电子学报 ›› 2019, Vol. 47 ›› Issue (6): 1285-1292.DOI: 10.3969/j.issn.0372-2112.2019.06.015

• 学术论文 • 上一篇    下一篇

多核相关向量机优化模型的锂电池剩余寿命预测方法

刘月峰1,2, 赵光权1, 彭喜元1   

  1. 1. 哈尔滨工业大学自动化测试与控制研究所, 黑龙江哈尔滨 150080;
    2. 内蒙古科技大学信息工程学院, 内蒙古包头 014010
  • 收稿日期:2018-04-02 修回日期:2018-12-06 出版日期:2019-06-25 发布日期:2019-06-25
  • 通讯作者: 赵光权
  • 作者简介:刘月峰 男,1977年12月生,内蒙古乌兰察布市人,现为内蒙古科技大学副教授、硕士生导师,哈尔滨工业大学博士研究生,主要研究方向为智能故障诊断和预测、机器学习等.E-mail:liuyuefeng01035@163.com;彭喜元 男,1961年12月生,内蒙古四子王旗人,现为哈尔滨工业大学教授、博士生导师,自动化测试与控制研究所所长,主要研究方向为自动测试技术、智能故障诊断技术等.E-mail:pxy@hit.edu.cn
  • 基金资助:
    国家自然科学基金(No.51565046);内蒙古自然科学基金(No.2018MS06019)

A Lithium-Ion Battery Remaining Using Life Prediction Method Based on Multi-kernel Relevance Vector Machine Optimized Model

LIU Yue-feng1,2, ZHAO Guang-quan1, PENG Xi-yuan1   

  1. 1. Institute of Automatic Test and Control, Harbin Institute of Technology, Harbin, Heilongjiang 150080, China;
    2. School of Information Engineering, Inner Mongolia University of Science & Technology, Baotou, Inner Mongolia 014010, China
  • Received:2018-04-02 Revised:2018-12-06 Online:2019-06-25 Published:2019-06-25

摘要: 基于相关向量机的剩余寿命预测方法,核函数是影响相关向量机模型预测性能的重要因素.目前的相关向量机预测模型以单核为主,且核函数的选择存在较大主观性,导致所构建的预测模型性能有限.本文提出一种融合多个核函数构建相关向量机预测模型的方法,通过果蝇算法优化多个核函数优化组合的线性方程系数,提高了模型的预测性能,并将该方法应用于预测锂离子电池的循环剩余寿命.分别采用美国NASA和马里兰大学的电池退化数据集,对本文的方法进行了实验验证.实验结果表明:多核相关向量机预测方法的平均绝对误差和均方根误差都小于最优的单核相关向量机预测方法.

关键词: 多核相关向量机, 果蝇优化算法, 锂离子电池, 剩余寿命预测

Abstract: For the remaining useful life (RUL) prediction method based on relevance vector machine (RVM),kernel function is the important item of RVM model for the final prediction result.The current RVM prediction models are dominated by single kernel,and the selection of RVM kernel is a little bit subjective.So,the prediction performance of the constructed RVM model is limited.To address this problem,a multi kernel RVM model is proposed for the RUL estimation,using the fruit fly optimization algorithm (FOA) to find the best corresponding coefficients of multi kernel in the linear combination of multi kernel functions,and to improve the prediction performance of RVM model applied in the RUL estimation of lithium-ion battery.The battery test data sets of the national aeronautics and space administration (NASA) and the center of advanced life cycle engineering (CACLE) in the university of Maryland are used respectively.Experiments have been carried out to test the performance of the proposed method.The results show that the mean absolute error (MAE) and root mean square error (RMSE) of multi kernel RVM method are both less than the single kernel RVM algorithm.

Key words: multi kernel relevence vector machine, fly optimization algorithm, lithium-ion battery, remaining useful life prediction

中图分类号: