Improving State of Health Estimation for Lithium-ion Batteries based on GAN and Partial Discharge Profiles

The aging effect will weaken the capacity of lithium batteries and seriously affect the performance of electric vehicles. Developing State of Health estimation technology for lithium batteries can help optimize the charging and discharging strategies of electric vehicles. This study investigates the use of partial discharge data for SOH estimation. To overcome the limitation of unstable output of traditional estimation models caused by partial discharge data in low voltage scenarios. This study first used the DoppelGANger network to generate artificially synthesized data. After the data augmentation process, train the Temporal Convolutional Network to construct a data-driven SOH model. Finally, the performance of the SOH model output is evaluated using three indicators: RMSE, MAPE, and delta. The proposed method improved 5 kinds of low-voltage operating conditions in 7 testing scenarios compared with traditional SOH estimation models. The experimental results provide a practical solution for data-driven SOH estimation.