基于多传感器信息融合的机器人故障诊断  

Fault Diagnosis of Robots Based on Multi-Sensor Information Fusion

作　　者：王秀青[1] 侯增广[2] 曾慧[3] 吕锋[1] 潘世英[1] 

机构地区：[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

出　　处：《上海交通大学学报》2015年第6期793-798,共6页Journal of Shanghai Jiaotong University

基　　金：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

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.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 obstruc- tion, 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 7 of the SVM by grid searching, the proposed method can successfully diagnose the faults of obstruction, front collision and collision. Besides, the selec- tion 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 sam- pling data influences the number of fusion data obtained and the accuracy of classification.

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 

分 类 号：TP24[自动化与计算机技术—检测技术与自动化装置]