Adaptive self-attention LSTM for RUL prediction of lithium-ion batteries

To achieve an accurate remaining useful life (RUL) prediction for lithium-ion batteries (LIBs), this study proposes an adaptive self-attention long short-term memory (SA-LSTM) prediction model. The innovations of the designed prediction model include the following. (1) It features an opti-mized local tangent space alignment algorithm, which allows the extraction of an indirect health indicator (HI) that can precisely describe battery degeneration from charge data. The extracted HI exhibits a high correlation with the standard capacity, thus facilitating RUL estimation. (2) By introducing a masked multi-head self-attention module into the time-series prediction model based on LSTM, critical information in the sequences is captured and the prediction performance is improved. (3) An online self-tuning mechanism for the weights and biases of neural networks is designed to correct cumulative estimation errors in long-term predictions and reduce the effects of local fluctuations and regeneration. The proposed prediction model enables the HI values in future cycles to be iteratively estimated using the one-step-ahead method, and the RUL can be forecast once the predicted signal falls. Experimental results indicate the effectiveness and su-periority of the proposed prediction method.

Automated summary

This study proposes an adaptive self-attention long short-term memory (SA-LSTM) prediction model for accurate remaining useful life (RUL) prediction of lithium-ion batteries (LIBs). The innovations of the designed prediction model include an optimized local tangent space alignment algorithm to extract an indirect health indicator (HI) that describes battery degeneration, a masked multi-head self-attention module to capture critical information in the sequences, and an online self-tuning mechanism to correct cumulative estimation errors and reduce the effects of local fluctuations. The proposed prediction model enables iterative estimation of HI values in future cycles and forecasting of RUL based on predicted signal falls. Experimental results demonstrate the effectiveness and superiority of the proposed method.