The invention discloses a power battery pack SOH prediction method and system. The system comprises the following modules: a data preprocessing module, an SDAE module and a neural network module. The method comprises the following steps: reading BMS historical data, cleaning the BMS historical data, extracting weather, driving behavior and conventional features, and classifying the features into continuous features and numeric features for preprocessing; the processed data are transmitted to an SDAE module, noise is added to the data, and the data are reconstructed; and the neural network learns a mapping relationship between the features and the SOH, and outputs an SOH prediction result. According to the method, more stable and more useful features are found through SDAE reconstruction input data, meanwhile, the more stable and efficient model is obtained through combination by means of the parallel computing characteristic of the neural network, the prediction precision of the model can be improved while the computing time is saved, and the method is suitable for battery pack SOH estimation during full-state and full-climate operation of the electric vehicle.
本发明公开了一种动力电池组SOH预测方法及系统,系统包括以下模块:数据预处理模块、SDAE模块、神经网络模块;方法包括以下步骤:通过读取BMS历史数据,对其进行清洗,提取天气、驾驶行为和常规三类特征,并分为连续型特征和数值型特征两类进行预处理;处理后传入SDAE模块,对数据加噪并重构数据;神经网络学习特征与SOH之间的映射关系,并输出SOH预测结果。本发明通过SDAE重构输入数据找到更稳定、更有用的特征,同时利用神经网络并行计算的特点,组合得到更具稳定性的高效的模型,可在节省计算时间的同时提高模型的预测精度,适用于电动汽车全状态、全气候运行时的电池组SOH估算。
Power battery pack SOH prediction method and system
一种动力电池组SOH预测方法及系统
2022-07-26
Patent
Electronic Resource
Chinese
Power battery pack temperature prediction method and system
European Patent Office | 2020
|The Prediction of Battery Pack Peak Power
Wiley | 2015
|Battery pack, power tool and battery pack charger system
European Patent Office | 2023
|Power battery pack equalization system, battery replacing system and battery pack
European Patent Office | 2020
|BATTERY PACK, POWER TOOL AND BATTERY PACK CHARGER SYSTEM
European Patent Office | 2020
|