Please wait a minute...
浙江大学学报(工学版)
J4  2010, Vol. 44 Issue (3): 453-457    DOI: 10.3785/j.issn.1008973X.2010.03.007
    
Diagnosis of simultaneous faults for mobile robots based on fuzzy clustering method
Download:   PDF(0KB) HTML
Export: BibTeX | EndNote (RIS)      

Abstract  

Most fault diagnosis methods for mobile robots that treat simultaneous multifaults as a single fault state need to design a filter for each fault combination and can only diagnose the specificset combinations of multifaults presently. To overcome these disadvantages, a simultaneous faults diagnosis method for mobile robots was proposed. According to the kinematic model of a mobile robot, a specific Kalman filter (KF) was designed for each single fault state to filter the fault data of the mobile robots. Residuals of the KFs were classified by fuzzy cluster method (FCM). Any simultaneous faults were diagnosed according to the membership to each single fault set. This technique was implemented on a 3wheels mobile robot Pioneer 3 to diagnosis 14 kinds of common single faults and simultaneous multifaults, and the simulation results showed the effectiveness of the technique.

Published: 20 March 2012
CLC:  TP24  
Service
E-mail this article
Add to my bookshelf
Add to citation manager
E-mail Alert
RSS
Articles by authors
Cite this article:

LIN Ji-Liang, JIANG Jing-Ping. Diagnosis of simultaneous faults for mobile robots based on fuzzy clustering method. J4, 2010, 44(3): 453-457.

URL:

http://www.zjujournals.com/eng/10.3785/j.issn.1008973X.2010.03.007     OR     http://www.zjujournals.com/eng/Y2010/V44/I3/453


基于模糊聚类的移动机器人并发故障诊断

移动机器人并发故障诊断技术大多将并发的多故障作为多种单故障组合状态处理,这样不仅需要为每种故障设计滤波器,且只能诊断特定的多故障组合.为了克服这些缺点,提出一种移动机器人多故障并发的故障诊断技术.根据移动机器人的运动模型,为每一种单故障状态设计一个对应的卡尔曼滤波器,用这些滤波器对移动机器人并发故障数据进行滤波.利用模糊聚类方法对滤波结果进行分类,根据移动机器人运行数据对不同单故障集合的隶属度诊断任意组合的并发故障.在三轮移动机器人Pioneer 3上进行仿真实验,对14种常见的单故障和多故障并发的情况进行诊断,证明了该方法对轮式移动机器人并发故障诊断的有效性.

［1］ GOEL P, DEDEOGLU G, ROUMELIOTIS S I, et al. Fault detection and identification in a mobile robot using multiple model estimation and neural network［C］//Proceedings of the 2000 IEEE International Conference on Robotics & Automation. San Francisco, CA: IEEE, 2000： 23022309.
［2］ 柳玉甜,蒋静坪.基于多模型和小脑模型关节控制器神经网络的移动机器人故障诊断［J］.电工技术学报, 2007, 22(3): 153158.
LIU Yutian, JIANG Jingping. Fault diagnosis based on CMAC neural network and multimodels for mobile robots［J］. Transactions of China Electrotechnical Society, 2007, 22(3): 153158.
［3］ CAI Zixing, DUAN Zhuohua, CAI Jingfeng, et al. A multiple particle filters method for fault diagnosis of mobile robot deadreckoning system［C］// Proceedings of IEEE International Conference on Intelligent Robots and Systems.［S.l］: IEEE, 2005： 481486.
［4］ 张彼德,孙财新,欧健,等,诊断汽轮发电机组故障的一种模糊聚类分析方法［J］.汽轮机技术,2002,44(5): 289291.
ZHANG Bide, SUN Caixing, OU Jian,et al. A fuzzy clustering method for turbogenerator vibration faulty diagnosis［J］. Turbine Technology, 2002,44(5): 289291.
［5］ WELCH G, BISHOP G, An introduction to the Kalman filter［EB/OL］. 20080610. http://www.cs.unc.edu/～welch/media/pdf/kalman_intro.pdf
［6］ GAO Xingbo, XIE Weixin. Advances in theory and applications of fuzzy clustering［J］. Chinese Science Bulletin,2000,45(11)： 961970.
［7］ 王玲,穆志纯,郭辉一种基于聚类的支持向量机增量学习算法［J］.北京科技大学学报,2007,29(8),：855858.
WANG Ling, MU Zhichun, GUO Hui. A sort of support vector machine incremental learning algorithm based on clustering［J］. Journal of University of Science and Technology Beijing,2007, 29(8)： 855858.
No related articles found!