The invention provides a vehicle battery health degree prediction method and device, and the method comprises the steps: obtaining the record data of a plurality of vehicle batteries under each charging condition, and each record data comprises the battery data and the driving data; filtering the abnormal record data through the quantile spacing and the quantile to obtain target record data; calculating a single health degree corresponding to each piece of target record data; performing linear fitting on the driving data in the target record data of each vehicle battery and the single health degree to obtain a linear fitting function corresponding to each vehicle battery; according to the linear fitting function corresponding to each vehicle battery, filtering the vehicle batteries to obtain a target vehicle battery; constructing a random forest model through target record data in a target vehicle battery and the single health degree corresponding to the target record data; and inputting the recorded data of the to-be-predicted vehicle battery into the random forest model, and predicting the vehicle battery health degree of the to-be-predicted vehicle battery.
本申请提供了一种车辆电池健康度的预测方法及装置,其中,该方法包括:获取多个车辆电池在每次充电情况下的记录数据,每条记录数据包括电池数据、行驶数据;通过分位数间距和分位数过滤异常的记录数据,得到目标记录数据;计算每个目标记录数据对应的单次健康度;针对每个车辆电池的目标记录数据中的行驶数据与单次健康度进行线性拟合,得到每个车辆电池对应的线性拟合函数;根据每个车辆电池对应的线性拟合函数,对车辆电池进行过滤得到目标车辆电池;通过目标车辆电池中的目标记录数据及目标记录数据对应的单次健康度,构建随机森林模型;将待预测车辆电池的记录数据输入至随机森林模型,预测出待预测车辆电池的车辆电池健康度。
Method and device for predicting health degree of vehicle battery
一种车辆电池健康度的预测方法及装置
2022-07-26
Patent
Electronic Resource
Chinese
Power battery health degree estimation method and vehicle
European Patent Office | 2024
|Health degree evaluation method and health degree evaluation device for power battery
European Patent Office | 2023
|Battery health degree monitoring method and electric vehicle trunk
European Patent Office | 2023
|Vehicle-mounted power battery health degree evaluation method and system and medium
European Patent Office | 2022
|