An improved sliding window - long short-term memory modeling method for real-world capacity estimation of lithium-ion batteries considering strong random charging characteristics

Abstract

Capacity estimation plays a significant role in ensuring safe and acceptable energy delivery, especially under real-time complex working conditions for whole-life-cycle lithium-ion batteries. For high-precision and robust capacity estimation, an improved sliding window-long short-term memory (SW-LSTM) modeling method is proposed by introducing multiple time-scale charging characteristic factors. The optimized feature information set is extracted by constructing an optimized differential integration-moving average autoregressive (DI-MAA) model, which is introduced as the input matrices of the whole-life-cycle capacity estimation model. With the constructed DI-MAA model, the relevant features are effectively extracted, overcoming the data limitation problem of the long-term dependence capacity estimation. For the experimental test, the maximum capacity estimation error is 3.56 %, and the average relative error is 0.032 under the complex Beijing bus dynamic stress test working condition. The proposed SW-LSTM estimation model with optimized DI-MAA-based data pre-processing treatment has high stability and robust advantages, serving an effective safety assurance for lithium-ion batteries with real-world complex working condition adaptation advantages.