Health prognostics of lithium-ion batteries based on universal voltage range features mining and adaptive multi-Gaussian process regression with Harris Hawks optimization algorithm

Abstract

In the field of battery prognostics and health management (PHM), accurate State-of-Health (SOH) estimation is important for the safe and reliable operation of lithium-ion batteries (LIBs). To improve the applicability and accuracy of the SOH estimation model, a new SOH estimation framework is proposed. Firstly, considering the different usage habits of users, to meet the needs of more users, a new health indicator (HI) was put forward, which involves only a small universal voltage range of charging data. Secondly, to alleviate the negative impact of the inherent cell inconsistency on SOH estimation accuracy, an adaptive Multi-Gaussian Process Regression model based on Harris Hawks Optimizer (HHO-MGPR) was proposed. The core idea is to use the HHO algorithm to automatically generate the optimal training subset combination for multiple GPR base learners so as to improve the model generalization ability. Finally, four open-source datasets with different battery types, temperature and operating conditions are employed for performance validation. The experimental results show that in all cases, the proposed HI can effectively characterize the battery degradation and the developed HHO-MGPR can improve the model generalization ability, indicating the proposed framework has wide applicability.