Flexible battery state of health and state of charge estimation using partial charging data and deep learning

Accurately monitoring battery states over battery life plays a central role in building intelligent battery man-agement systems. This study proposes a flexible method using only short pieces of charging data to estimate both maximum and remaining capacities to simultaneously address the state of health and state of charge estimation problems. Different from conventional studies based on specific operating data to estimate one state, the pro-posed method is based on a convolutional neural network that only requires short-term charging data to estimate two states. The proposed method is first validated based on the degradation data of eight 0.74 Ah batteries. We show that the maximum and remaining capacities can be accurately estimated using arbitrary pieces of 1 C charging data collected within 400 s over battery life, and the root mean square error is lower than 12.68 mAh. The influence of the input data length and different loss weights of the two states is investigated to demonstrate the high flexibility of the proposed method. Interestingly, it is observed that the simultaneous estimation of two states achieves higher accuracy than individual state estimation. Further validations on other two types of batteries reveal that the proposed method can ensure reliable estimation in the cases of different battery chemistries and different working conditions. Our method offers a flexible and easy-to-implement approach to achieving an accurate estimation of multiple states over battery life.