Development of Remaining Useful Life (RUL) Prediction of Lithium-ion Battery Using Genetic Algorithm-Deep Learning Neural Network (GADNN) Hybrid Model

Abstract

Designing a battery management system requires knowing the battery’s remaining useful life (RUL). The Deep Learning Neural Network (DLNN) algorithm was optimized in this study utilizing evolutionary algorithms to forecast the RUL batteries. Using a Genetic Algorithm (GA), the most crucial features from the raw dataset were identified. After that, a GADLNN hybrid model was created to choose the DLNN model’s ideal network algorithm, hidden neuron activation function, hidden layer count, and neuron count in each hidden layer. Specifically, NASA provided a dataset related to lithium-ion battery cycle life. For the model development, data validation, and testing phases, the dataset was split into a training set, validation set, and testing set. Several quality assessment criteria were employed to measure the effectiveness of the machine learning (ML) algorithms, such as the Coefficient of Determination (R2), Index of Agreement (IA), Mean Absolute Error (MAE), and Root Mean Squared Error (RMSE). The hybrid GA-DLNN model demonstrated the capacity to identify the most advantageous set of parameters for the prediction procedure. The outcomes demonstrated that, in comparison to results obtained using all input variables, the performance of the hybrid model employing only the most crucial features gave the maximum accuracy. Using 11-input GA-DLNN: R2=0.985,MAE=3.806, RMSE =5.596, IA=0.996. Using 21-input GA-DLNN: R2=0.987, MAE=3.314, RMSE =5.273, IA=0.997.