An RUL prediction approach for lithium-ion batteries based on FIG and SVM with multi-kernel

Lithium ion battery is a common energy storage component in life. Accurately predicting the remaining service life (rul) is significant. This article establishes a data-driven RUL prediction method. The original cycle data of the battery is processed by FIG, and the granulation data is used to replace the original data for subsequent analysis. Aiming at the kernel function selection problem of support vector machine(SVM), a multi-kernel function is established to enhance the learning and generalization capability of the model. The validation set is used to verify the feasibility and accuracy of the model and the prediction accuracy of the model is less than 1%. A Single-kernel battery life prediction model is established and compared with the hybrid core function battery life model. The comparative analysis proves that the model established in this paper has higher accuracy.