A Meta-Learning Method for Few-Shot Multi-Domain State of Health Estimation of Lithium-ion Batteries

Diverse electrochemical characteristics and complex operational conditions of the lithium-ion battery cause multi-domain discrepancies in practical applications, which poses huge challenges to the robust state of health (SOH) estimation based on small samples. This paper proposes a novel meta-learning method for few-shot multi-domain battery SOH estimation using relaxation voltages. Firstly, a convolution neural network (CNN)-attention based parallel network is developed to enhance the extraction of transferable health features across multiple domains. Secondly, the loss interaction difference of multiple target-domain tasks is proposed to improve the meta-learning method for comprehensive task judgment. Finally, the cross-domain validation is conducted on two types of batteries operating under three working temperatures. The results reveal that the proposed method can provide higher estimation accuracy compared to state-of-the-art network architectures. By only using 6 cycles from one target battery, it achieves lower average root-mean-square error and mean absolute error of 2.28% and 1.79% for NCA batteries and 1.38% and 1.14% for NCM batteries, outperforming traditional methods without pre-training and transfer learning.