A hybrid data-driven method for rapid prediction of lithium-ion battery capacity

The quick and accurate prediction of future capacity is a challenging issue in the field of battery health management. To solve this problem, the paper proposes a data-driven model based on advanced machine-learning techniques. First, wavelet transform is used to denoise the initial features, and the relatively important features are selected with the help of random forest. Second, the paper uses the approximate entropy theory to construct multi-time scale sliding window data to solve the problem that the sliding window size can not be determined in traditional methods. Third, in order to overcome the disadvantages of traditional methods, such as the comparative inefficiency in converging and using temporal contextual information, the paper proposes a novel mogrifier long short-term memory network denoted as QGA-ASM-LSTM, which is based on attention mechanism and similarity judgment mechanism, using quantum genetic algorithm to optimize its parameters. Finally, the proposed data-driven method is used to model the degradation of lithium-ion batteries and finish the fast capacity prediction. The results of experiments on different public datasets demonstrate that the performance of QGA-ASM-LSTM exceeds the state-of-the-art models in terms of prediction accuracy and training time.