Remaining useful life prediction of lithium-ion battery based on data-driven and multi-model fusion
2022-01-0869
03/29/2022
- Content
- With the rapid development of new energy vehicles, the echelon utilization of retired power battery has become an important factor to promote the healthy development of this industry, while the remaining useful life (RUL), as the key reference factor for the echelon utilization of retired power battery , has attracted the attention and research of many scholars in recent years. At present, most prediction methods are based on off-line data, which can not process real-time data in time, so it is difficult to realize online prediction of RUL. In order to realize the real-time online monitoring and high-precision calculation of lithium-ion battery RUL, this paper proposes a lithium-ion battery RUL prediction method based on data-driven and multi-model fusion. Fast feature online extraction of one-dimensional battery capacity time series data via convolutional neural network(CNN), mining potential hidden information. Then the size of the amount of information retained in before and after data is controlled through the long and short-term memory neural network (LSTM) ,so as to solve the problem of long-dependent characteristics in time series data and efficiently identify the data mode. Finally, using the Bayesian model average (BMA) algorithm with uncertainty expression ability, we integrate the CNN model and the LSTM model according to the calculated weight coefficient, obtain the predicted aging model, and then calculate the RUL according to the capacity failure threshold. The proposed method not only make up for the lack of uncertainty expression of the deep learning models, but the fusion model further improves the prediction accuracy of the lithium-ion battery RUL. We have conducted experiment using the lithium-ion battery aging data set published by NASA, the prediction accuracy is greatly improved compared with the prediction model based on off-line data.
- Citation
- Fan, L., and Lu, X., "Remaining useful life prediction of lithium-ion battery based on data-driven and multi-model fusion," SAE Technical Paper 2022-01-0869, 2022, .