes, when the program product runs on a terminal device, the program code is used to cause the terminal device to execute the implementation The steps of the safety assessment method for a vehicle battery described in Embodiment 1 or 2.
  • the program code for executing the present invention can be written in any combination of one or more programming languages, and the program code can be completely executed on the user equipment, partially executed on the user equipment, as an independent
  • the software package executes on the user's device, partly on the user's device, partly on the remote device, or entirely on the remote device.

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Human Resources & Organizations (AREA)
  • Physics & Mathematics (AREA)
  • Strategic Management (AREA)
  • Economics (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Tourism & Hospitality (AREA)
  • Entrepreneurship & Innovation (AREA)
  • General Business, Economics & Management (AREA)
  • Development Economics (AREA)
  • Marketing (AREA)
  • Game Theory and Decision Science (AREA)
  • Quality & Reliability (AREA)
  • Operations Research (AREA)
  • Educational Administration (AREA)
  • Evolutionary Computation (AREA)
  • General Health & Medical Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Primary Health Care (AREA)
  • General Engineering & Computer Science (AREA)
  • Artificial Intelligence (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Biology (AREA)
  • Computer Security & Cryptography (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Medical Informatics (AREA)
  • Software Systems (AREA)
  • Computer Hardware Design (AREA)
  • Geometry (AREA)
  • Secondary Cells (AREA)
  • Electric Propulsion And Braking For Vehicles (AREA)

Abstract

一种车用电池的安全评估方法，包括：获取目标车用电池的实时电池安全评估变量；将实时电池安全评估变量输入电池安全评估模型，通过电池安全评估模型输出目标车用电池的实时安全评估量化结果；电池安全评估模型以样本车用电池的样本电池安全评估变量为输入训练得到，电池安全评估模型在训练时输出样本车用电池的预测安全评估量化结果。本申请涉及电池评估领域，其基于训练好的电池安全评估模型对车用电池进行实时监控，基于实时安全评估量化结果实现对电池安全性能有效监控。此外，还公开了实现方法的安全评估系统，电子设备及计算机可读存储介质。

Description

车用电池的安全评估方法、系统、设备及可读存储介质
本申请要求申请日为2020/12/31的中国专利申请2020116187579的优先权。本申请引用上述中国专利申请的全文。
技术领域
本发明属于电池评估领域，特别涉及一种车用电池的安全评估方法、系统、设备及可读存储介质。
背景技术
在新能源汽车产业高速发展的同时，汽车用动力蓄电池的安全性备受关注。为确保蓄电池单体、电池包或系统的基本安全要求，在如振动、机械冲击、碰撞、挤压、湿热循环、浸水、热稳定性、温度冲击、盐雾、高海拔、过温、过流、过充、过放、外部短路等环境下，都给出了规范试验指导。而在实际运行过程中，缺乏有效的方法实时对电池的安全性进行监控，存在一定的安全隐患。
发明内容
本发明要解决的技术问题是为了克服现有技术中缺乏有效的方法实时对车用电池的安全性进行监控，存在一定的安全隐患的缺陷，提供一种车用电池的安全评估方法、系统、设备及可读存储介质。
本发明是通过下述技术方案来解决上述技术问题：
一种车用电池的安全评估方法，所述安全评估方法包括：
获取目标车用电池的实时电池安全评估变量；
将所述实时电池安全评估变量输入电池安全评估模型，通过所述电池安全评估模型输出所述目标车用电池的实时安全评估量化结果；
所述电池安全评估模型以样本车用电池的样本电池安全评估变量为输入训练得到，所述电池安全评估模型在训练时输出所述样本车用电池的预测安全评估量化结果。
本实施方式中，事先采用样本车用电池的样本电池安全评估变量训练电池安全评估模型，使得电池安全评估模型学会基于电池安全评估变量进电池安全评估的能力，再基于训练好的电池安全评估模型对车用电池进行实时监控，获取实时的电池安全评估变量后输入电池安全评估模型，输出实时安全评估量化结果，进而，可以基于实时安全评估 量化结果对任一电动车任一时间点的电池安全性能进行评估，以实现对电池的安全性能有效监控。
较佳地，所述实时电池安全评估变量包括与多个电池安全评估参数对应的多个实时变量；
所述将所述实时电池安全评估变量输入电池安全评估模型，通过所述电池安全评估模型输出所述目标车用电池的实时安全评估量化结果的步骤具体包括：
将多个所述实时变量输入所述电池安全评估模型；
通过所述电池安全评估模型，基于与每个电池安全评估参数对应的权重对所述多个实时变量进行处理得到处理结果，及根据所有处理结果得到所述目标车用电池的实时安全评估量化结果并输出。
本实施方式中，实时电池安全评估变量包括与多个电池安全评估参数对应的多个实时变量，这样可以从多个数据维度进行电池安全评估，提高电池安全评估的准确性；而且在采用多个数据维度的电池安全评估参数时，还考虑到不同数据维度的电池安全评估参数对电池安全评估的影响程度不同，基于与每个电池安全评估参数对应的权重对多个实时变量进行处理，进一步提高了电池安全评估的准确性和可信度。
较佳地，所述安全评估方法还包括所述电池安全评估模型的训练步骤，所述训练步骤包括：
选取多个电池安全评估参数；
收集样本车用电池的样本电池安全评估变量；所述样本电池安全评估变量包括与所述多个电池安全评估参数对应的多个样本变量；
将所述样本电池安全评估变量作为输入数据训练所述电池安全评估模型，以得到所述电池安全评估模型中与每个电池安全评估参数对应的权重；
基于与每个电池安全评估参数对应的权重对所述多个样本变量进行处理，以得到所述样本车用电池的预测安全评估量化结果。
本实施方式中，综合考虑不同电池安全评估参数对电池安全性的影响，训练中，对每个电池安全评估参数的权重系数进行训练优化，以提高电池安全评估模型的准确度。
较佳地，所述收集样本车用电池的样本电池安全评估变量的步骤具体包括：
获取样本车用电池在实验室故障场景下的实验数据，并从所述实验数据中提取电池特征数据生成所述样本电池安全评估变量；
和/或，
获取样本车用电池在现实应用场景下的历史数据，并从所述历史数据中提取电池特 征数据生成所述样本电池安全评估变量。
本实施方式中，为确保训练数据的全面性和真实性，综合使用实验室故障场景和现实应用场景下的数据对电池安全评估模型进行训练。
较佳地，所述获取目标车用电池的实时电池安全评估变量的步骤之后，所述安全评估方法还包括：
对所述实时电池安全评估变量进行降噪和/或纠偏处理；
和/或，
对所述实时电池安全评估变量进行归一化处理或浮点处理或标度化处理。
本实施方式中，为去除数据中可能的不准确数据或干扰数据，对数据进行降噪和/或纠偏处理以去除干扰数据，另外，为方便数据处理，对数据进行归一化处理或浮点处理或标度化处理以确保数据统一性。
较佳地，所述实时安全评估量化结果为实时电池热失控概率，所述电池安全评估模型具体按照以下公式对所述实时电池安全评估变量进行处理，得到实时电池热失控概率，具体包括：
Figure PCTCN2021143092-appb-000001
Figure PCTCN2021143092-appb-000002
Figure PCTCN2021143092-appb-000003
其中，y i为第i秒或分钟时的实时电池热失控概率，
Figure PCTCN2021143092-appb-000004
为第i秒或分钟时的第n个实时变量归一化处理或浮点处理或标度化处理后的值，
Figure PCTCN2021143092-appb-000005
为第i秒或分钟时第n个电池安全评估参数的权重。
本实施方式中，提供了具体场景下的实时电池热失控概率计算方式，使得实时电池热失控概率的计算关系明了，计算结果更具说服力。
较佳地，所述电池安全评估模型应用于车辆控制器和/或电池管理系统，所述安全评估方法还包括：
在所述实时安全评估量化结果表示所述目标车用电池异常时，发出警报信号。
本实施方式中，可以通过阈值对实时安全评估量化结果进行判定，以确定目标车用电池是否异常，当实时安全评估量化结果表示目标车用电池异常时，并在超出阈值时及时发出警报信息以便用户及时进行检测或维护。
一种车用电池的安全评估系统，所述安全评估系统包括：
实时变量获取模块，用于获取目标车用电池的实时电池安全评估变量；
评估结果输出模块，用于将所述实时电池安全评估变量输入电池安全评估模型，通 过所述电池安全评估模型输出所述目标车用电池的实时安全评估量化结果；
所述电池安全评估模型以样本车用电池的样本电池安全评估变量为输入训练得到，所述电池安全评估模型在训练时输出所述样本车用电池的预测安全评估量化结果。
本实施方式中，事先采用样本车用电池的样本电池安全评估变量训练电池安全评估模型，使得电池安全评估模型学会基于电池安全评估变量进电池安全评估的能力，再基于训练好的电池安全评估模型对车用电池进行实时监控，获取实时的电池安全评估变量后输入电池安全评估模型，输出实时安全评估量化结果，进而，可以基于实时安全评估量化结果对任一电动车任一时间点的电池安全性能进行评估，以实现对电池的安全性能有效监控。
较佳地，所述实时电池安全评估变量包括与多个电池安全评估参数对应的多个实时变量；
所述评估结果输出模块用于将多个所述实时变量输入所述电池安全评估模型；并通过所述电池安全评估模型，基于与每个电池安全评估参数对应的权重对所述多个实时变量进行处理得到处理结果，及根据所有处理结果得到所述目标车用电池的实时安全评估量化结果并输出。
本实施方式中，实时电池安全评估变量包括与多个电池安全评估参数对应的多个实时变量，这样可以从多个数据维度进行电池安全评估，提高电池安全评估的准确性；而且在采用多个数据维度的电池安全评估参数时，还考虑到不同数据维度的电池安全评估参数对电池安全评估的影响程度不同，基于与每个电池安全评估参数对应的权重对多个实时变量进行处理，进一步提高了电池安全评估的准确性和可信度。
较佳地，所述安全评估系统还包括训练模块，所述训练模块具体包括：
评估参数选取单元，用于选取多个电池安全评估参数；
收集单元，用于收集样本车用电池的样本电池安全评估变量；所述样本电池安全评估变量包括与所述多个电池安全评估参数对应的多个样本变量；
权重获取单元，用于将所述样本电池安全评估变量作为输入数据训练所述电池安全评估模型，以得到所述电池安全评估模型中与每个电池安全评估参数对应的权重；
评估结果输出单元，用于基于与每个电池安全评估参数对应的权重对所述多个样本变量进行处理，以得到所述样本车用电池的预测安全评估量化结果。
本实施方式中，综合考虑不同电池安全评估参数对电池安全性的影响，训练中，对每个电池安全评估参数的权重系数进行训练优化，以提高电池安全评估模型的准确度。
较佳地，所述收集单元用于获取样本车用电池在实验室故障场景下的实验数据，并 从所述实验数据中提取电池特征数据生成所述样本电池安全评估变量；
和/或，
所述收集单元用于获取样本车用电池在现实应用场景下的历史数据，并从所述历史数据中提取电池特征数据生成所述样本电池安全评估变量。
本实施方式中，为确保训练数据的全面性和真实性，综合使用实验室故障场景和现实应用场景下的数据对电池安全评估模型进行训练。
较佳地，所述安全评估方法还包括数据预处理模块；
所述数据预处理模块用于对所述实时电池安全评估变量进行降噪和/或纠偏处理；
和/或，
所述数据预处理模块用于对所述实时电池安全评估变量进行归一化处理或浮点处理或标度化处理。
本实施方式中，为去除数据中可能的不准确数据或干扰数据，对数据进行降噪和/或纠偏处理以去除干扰数据，另外，为方便数据处理，对数据进行归一化处理或浮点处理或标度化处理以确保数据统一性。
较佳地，所述实时安全评估量化结果为实时电池热失控概率，所述电池安全评估模型具体按照以下公式对所述实时电池安全评估变量进行处理，得到实时电池热失控概率，具体包括：
Figure PCTCN2021143092-appb-000006
Figure PCTCN2021143092-appb-000007
Figure PCTCN2021143092-appb-000008
其中，y i为第i秒或分钟时的实时电池热失控概率，
Figure PCTCN2021143092-appb-000009
为第i秒或分钟时的第n个实时变量归一化处理或浮点处理或标度化处理后的值，
Figure PCTCN2021143092-appb-000010
为第i秒或分钟时第n个电池安全评估参数的权重。
本实施方式中，提供了具体场景下的实时电池热失控概率计算方式，使得实时电池热失控概率的计算关系明了，计算结果更具说服力。
较佳地，所述电池安全评估模型应用于车辆控制器和/或电池管理系统，所述安全评估系统还包括：
警报模块，用于在所述实时安全评估量化结果表示所述目标车用电池异常时，发出警报信号。
本实施方式中，可以通过阈值对实时安全评估量化结果进行判定，以确定目标车用电池是否异常，当实时安全评估量化结果表示目标车用电池异常时，并在超出阈值时及 时发出警报信息以便用户及时进行检测或维护。
一种电子设备，包括存储器、处理器及存储在存储器上并可在处理器上运行的计算机程序，所述处理器执行所述计算机程序时实现上述的车用电池的安全评估方法。
一种计算机可读存储介质，其上存储有计算机程序，所述程序被处理器执行时实现上述的车用电池的安全评估方法的步骤。
本发明的积极进步效果在于：本申请基于训练好的电池安全评估模型对车用电池进行实时监控，获取实时的电池安全评估变量后输入电池安全评估模型，输出实时安全评估量化结果，进而，可以基于实时安全评估量化结果对任一电动车任一时间点的电池安全性能进行评估，以实现对电池的安全性能有效监控。
附图说明
图1为本发明实施例1的车用电池的安全评估方法的流程图。
图2为本发明实施例1的车用电池的安全评估方法中步骤20的流程图。
图3为本发明实施例2的车用电池的安全评估方法的流程图。
图4为本发明实施例3的车用电池的安全评估系统的模块示意图。
图5为本发明实施例4的车用电池的安全评估系统的模块示意图。
图6为本发明实施例5的电子设备的结构实体图。
具体实施方式
下面通过实施例的方式进一步说明本发明，但并不因此将本发明限制在所述的实施例范围之中。
实施例1
一种车用电池的安全评估方法，如图1，安全评估方法包括：
步骤10、获取目标车用电池的实时电池安全评估变量；
步骤20、将实时电池安全评估变量输入电池安全评估模型，通过电池安全评估模型输出目标车用电池的实时安全评估量化结果；
电池安全评估模型以样本车用电池的样本电池安全评估变量为输入训练得到，电池安全评估模型在训练时输出样本车用电池的预测安全评估量化结果。
需要说明的是，实时电池安全评估变量所源自的原始数据可通过电池管理系统采集，样本电池安全评估变量所源自的原始数据也可通过电池管理系统采集。电池安全评估模型可以存储在电动车辆中，比如电池管理系统或整车控制器，这样可在电动车辆中执行 该车用电池的安全评估方法；电池安全评估模型也可以存储在换电站，比如换电站的边缘计算服务器，这样可在换电站执行该车用电池的安全评估方法；电池安全评估模型还可以存储在云端，比如数据中心服务器，这样可以在云端执行该车用电池的安全评估方法。
在一种可实施的方式中，可以通过车辆自身的电池管理系统(BMS)来采集数据，一方面用于本地计算，获取实时安全评估量化结果，另一方面，将数据汇聚到远程数据中心，进一步可以基于大数据基础平台，利用数据持续优化模型，提高预测准确度。
其中，实时电池安全评估变量包括与多个电池安全评估参数对应的多个实时变量。其中，电池安全评估参数是对电池安全进行评估所基于的参数，参数的具体值为变量。电池安全评估参数包括电压、温度、湿度、电流、烟雾、盐雾、振动和海拔中的至少一个，相应地，实时变量包括电压值、温度值、湿度值、电流值、烟雾值、盐雾值、振动值和海拔值中的至少一个。如图2所示，步骤20具体包括：
步骤201、将多个实时变量输入电池安全评估模型；
步骤202、通过电池安全评估模型，基于与每个电池安全评估参数对应的权重对多个实时变量进行处理得到处理结果；其中，每个电池安全评估参数对应一个实时变量，每个电池安全评估参数对应一个权重。
步骤203、根据所有处理结果得到目标车用电池的实时安全评估量化结果并输出。
在一种具体实施的方式中，实时安全评估量化结果为实时电池热失控概率，电池安全评估模型具体按照以下公式对实时电池安全评估变量进行处理，得到实时电池热失控概率，具体包括：
Figure PCTCN2021143092-appb-000011
Figure PCTCN2021143092-appb-000012
Figure PCTCN2021143092-appb-000013
其中，y i为第i秒或分钟时的实时电池热失控概率，
Figure PCTCN2021143092-appb-000014
为第i秒或分钟时的第n个实时变量归一化处理或浮点处理或标度化处理后的值，
Figure PCTCN2021143092-appb-000015
为第i秒或分钟时第n个电池安全评估参数的权重。
本实施例中，为去除数据中可能的不准确数据或干扰数据，对数据进行降噪和/或纠偏处理以去除干扰数据，另外，为方便数据处理，对数据进行归一化处理或浮点处理或标度化处理以确保数据统一性，参见图1，步骤10之后，安全评估方法还包括：
步骤11、对实时电池安全评估变量进行降噪和/或纠偏处理；
步骤12、对实时电池安全评估变量进行归一化处理或浮点处理或标度化处理。
本实施例中，可以通过阈值对实时安全评估量化结果进行判定，以确定目标车用电池是否异常，当实时安全评估量化结果表示目标车用电池异常时，并在超出阈值时及时发出警报信息以便用户及时进行检测或维护，电池安全评估模型应用于车辆控制器和/或电池管理系统，参见图1，步骤20之后，安全评估方法还包括：
步骤30、在实时安全评估量化结果表示目标车用电池异常时，发出警报信号。
在一种具体实施的方式中，可以通过车辆仪表进行警示。比如，将报警信息发送至电动汽车的整车控制器，通过整车控制器在车辆仪表盘进行警示。另外还可以将报警信息发送至监控平台，通过监控平台在监控屏幕中警示。
本实施例中，基于训练好的电池安全评估模型对车用电池进行实时监控，获取实时的电池安全评估变量后输入电池安全评估模型，输出实时安全评估量化结果，进而，可以基于实时安全评估量化结果对任一电动车任一时间点的电池安全性能进行评估，以实现对电池的安全性能有效监控。
实施例2
本实施例的车用电池的安全评估方法是在实施例1的基础上进一步改进，综合考虑不同电池安全评估参数对电池安全性的影响，训练中，对每个电池安全评估参数的权重系数进行训练优化，以提高电池安全评估模型的准确度，如图3所示，步骤20之前，安全评估方法还包括电池安全评估模型的训练步骤，具体包括：
步骤13、选取多个电池安全评估参数；
步骤14、收集样本车用电池的样本电池安全评估变量；样本电池安全评估变量包括与多个电池安全评估参数对应的多个样本变量；
步骤15、将样本电池安全评估变量作为输入数据训练电池安全评估模型，以得到电池安全评估模型中与每个电池安全评估参数对应的权重；
步骤16、基于与每个电池安全评估参数对应的权重对多个样本变量进行处理，以得到样本车用电池的预测安全评估量化结果。
需要说明的是，在对电池安全评估模型进行训练的过程中，选取x％的数据作为训练集，选取剩余的y％的数据作为验证集，其中，x+y＝100。电池安全评估模型的训练中，以训练集进行训练得到模型，再以验证集对各模型进行验证确定模型的误差，进一步可以利用信息熵等方式对模型参数进行调整以进一步提高模型的精度，又或者，可以利用交叉验证方法选择模型，使用训练集数据对所有候选模型进行参数估计，再使用验证集为检验样本，然后计算预测均方误差，比较各个模型的预测均方误差，选择预测均方误差最小的拟合模型为选择模型。
另外，为确保训练数据的全面性和真实性，综合使用实验室故障场景和现实应用场景下的数据对电池安全评估模型进行训练，步骤14具体包括：
获取样本车用电池在实验室故障场景下的实验数据，并从实验数据中提取电池特征数据生成样本电池安全评估变量；
获取样本车用电池在现实应用场景下的历史数据，并从历史数据中提取电池特征数据生成样本电池安全评估变量。本实施例中，基于深度学习算法对样本数据进行训练，综合使用实验室故障场景和现实应用场景下的数据，训练得到更加精准的电池安全评估模型，进而，基于电池安全评估模型实现对任一电动车任一时间点的实时电池热失控概率预测，以实现对电池的安全性能的有效监控。
在上述实施方式中，云端的数据中心服务器用于训练电池安全评估模型，该电池安全评估模型在训练完成后，可直接在数据中心服务器应用；也可下发到电动汽车，在电动汽车的整车控制器或者电池管理系统应用；还可下发至换电站的边缘计算服务器，在边缘计算服务器应用。
在另外的实施方式中，云端的数据中心服务器在训练完成电池安全评估模型后，还可持续获取电池安全评估参数的变量，在电池安全评估模型的准确率低于预设阈值时，更新电池安全评估模型；或，在电池安全评估模型的使用时长高于预设时长时，更新电池安全评估模型。这样可以保障电池安全评估模型的时效性以及提高电池安全评估模型的准确率。
实施例3
一种车用电池的安全评估系统，如图4所示，安全评估系统包括：
实时变量获取模块1，用于获取目标车用电池的实时电池安全评估变量；
评估结果输出模块2，用于将实时电池安全评估变量输入电池安全评估模型，通过电池安全评估模型输出目标车用电池的实时安全评估量化结果；
电池安全评估模型以样本车用电池的样本电池安全评估变量为输入训练得到，电池安全评估模型在训练时输出样本车用电池的预测安全评估量化结果。
需要说明的是，实时电池安全评估变量所源自的原始数据可通过电池管理系统采集，样本电池安全评估变量所源自的原始数据也可通过电池管理系统采集。电池安全评估模型可以存储在电动车辆中，比如电池管理系统或整车控制器，这样可在电动车辆中执行该车用电池的安全评估方法；电池安全评估模型也可以存储在换电站，比如换电站的边缘计算服务器，这样可在换电站执行该车用电池的安全评估方法；电池安全评估模型还可以存储在云端，比如数据中心服务器，这样可以在云端执行该车用电池的安全评估方 法。
在一种可实施的方式中，可以通过车辆自身的电池管理系统(BMS)来采集数据，一方面用于本地计算，获取实时安全评估量化结果，另一方面，将数据汇聚到远程数据中心，进一步可以基于大数据基础平台，利用数据持续优化模型，提高预测准确度。
在一种可实施的方式中，实时电池安全评估变量包括与多个电池安全评估参数对应的多个实时变量。其中，电池安全评估参数是对电池安全进行评估所基于的参数，参数的具体值为变量。电池安全评估参数包括电压、温度、湿度、电流、烟雾、盐雾、振动和海拔中的至少一个，相应地，实时变量包括电压值、温度值、湿度值、电流值、烟雾值、盐雾值、振动值和海拔值中的至少一个。
评估结果输出模块2用于将多个实时变量输入电池安全评估模型，并通过电池安全评估模型，基于与每个电池安全评估参数对应的权重对多个实时变量进行处理得到处理结果，及根据所有处理结果得到目标车用电池的实时安全评估量化结果并输出。
在一种具体实施的方式中，实时安全评估量化结果为实时电池热失控概率，电池安全评估模型具体按照以下公式对实时电池安全评估变量进行处理，得到实时电池热失控概率，具体包括：
Figure PCTCN2021143092-appb-000016
Figure PCTCN2021143092-appb-000017
Figure PCTCN2021143092-appb-000018
其中，y i为第i秒或分钟时的实时电池热失控概率，
Figure PCTCN2021143092-appb-000019
为第i秒或分钟时的第n个实时变量归一化处理或浮点处理或标度化处理后的值，
Figure PCTCN2021143092-appb-000020
为第i秒或分钟时第n个电池安全评估参数的权重。
本实施例中，为去除数据中可能的不准确数据或干扰数据，对数据进行降噪和/或纠偏处理以去除干扰数据，另外，为方便数据处理，对数据进行归一化处理或浮点处理或标度化处理以确保数据统一性，安全评估系统还包括数据预处理模块3；
数据预处理模块3用于对实时电池安全评估变量进行降噪和/或纠偏处理；
数据预处理模块3还用于对实时电池安全评估变量进行归一化处理或浮点处理或标度化处理。
本实施例中，可以通过阈值对实时安全评估量化结果进行判定，以确定目标车用电池是否异常，当实时安全评估量化结果表示目标车用电池异常时，并在超出阈值时及时发出警报信息以便用户及时进行检测或维护，电池安全评估模型应用于车辆控制器和/或电池管理系统，安全评估系统还包括：
警报模块4，用于在实时安全评估量化结果表示目标车用电池异常时，发出警报信号。
在一种具体实施的方式中，可以通过车辆仪表进行警示。比如，将报警信息发送至电动汽车的整车控制器，通过整车控制器在车辆仪表盘进行警示。另外还可以将报警信息发送至监控平台，通过监控平台在监控屏幕中警示。
本实施例中，基于训练好的电池安全评估模型对车用电池进行实时监控，获取实时的电池安全评估变量后输入电池安全评估模型，输出实时安全评估量化结果，进而，可以基于实时安全评估量化结果对任一电动车任一时间点的电池安全性能进行评估，以实现对电池的安全性能有效监控。
实施例4
本实施例的车用电池的安全评估系统是在实施例3的基础上进一步改进，综合考虑不同电池安全评估参数对电池安全性的影响，训练中，对每个电池安全评估参数的权重系数进行训练优化，以提高电池安全评估模型的准确度，如图5所示，安全评估系统还包括训练模块5，训练模块5具体包括：
评估参数选取单元51，用于选取多个电池安全评估参数；
收集单元52，用于收集样本车用电池的样本电池安全评估变量；样本电池安全评估变量包括与多个电池安全评估参数对应的多个样本变量；
权重获取单元53，用于将样本电池安全评估变量作为输入数据训练电池安全评估模型，以得到电池安全评估模型中与每个电池安全评估参数对应的权重；
评估结果输出单元54，用于基于与每个电池安全评估参数对应的权重对多个样本变量进行处理，以得到样本车用电池的预测安全评估量化结果。
需要说明的是，在对电池安全评估模型进行训练的过程中，选取x％的数据作为训练集，选取剩余的y％的数据作为验证集，其中，x+y＝100。电池安全评估模型的训练中，以训练集进行训练得到模型，再以验证集对各模型进行验证确定模型的误差，进一步可以利用信息熵等方式对模型参数进行调整以进一步提高模型的精度，又或者，可以利用交叉验证方法选择模型，使用训练集数据对所有候选模型进行参数估计，再使用验证集为检验样本，然后计算预测均方误差，比较各个模型的预测均方误差，选择预测均方误差最小的拟合模型为选择模型。
另外，为确保训练数据的全面性和真实性，综合使用实验室故障场景和现实应用场景下的数据对电池安全评估模型进行训练；
收集单元52用于获取样本车用电池在实验室故障场景下的实验数据，并从实验数据 中提取电池特征数据生成样本电池安全评估变量；
收集单元52还用于获取样本车用电池在现实应用场景下的历史数据，并从历史数据中提取电池特征数据生成样本电池安全评估变量。
本实施例中，基于深度学习算法对样本数据进行训练，综合使用实验室故障场景和现实应用场景下的数据，训练得到更加精准的电池安全评估模型，进而，基于电池安全评估模型实现对任一电动车任一时间点的实时电池热失控概率预测，以实现对电池的安全性能的有效监控。
在上述实施方式中，云端的数据中心服务器用于训练电池安全评估模型，该电池安全评估模型在训练完成后，可直接在数据中心服务器应用；也可下发到电动汽车，在电动汽车的整车控制器或者电池管理系统应用；还可下发至换电站的边缘计算服务器，在边缘计算服务器应用。
在另外的实施方式中，云端的数据中心服务器在训练完成电池安全评估模型后，还可持续获取电池安全评估参数的变量，在电池安全评估模型的准确率低于预设阈值时，更新电池安全评估模型；或，在电池安全评估模型的使用时长高于预设时长时，更新电池安全评估模型。这样可以保障电池安全评估模型的时效性以及提高电池安全评估模型的准确率。
实施例5
一种电子设备，包括存储器、处理器及存储在存储器上并可在处理器上运行的计算机程序，所述处理器执行所述计算机程序时实现实施例1或2所述的车用电池的安全评估方法。
图6为本实施例提供的一种电子设备的结构示意图。图6示出了适于用来实现本发明实施方式的示例性电子设备90的框图。图6显示的电子设备90仅仅是一个示例，不应对本发明实施例的功能和使用范围带来任何限制。
如图6所示，电子设备90可以以通用计算设备的形式表现，例如其可以为服务器设备。电子设备90的组件可以包括但不限于：至少一个处理器91、至少一个存储器92、连接不同系统组件(包括存储器92和处理器91)的总线93。
总线93包括数据总线、地址总线和控制总线。
存储器92可以包括易失性存储器，例如随机存取存储器(RAM)921和/或高速缓存存储器922，还可以进一步包括只读存储器(ROM)923。
存储器92还可以包括具有一组(至少一个)程序模块924的程序工具925，这样的程序模块924包括但不限于：操作系统、一个或者多个应用程序、其它程序模块以及程 序数据，这些示例中的每一个或某种组合中可能包括网络环境的实现。
处理器91通过运行存储在存储器92中的计算机程序，从而执行各种功能应用以及数据处理。
电子设备90也可以与一个或多个外部设备94(例如键盘、指向设备等)通信。这种通信可以通过输入/输出(I/O)接口95进行。并且，电子设备90还可以通过网络适配器96与一个或者多个网络(例如局域网(LAN)，广域网(WAN)和/或公共网络，例如因特网)通信。网络适配器96通过总线93与电子设备90的其它模块通信。应当明白，尽管图中未示出，可以结合电子设备90使用其它硬件和/或软件模块，包括但不限于：微代码、设备驱动器、冗余处理器、外部磁盘驱动阵列、RAID(磁盘阵列)系统、磁带驱动器以及数据备份存储系统等。
应当注意，尽管在上文详细描述中提及了电子设备的若干单元/模块或子单元/模块，但是这种划分仅仅是示例性的并非强制性的。实际上，根据本申请的实施方式，上文描述的两个或更多单元/模块的特征和功能可以在一个单元/模块中具体化。反之，上文描述的一个单元/模块的特征和功能可以进一步划分为由多个单元/模块来具体化。
实施例6
一种计算机可读存储介质，其上存储有计算机程序，所述程序被处理器执行时实现实施例1或2所述的车用电池的安全评估方法的步骤。
其中，可读存储介质可以采用的更具体可以包括但不限于：便携式盘、硬盘、随机存取存储器、只读存储器、可擦拭可编程只读存储器、光存储器件、磁存储器件或上述的任意合适的组合。
在可能的实施方式中，本发明还可以实现为一种程序产品的形式，其包括程序代码，当所述程序产品在终端设备上运行时，所述程序代码用于使所述终端设备执行实现实施例1或2所述的车用电池的安全评估方法的步骤。
其中，可以以一种或多种程序设计语言的任意组合来编写用于执行本发明的程序代码，所述程序代码可以完全地在用户设备上执行、部分地在用户设备上执行、作为一个独立的软件包执行、部分在用户设备上部分在远程设备上执行或完全在远程设备上执行。
虽然以上描述了本发明的具体实施方式，但是本领域的技术人员应当理解，这仅是举例说明，本发明的保护范围是由所附权利要求书限定的。本领域的技术人员在不背离本发明的原理和实质的前提下，可以对这些实施方式做出多种变更或修改，但这些变更和修改均落入本发明的保护范围。

Claims (10)

  1. 一种车用电池的安全评估方法，其特征在于，所述安全评估方法包括：
    获取目标车用电池的实时电池安全评估变量；
    将所述实时电池安全评估变量输入电池安全评估模型，通过所述电池安全评估模型输出所述目标车用电池的实时安全评估量化结果；
    所述电池安全评估模型以样本车用电池的样本电池安全评估变量为输入训练得到，所述电池安全评估模型在训练时输出所述样本车用电池的预测安全评估量化结果。
  2. 如权利要求1所述的车用电池的安全评估方法，其特征在于，所述实时电池安全评估变量包括与多个电池安全评估参数对应的多个实时变量；
    所述将所述实时电池安全评估变量输入电池安全评估模型，通过所述电池安全评估模型输出所述目标车用电池的实时安全评估量化结果的步骤具体包括：
    将多个所述实时变量输入所述电池安全评估模型；
    通过所述电池安全评估模型，基于与每个电池安全评估参数对应的权重对所述多个实时变量进行处理得到处理结果，及根据所有处理结果得到所述目标车用电池的实时安全评估量化结果并输出。
  3. 如权利要求2所述的车用电池的安全评估方法，其特征在于，所述安全评估方法还包括所述电池安全评估模型的训练步骤，所述训练步骤包括：
    选取多个电池安全评估参数；
    收集样本车用电池的样本电池安全评估变量；所述样本电池安全评估变量包括与所述多个电池安全评估参数对应的多个样本变量；
    将所述样本电池安全评估变量作为输入数据训练所述电池安全评估模型，以得到所述电池安全评估模型中与每个电池安全评估参数对应的权重；
    基于与每个电池安全评估参数对应的权重对所述多个样本变量进行处理，以得到所述样本车用电池的预测安全评估量化结果。
  4. 如权利要求3所述的车用电池的安全评估方法，其特征在于，所述收集样本车用电池的样本电池安全评估变量的步骤具体包括：
    获取样本车用电池在实验室故障场景下的实验数据，并从所述实验数据中提取电池特征数据生成所述样本电池安全评估变量；
    和/或，
    获取样本车用电池在现实应用场景下的历史数据，并从所述历史数据中提取电池特 征数据生成所述样本电池安全评估变量。
  5. 如权利要求1-4中至少一项所述的车用电池的安全评估方法，其特征在于，所述获取目标车用电池的实时电池安全评估变量的步骤之后，所述安全评估方法还包括：
    对所述实时电池安全评估变量进行降噪和/或纠偏处理；
    和/或，
    对所述实时电池安全评估变量进行归一化处理或浮点处理或标度化处理。
  6. 如权利要求2-5中至少一项所述的车用电池的安全评估方法，其特征在于，所述实时安全评估量化结果为实时电池热失控概率，所述电池安全评估模型具体按照以下公式对所述实时电池安全评估变量进行处理，得到实时电池热失控概率，具体包括：
    Figure PCTCN2021143092-appb-100001
    Figure PCTCN2021143092-appb-100002
    Figure PCTCN2021143092-appb-100003
    其中，y i为第i秒或分钟时的实时电池热失控概率，
    Figure PCTCN2021143092-appb-100004
    为第i秒或分钟时的第n个实时变量归一化处理或浮点处理或标度化处理后的值，
    Figure PCTCN2021143092-appb-100005
    为第i秒或分钟时第n个电池安全评估参数的权重。
  7. 如权利要求1-6中至少一项所述的车用电池的安全评估方法，其特征在于，所述电池安全评估模型应用于车辆控制器和/或电池管理系统，所述安全评估方法还包括：
    在所述实时安全评估量化结果表示所述目标车用电池异常时，发出警报信号。
  8. 一种车用电池的安全评估系统，其特征在于，所述安全评估系统包括：
    实时变量获取模块，用于获取目标车用电池的实时电池安全评估变量；
    评估结果输出模块，用于将所述实时电池安全评估变量输入电池安全评估模型，通过所述电池安全评估模型输出所述目标车用电池的实时安全评估量化结果；
    所述电池安全评估模型以样本车用电池的样本电池安全评估变量为输入训练得到，所述电池安全评估模型在训练时输出所述样本车用电池的预测安全评估量化结果。
  9. 一种电子设备，包括存储器、处理器及存储在存储器上并可在处理器上运行的计算机程序，其特征在于，所述处理器执行所述计算机程序时实现权利要求1至7中至少一项所述的车用电池的安全评估方法。
  10. 一种计算机可读存储介质，其上存储有计算机程序，其特征在于，所述程序被处理器执行时实现权利要求1至7中至少一项所述的车用电池的安全评估方法的步骤。
PCT/CN2021/143092 2020-12-31 2021-12-30 车用电池的安全评估方法、系统、设备及可读存储介质 WO2022143903A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202011618757.9 2020-12-31
CN202011618757.9A CN114692926A (zh) 2020-12-31 2020-12-31 车用电池的安全评估方法、系统、设备及可读存储介质

Publications (1)

Publication Number Publication Date
WO2022143903A1 true WO2022143903A1 (zh) 2022-07-07

Family

ID=82133756

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/143092 WO2022143903A1 (zh) 2020-12-31 2021-12-30 车用电池的安全评估方法、系统、设备及可读存储介质

Country Status (2)

Country Link
CN (1) CN114692926A (zh)
WO (1) WO2022143903A1 (zh)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116613867A (zh) * 2023-07-20 2023-08-18 西安峰盛智能电子有限公司 用于agv的无线电能传输系统及其控制方法
CN116952751A (zh) * 2023-09-20 2023-10-27 中国汽车技术研究中心有限公司 一种电池包损伤测评方法、系统及设备
CN117872166A (zh) * 2024-03-11 2024-04-12 广东采日能源科技有限公司 储能电池热失控检测方法、装置及电子设备

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109711007A (zh) * 2018-12-11 2019-05-03 北京匠芯电池科技有限公司 动力锂离子电池安全性能无损诊断的方法
CN109932663A (zh) * 2019-03-07 2019-06-25 清华四川能源互联网研究院 电池健康状态评估方法、装置、存储介质及电子装置
CN109978229A (zh) * 2019-02-12 2019-07-05 常伟 一种对动力电池组全电芯多点温度及连接点温度进行热失控预测的方法
US20200341065A1 (en) * 2019-04-26 2020-10-29 Panasonic Intellectual Property Management Co., Ltd. Safety estimation device for batteries and safety estimation method for batteries
CN111983468A (zh) * 2020-08-24 2020-11-24 哈尔滨理工大学 基于神经网络的锂动力电池的安全度估算方法

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109711007A (zh) * 2018-12-11 2019-05-03 北京匠芯电池科技有限公司 动力锂离子电池安全性能无损诊断的方法
CN109978229A (zh) * 2019-02-12 2019-07-05 常伟 一种对动力电池组全电芯多点温度及连接点温度进行热失控预测的方法
CN109932663A (zh) * 2019-03-07 2019-06-25 清华四川能源互联网研究院 电池健康状态评估方法、装置、存储介质及电子装置
US20200341065A1 (en) * 2019-04-26 2020-10-29 Panasonic Intellectual Property Management Co., Ltd. Safety estimation device for batteries and safety estimation method for batteries
CN111983468A (zh) * 2020-08-24 2020-11-24 哈尔滨理工大学 基于神经网络的锂动力电池的安全度估算方法

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116613867A (zh) * 2023-07-20 2023-08-18 西安峰盛智能电子有限公司 用于agv的无线电能传输系统及其控制方法
CN116613867B (zh) * 2023-07-20 2023-12-26 上海木链工业互联网科技有限公司 用于agv的无线电能传输系统及其控制方法
CN116952751A (zh) * 2023-09-20 2023-10-27 中国汽车技术研究中心有限公司 一种电池包损伤测评方法、系统及设备
CN116952751B (zh) * 2023-09-20 2023-12-15 中国汽车技术研究中心有限公司 一种电池包损伤测评方法、系统及设备
CN117872166A (zh) * 2024-03-11 2024-04-12 广东采日能源科技有限公司 储能电池热失控检测方法、装置及电子设备
CN117872166B (zh) * 2024-03-11 2024-05-14 广东采日能源科技有限公司 储能电池热失控检测方法、装置及电子设备

Also Published As

Publication number Publication date
CN114692926A (zh) 2022-07-01

Similar Documents

Publication Publication Date Title
WO2022143903A1 (zh) 车用电池的安全评估方法、系统、设备及可读存储介质
CN111241154B (zh) 一种基于大数据的蓄电池故障预警方法及系统
Hong et al. Vehicle energy system active defense: a health assessment of lithium‐ion batteries
WO2022253038A1 (zh) 基于弹性网的锂电池健康状态预测方法、系统、设备及介质
CN114371409B (zh) 电池状态预测模型的训练方法、电池状态预测方法及装置
CN114148216A (zh) 电池自放电率异常检测方法、系统、设备及存储介质
CN115291116A (zh) 储能电池健康状态预测方法、装置及智能终端
CN115356639A (zh) 一种双向锂离子电池智能健康监控方法及系统
CN116572747B (zh) 电池故障检测方法、装置、计算机设备和存储介质
CN112884199A (zh) 水电站设备故障预测方法、装置、计算机设备和存储介质
CN113837596A (zh) 一种故障确定方法、装置、电子设备及存储介质
US20220283242A1 (en) Method and device for managing battery data
CN116720324A (zh) 基于预测模型的牵引变电所关键设备故障预警方法及系统
CN114462897A (zh) 高速公路机电系统综合性能评估方法、装置及存储介质
CN114879070A (zh) 一种电池状态评估方法及相关设备
CN113295399B (zh) 换流阀元件状态评估方法、装置、电子设备和存储介质
CN114462828A (zh) 一种工程施工用安全预警监理系统及其监理方法
CN113487086A (zh) 设备剩余使用寿命预测方法、装置、计算机设备和介质
CN116736166A (zh) 电池包的电芯异常检测方法、装置及电池包
Li et al. Battery remaining useful life prediction using improved mutated particle filter
CN116149971B (zh) 设备故障预测方法、装置、电子设备及存储介质
CN116299038B (zh) 电芯微短路的检测方法、系统、设备及存储介质
CN117872142A (zh) 一种基于值率模型的动力电池电压故障在线诊断评估方法
CN116703037B (zh) 一种基于道路施工的监控方法及装置
CN115599077B (zh) 车辆故障定界方法、装置、电子设备及存储介质

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 21914634

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 21914634

Country of ref document: EP

Kind code of ref document: A1