基于EMD-GPR的锂离子电池剩余寿命预测方法研究

Research on Residual Life Prediction Method of Lithium Ion Battery Based on EMD-GPR

提出一种基于经验模态分解(Empirical Mode Decomposition,EMD)和高斯过程回归(Gaussian Process Regression,GPR)的锂离子电池剩余寿命预测方法。运用EMD对电池容量数据进行分解,从分解结果中选择能够表征锂电池退化的趋势项。基于趋势项,构建GPR预测模型。利用拟合的GPR模型分别对锂离子电池剩余寿命进行点预测和区间预测。实验结果表明,点预测方法中多步预测精度更高,而区间预测能提供更多的参考信息,具有更强的有效性和适用性。

A residual life prediction method for lithium-ion batteries based on empirical mode decomposition(EMD)and Gaussian process regression(GPR)was proposed.EMD was used to decompose the battery capacity data,and the trend items representing the degradation of lithium batteries were selected from the decomposition results.Based on the trend term,the prediction model of GPR was built.The fitted GPR model was used to predict the remaining life of lithium-ion batteries by point and interval respectively.The experimental results show that the point prediction method has higher accuracy in multi-step prediction,while the interval prediction can provide more reference information and has stronger validity and applicability.