上海交通大学学报(自然版) ›› 2015, Vol. 49 ›› Issue (06): 793-798.

• 自动化技术、计算机技术 • 上一篇    下一篇

基于多传感器信息融合的机器人故障诊断

王秀青1,侯增广2,曾慧3,吕锋1,潘世英1   

  1. (1. 河北师范大学 职业技术学院, 石家庄 050024; 2. 中国科学院自动化研究所 复杂系统管理与控制国家重点实验室, 北京 100190; 3. 北京科技大学 自动化学院, 北京 100083)
  • 收稿日期:2015-03-18 出版日期:2015-06-29 发布日期:2015-06-29
  • 基金资助:

    国家自然科学基金(61175059, 61375010),中国科学院复杂系统管理与控制国家重点实验室开放课题(20120103),河北省自然科学基金(F2014205115)项目资助

Fault Diagnosis of Robots Based on Multi-Sensor Information Fusion

WANG Xiuqing1,HOU Zengguang2,ZENG Hui3,L Feng1,PAN Shiying1   

  1. (1. Vocational and Technical Institule, Hebei Normal University, Shijiazhuang 050024,  China;2. Key Laboratory of Complex Systems and Intelligence Science, Institute of Automation, Chinese Academy of Sciences, Beijing 100090, China; 3. School of Automation, University of Science and Technology Beijing, Beijing 100083, China)
  • Received:2015-03-18 Online:2015-06-29 Published:2015-06-29

摘要:

摘要:  提出一种新型的多传感器信息融合方法,并将此方法与支持向量机相结合,针对生产装配线上机械手在向抓握物体位置行进时遇到的机械手受阻、前方碰撞、除前方外其他方向碰撞3种故障形式进行诊断;通过适当融合向量的选取、支持向量机模型参数的寻优,成功地对3种故障进行了诊断;同时,对多传感器信息融合方法中的融合向量属性数量的选择进行了分析.结果表明,在传感器测量数据一定的条件下,融合数据属性数量的选取对融合向量样本的数量、分类的准确率均有影响.

关键词: 多传感器信息融合, 机器人, 故障诊断, 分类, 支持向量机

Abstract:

Abstract: A novel multi-sensor information fusion method  combined with the support vector machine (SVM) was proposed  in diagnosing three types of faults  which are collision, front collision and obstruction, as the robot’s arm approaches the grasping place.   After fusing the proper number of the data from multisensors and searching the optimal parameters C and γ of the SVM by grid searching, the proposed method can successfully diagnose the faults of obstruction, front collision and collision. Besides,  the selection of the number of the features of data to be fused by multisensor information fusion was discussed. The experimental results show that the selection of the proper number of the fusing features of the sampling data influences the number of fusion data obtained and the accuracy of classification.

Key words: multi-sensor information fusion, robot, fault diagnosis, classification; support vector machine (SVM)

中图分类号: