广西师范大学学报(自然科学版) ›› 2018, Vol. 36 ›› Issue (1): 25-33.doi: 10.16088/j.issn.1001-6600.2018.01.004

• • 上一篇    下一篇

基于AP-HMM混合模型的充电桩故障诊断

林越1,2,刘廷章1*,陈一凡1,金勇3,梁立新3   

  1. 1.上海大学机电与工程学院,上海200072;
    2.海南热带海洋学院信息工程学院,海南三亚572022;
    3.上海国际汽车城(集团)有限公司,上海201805
  • 收稿日期:2017-06-08 出版日期:2018-01-20 发布日期:2018-07-17
  • 通讯作者: 刘廷章(1976—),男,山西太原人,上海大学教授,博导。E-mail:liutzh@shu.edu.cn
  • 基金资助:
    国家自然科学基金(61273190);上海嘉定新能源汽车商业模式创新产业联盟

The Fault Diagnosis of Charging Piles Based on Hybrid AP-HMM Model

LIN Yue1,2,LIU Tingzhang 1*,CHEN Yifan1,JIN Yong3,LIANG Lixin3   

  1. 1. College of Mechatronics Engineering and Automation,Shanghai University,Shanghai 200072,China;
    2. College of Marine Communication Engineering,Hainan Tropical Ocean University,Sanya Hainan 572022,China;
    3. Shanghai International Automobile City GroupCo. Ltd., Shanghai 201805, China
  • Received:2017-06-08 Online:2018-01-20 Published:2018-07-17

摘要: 确定性的相似性传播(AP)聚类方法和统计性的隐马尔可夫模型(HMM)是2种常用的设备故障诊断方法,但电动汽车充电桩结构设计复杂且目前积累的故障样本不多,使用上述2种方法均不够理想。针对充电桩故障诊断本身具有的特点,结合AP聚类快速、准确提取故障的特征和HMM强大的故障分类能力,本文提出一种基于AP-HMM混合模型的充电桩故障诊断方法。为了研究充电桩长期工作的状态性质,采用马尔可夫平衡方程组求得充电桩发生故障的稳态概率值。实验结果表明,与传统模型相比,AP-HMM混合模型的充电桩故障诊断学习精度提高了3%以上。本文提出的混合模型具有一定的可行性与普适性,可在一定程度上用于速度要求低但精度要求高的其他电子设备故障诊断。

关键词: 相似性传播聚类, 隐马尔可夫模型, 充电桩, 稳态分布, 故障诊断

Abstract: Affinity propagation (AP) of uncertainty hidden Markov model (HMM) and statistical clustering method are the two commonly used methods for fault diagnosis of equipment. However, since the structure of a electric car charging pile is complex and there are few fault samples on it, the above two methods are not ideal for fault diagnosis. According to the characteristics of charging pile with fault diagnosis, taking into account the AP clustering fast and accurate fault feature extraction and HMM powerful capability of fault classification, a fault diagnosis method of charging pile is presented based on AP-HMM hybrid model in this paper. At the same time, in order to discuss the long-term nature of the charging pile, the Markov equilibrium equations are used to obtain the stable probability of fault. The experimental results verify the correctness of the above theoretical analysis, and the results show that the AP-HMM hybrid model has the advantage of high diagnostic accuracy compared with the traditional model. The hybrid model proposed in this paper has certain feasibility and universality, and can be applied to the fault diagnosis of other electronic equipments with low speed and high precision.

Key words: affinity propagation clustering, hidden Markov model, charging piles;stable distribution, fault diagnosis

中图分类号: 

  • TP274
[1] 章博文,李显君,闫旭.专利视角下中美电动汽车技术发展比较分析[J].哈尔滨工业大学学报,2017,49(7):86-92.
[3] 钱立军,赵明宇,张卫国.一种电动汽车充电安全预警模型设计方法[J].电网与清洁能源,2016,32(12):114-119.
[3] 徐亚森,王仲生,姜洪开.基于能量演化的航空发动机故障预示模型设计[J].测控技术,2012,31(8):140-143.
[4] 姜毅,郑宽馀,石亚伟,等.双馈风力发电机的建模与故障状态研究[J].西南师范大学学报,2014,39(4):152-158.
[5] 石东院,熊国江,陈金富,等.基于径向基函数神经网络和模糊积分融合的电网分区故障诊断[J].中国电机工程学报,2014,34(4):562-569.
[6] 林已杰,赖清,周敏.基于BP神经网络和马尔可夫模型的服务器软件老化预测方法[J].西南师范大学学报,2011,36(4):193-197.
[7] FREY B,DUECK D. Clustering by passing messages between data points[J].Science,2007,315(5814):972-976.
[8] 苗强.基于隐马尔可夫模型的故障诊断系统研究[J].航空学报,2005,26(5):642-646.
[9] 唐飞,王波,查晓明,等.基于双阶段并行隐马尔可夫模型的电力系统暂态稳定评估[J].中国电机工程学学报,2013,33(10):91-97.
[10] 邓勇,师奕兵,张伟.基于FRWT的模拟电路早期故障诊断[J].仪器仪表学报,2012,33(3):555-560.
[11] ATLAS L,OSTENDORF M,BERNARD G D. Hidden Markov models for monitoring machining tool-wear[C]//IEEE ICASSP 2000. Piscataway, NJ:IEEE Press, 2000:3887-3890.
[12] OCAK H,LOPARO K A.A new bearing fault detection and diagnosis scheme based on hidden Markov modeling of vibration signals[C]//IEEE ICASSP 2001. Piscataway, NJ:IEEE Press, 2001:3141-3144.
[13] 李丽敏,王仲生,姜洪开.基于相似性传播聚类的航空发动机突发故障诊断[J].振动与冲击,2014,33(1):52-55.
[14] 郑国忠,童行伟.概率导论[M].北京:人民邮电出版社,2009:300-303.
[15] BAUM L E,PETRIE T. Statistical inference for probabilistic function of finite state Markov chains[J].The Annals of Mathematical Statistics,1996,47(6):1554-1563.
[16] 刘韬.基于隐马尔可夫模型与信息融合的设备故障诊断与性能退化评估研究[D].上海:上海交通大学,2013:58-66.
[1] 王勋, 罗晓曙. 基于图像处理自适应变步长调焦搜索算法[J]. 广西师范大学学报(自然科学版), 2016, 34(3): 25-31.
[2] 刘慧敏, 官冬杰, 张梦婕. 三峡库区生态安全后续发展胁迫因子及胁迫机理研究[J]. 广西师范大学学报(自然科学版), 2016, 34(3): 150-158.
[3] 林越, 刘廷章, 黄莉荣, 奚晓晔, 潘建. 基于双向KL距离聚类算法的变压器状态异常检测[J]. 广西师范大学学报(自然科学版), 2018, 36(4): 20-26.
[4] 苏诚, 陈文娜, 周玲, 黄冬梅. 面向海洋空间数据集成的多Agent任务分配机制[J]. 广西师范大学学报(自然科学版), 2011, 29(2): 205-209.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!
版权所有 © 广西师范大学学报(自然科学版)编辑部
地址:广西桂林市三里店育才路15号 邮编:541004
电话:0773-5857325 E-mail: gxsdzkb@mailbox.gxnu.edu.cn
本系统由北京玛格泰克科技发展有限公司设计开发