An HI Extraction Framework for Lithium-Ion Battery Prognostics Based on SAE-VMD

基于SAE-VMD的锂离子电池健康因子提取方法

School of Computer Science and Engineering, Northwestern Polytechnical University, Xi'an 710072, China

Received: 8 October 2019

Abstract

The signals of lithium-ion battery degradation are non-stationary and nonlinear. To adaptively extract the health indicator(HI) that can accurately represent the battery degradation characters and improve the prediction precision of battery remaining useful life (RUL), a stacked auto encoder-variational mode decomposition(SAE-VMD) based HI construction framework is proposed. Firstly, the stacked auto encoder(SAE) is used to reduce the noises of battery parameters and lower the data dimensionality and construct a syncretic HI that contains the battery degradation characters. Then the variational mode decomposition(VMD) is employed for effectively separating the syncretic HI into three modalities: the global attenuation, the local regeneration and the noises. The three modalities are selected as HIs to eliminate the HI noises and improve the RUL prediction precision. The RUL prediction results of lithium-ion battery indicate that the HI extracted by using the present method can obtain a better RUL prediction precision and verify the high quality of the extracted HI.

摘要

电池退化信号具有非平稳、非线性特性，为自适应提取能准确表达电池退化特性的健康因子（HI），提高锂离子电池剩余寿命（RUL）的预测精度，提出一种基于堆叠稀疏自编码（SAE）和变分模态分解（VMD）的HI构建方法。首先利用SAE深度神经网络对多个电池参数去噪、降维，提取出一个集中包含电池退化特性的融合HI；然后利用VMD将融合HI的全局衰减、局部再生和其他噪声3种模态进行有效分离，将被分离的3个分量作为电池HI，以此消除HI不同尺度上波动之间的相互干扰，提高RUL预测精度。锂离子电池RUL的预测结果表明，使用该方法所提HI得到的RUL预测精度最高，说明所提HI品质最高。