电子测量与仪器学报

杨彦茹,温杰,史元浩,张泽慧,刘文海.基于 CEEMDAN 和 SVR 的锂离子电池剩余使用寿命预测[J].电子测量与仪器学报,2020,34(12):197-205

基于 CEEMDAN 和 SVR 的锂离子电池剩余使用寿命预测

Remaining useful life prediction for lithium-ion battery based on CEEMDAN and SVR

DOI：

英文关键词:lithium-ion battery remaining useful life support vector regression complete ensemble empirical mode decomposition with adaptive noise

基金项目:国家自然科学基金(61533013)、山西省重点研发计划(201703D111011)、山西省自然科学基金(201801D121159)、山西省青年自然科学基金(201801D221208)、山西省高等学校科技创新项目(2019L0583)、山西省研究生教育创新项目(2020SY408,2020SY405)资助

作者	单位
杨彦茹	1.中北大学电气与控制工程学院
温杰	1.中北大学电气与控制工程学院
史元浩	1.中北大学电气与控制工程学院
张泽慧	1.中北大学电气与控制工程学院
刘文海	1.中北大学电气与控制工程学院

Author	Institution
Yang Yanru	1.School of electrical and control engineering, North University of China
Wen Jie	1.School of electrical and control engineering, North University of China
Shi Yuanhao	1.School of electrical and control engineering, North University of China
Zhang Zehui	1.School of electrical and control engineering, North University of China
Liu Wenhai	1.School of electrical and control engineering, North University of China

摘要点击次数: 509

全文下载次数: 7147

中文摘要:

锂离子电池剩余使用寿命(RUL)的估算是锂离子电池健康管理的关键,准确可靠地预测锂离子电池的剩余使用寿命对系统的安全正常运行至关重要。提出了一种结合完备集合经验模态分解(CEEMDAN)和支持向量回归( SVR)的锂离子电池剩余使用寿命预测方法。首先,在放电过程中提取了一个可测量的健康因子,并使用 Pearson 和 Spearman 法分析健康因子与容量之间的相关性,然后利用 CEEMDAN 将健康因子进行分解,获得一系列相对平稳的分量,最后采用 CEEMDAN 分解后的健康因子作为 SVR 预测模型输入,容量作为输出,实现锂离子电池 RUL 预测。利用 NASA PCoE 提供的锂离子电池退化数据集进行试验,与标准 SVR 模型相比,实验结果表明利用该方法能够有效验证所提出的 RUL 预测模型的有效性,并且使预测误差控制在 2%以下。

英文摘要:

Estimation of lithium-ion battery remaining useful life (RUL) is the key to lithium-ion battery health. Achieving accurate and reliable remaining useful life prediction of lithium-ion batteries is very vital for the normal operation of the battery system. Proposes a lithium-ion battery RUL prediction method based on the combination of complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) and support vector machine-regression (SVR). First, a measurable health factor is extracted during the discharge process, and the correlation between health factor and capacity is analyzed by Pearson and Spearman methods. Then, the health factor is decomposed by CEEMDAN to obtain a series of the relatively stable components. Finally, the health factor decomposed by CEEMDAN is used as the input of SVR prediction model, and the capacity is used as the output, so as to realize lithium-ion RUL prediction. The lithium-ion battery data published by NASA PcoE is used to carry out simulation experiments, and compare it with the standard SVR model, the experimental results show that the proposed method can effectively verify the effectiveness of the proposed RUL prediction model, and the prediction error is controlled below 2%.

查看全文查看/发表评论下载PDF阅读器