Remaining Useful Life Prediction of Lithium-Ion Batteries Based on Cataclysmic Mutation Genetic Algorithm and Support Vector Regression

Abstract

The remaining useful life (RUL) of lithium-ion batteries is the core of power equipment prognostics. Accurate prediction of battery remaining useful life can be carried out in advance for the maintenance and replacement of batteries with potential safety hazards to ensure the normal operation of the energy storage system. Based on this, this paper proposes a remaining useful life prediction method for lithium-ion batteries based on cataclysmic mutation genetic algorithm (CMGA) and support vector regression (SVR). Firstly, the parameter optimization of support vector regression was carried out by using the cataclysmic mutation genetic algorithm. Secondly, a support vector regression model is established to predict the remaining useful life of lithium-ion batteries. Finally, CMGA-SVR was compared with GA-SVR and Cross Validation (CV)-SVR models to verify the effectiveness of the method. Results show that CMGA-SVR has stronger fitting ability and higher optimization precision. Compared with GA-SVR and CV-SVR, its average Mean squared error (MSE) is reduced by 0.029 and 1.608, respectively, and its average Squared correlation coefficient (R2) is increased by 0.8% and 4.4%, respectively, which provides a reference for the prediction of the remaining useful life of lithium-ion batteries.