基于起始电压分段与迁移学习的锂离子电池 SOH 估计

Aiming at the problem that traditional state of health（SOH）estimation algorithms cannot extract the required features during random partial charging and discharging of actual batteries，a segmented estimation method based on the initial voltage under charging state is proposed. This method extracts the features corresponding to the initial charging voltage point by analyzing the capacity increment curve of the battery，determines the optimal features and number of features based on random forest and related indicators，and uses them as the basis for segmenting the initial charging voltage of the battery. Corresponding features are used for SOH estimation in different segmentation intervals. Subsequently，transfer learning methods were used to solve the problem of insufficient data to support modeling in the actual operation of lithium batteries，using the sample transfer method TrAdaBoost.