Fault diagnosis of lithium battery based on fuzzy Bayesian network

被引：0
作者：
Li R. [1 ]
Li S. [1 ]
Zhou Y. [1 ]
机构：
[1] Department of Electrical Engineering and Automation, Harbin University of Science and Technology, Harbin
来源：
Li, Ran (hrust_g0710@163.com) | 2018年 / Totem Publishers Ltd卷 / 14期
关键词：
Bayesian network; Electrical vehicle; Fault diagnosis; Fuzzy mathematics; Lithium battery;
D O I：
10.23940/ijpe.18.10.p6.23022311
中图分类号：
学科分类号：
摘要：
With the development of battery technology, lithium batteries are widely applied to electrical vehicles. The generation of the lithium battery fault has certain complexity and uncertainty, and the quantity of lithium batteries's real-time data test point is low. In addition, the test data is incomplete. Therefore, a fault diagnosis method for lithium batteries is presented based on a fuzzy Bayesian network, and a fault diagnosis model is established combined with fuzzy mathematics and the Bayesian network. The data is fuzzified by fuzzy mathematics to obtain the membership of fault symptoms. The demand of date and computation complexity is reduced by the Leaky Noisy-OR Bayesian network model. If the amount of fault nodes is large, the demand of conditional probability is reduced greatly, from 2n to 2n, by applying the Bayesian network constructed by the model presented above. This method requires less diagnosis time and sample demand, and it has high quality of diagnosis as well as many other advantages. The fault diagnosis of lithium batteries is supported by this method. © 2018 Totem Publisher, Inc. All rights reserved.
引用
收藏
页码：2302 / 2311
页数：9
相关论文
共 16 条
  • [1] Zhang H., Pei L., Sun J., Song K., Lu R.G., Zhao Y.P., Et al., Online diagnosis for the capacity fade fault of a parallel-connected lithium ion battery group, Energies, 9, 5, pp. 387-404, (2016)
  • [2] Sidhu A., Izadian A., Anwar S., Adaptive Nonlinear Model-based Fault Diagnosis of Li-Ion Batteries, IEEE Transactions on Industrial Electronics, 62, 2, pp. 1002-1011, (2015)
  • [3] Gu A., Zhang X.W., Fault Diagnosis System for Power Battery based on RBF Neural Network, Chinese Journal of Power Sources, 40, 10, pp. 1943-1945, (2016)
  • [4] Wu C., Zhu C., Ge Y., A new fault diagnosis and prognosis technology for high-power lithium-ion battery, IEEE Transactions on Plasma Science, 45, 7, pp. 1533-1538, (2017)
  • [5] Wang Y.H., Jiang C.H., Fuzzy neural network expert system for fault diagnosis in power lithium battery application, Electrical Measurement & Instrumentation, 52, 14, pp. 118-123, (2015)
  • [6] Cai B., Huang L., Xie M., Bayesian networks in fault diagnosis, IEEE Transactions on Industrial Informatics, 1, 1, (2017)
  • [7] Li H.J., Cheng Y.W., Yao C., Xu H.F., Yao Z., Qu C.F., Fault Diagnosis Method of Vehicle Power System using Bayesian Network, Applied Mechanics & Materials, 23, pp. 3134-3138, (2014)
  • [8] Liu Q., Yu C., LGSPP-Bayes for fault detection and diagnosis, International Journal of Engineering Practical Research, 4, 1, pp. 89-93, (2015)
  • [9] Yuan G., Shi G., Hou N., Kuang X., The application of FMEA technology in the unstable failure analysis, Proceedings of IEEE International Conference on Reliability, Maintainability and Safety, pp. 663-665, (2015)
  • [10] Peng F., Study on Transformer Fault Diagnosis based on Dynamic Fault Tree, Journal of Electrical and Electronic Engineering, 3, 5, pp. 133-138, (2015)
12