For the purpose of assuring dependability and safety, the lifespan of a lithium-ion battery must be accurately predicted. It also serves as an advance warning mechanism for stopping battery from failing. New data-driven estimate techniques are made possible by recent advances in machine learning (ML). In this study, we propose a hybrid technique for estimating battery's remaining usable life and enhancing forecast accurateness while maintaining tolerable processing time. This hybrid method is called CNN-LSTM and merges Convolutional Neural Network (CNN) and Long Short Term Memory (LSTM). To demonstrate advantages of the suggested hybrid estimation strategy, a comparison is made against several ML estimation algorithms. To test the accuracy of the predictions, two statistical indicators—the MSE, MAE, R2, and RMSE—are used. CNNs and LSTM are two wellknown algorithms that may be used to create a hybrid algorithm that will calculate the battery's Remaining Usable Life (RUL) and enhance lithium-ion batteries' long-term prediction ability. Utilizing the CALCE dataset of several lithium-ion batteries, experimental validation is carried out. Results show that hybrid approaches outperform single ones and that the recommended strategy is successful in lowering prediction error and outperforming other methods in terms of RUL prediction performance.

.