[author_cn_name].[cn_title][J].空军工程大学学报:自然科学版,[year_id],[volume]([issue]):[start_page]-[end_page] 基于置信规则库的锂电池SOC估计-SOC Estimation of Lithium Battery Based on Belief Rule Base
文章摘要
吕延卓,肖明清,唐希浪,李剑峰,刘强,王联科.基于置信规则库的锂电池SOC估计[J].空军工程大学学报:自然科学版,2019,20(4):39-45
基于置信规则库的锂电池SOC估计
SOC Estimation of Lithium Battery Based on Belief Rule Base
  
DOI:
中文关键词: 锂电池  电池荷电状态估计  置信规则库
英文关键词: Lithium battery  SOC estimation  belief rule base
基金项目:
作者单位
吕延卓,肖明清,唐希浪,李剑峰,刘强,王联科 1.空军工程大学研究生院,西安,7100512.空军工程大学航空工程学院,西安,710038 
摘要点击次数: 8
全文下载次数: 17
中文摘要:
      电池荷电状态(SOC)的准确估计在电池广泛应用的背景下日益重要,但是构建精确的物理模型十分困难,使用纯粹的数据驱动方法又容易因为电池个体差异性出现过拟合问题。针对这些问题,提出基于置信规则库(BRB)的方法对锂电池SOC的进行估计。该方法既允许专家通过经验知识克服数据驱动方法的过拟合问题,又能通过参数训练克服专家知识的不准确性。以某型磷酸铁锂(LiFePO-4)电池为例,对提出的方法进行了验证,并将其与神经网络进行了对比。结果表明,该方法估计SOC具有较高的精度,估计误差不超过10%,且可以克服传统神经网络方法存在的过拟合问题。
英文摘要:
      The accurate estimation of the state of charge (SOC) of a battery is increasingly important in the context of the wide application of batteries. However,it is difficult to build accurate physical models,and the use of pure data driven methods is prone to overfitting problems due to individual differences of batteries. To solve these problems,propose a method based on belief rule base (BRB) to estimate SOC of lithium battery. This method allows experts to overcome the overfitting problem of data driven methods through empirical knowledge and the inaccuracy of expert knowledge through parameter training. A lithium iron phosphate (LiFePO-4) battery is taken as an example to verify the proposed method,and the results are compared with those of the neural network. The results show that this method has high accuracy in SOC estimation,the estimated error is not more than 10%,and can overcome the overfitting problem of traditional neural network methods.
查看全文   查看/发表评论  下载PDF阅读器
关闭