考虑多故障同发的可重构机械臂分散主动容错控制  

Decentralized active fault-tolerant control for reconfigurable manipulator with simultaneous faults

作　　者：杜艳丽[1,2] 李元春[1,3] 

机构地区：[1]吉林大学汽车仿真与控制国家重点实验室,吉林长春130012 [2]北华大学电气信息工程学院,吉林吉林132021 [3]长春工业大学控制工程系,吉林长春130012

出　　处：《中南大学学报（自然科学版）》2014年第3期727-733,共7页Journal of Central South University:Science and Technology

基　　金：国家自然科学基金资助项目(60974010);吉林省科技发展计划项目(20110705)

摘　　要：针对含有传感器故障及执行器故障的可重构机械臂系统的轨迹跟踪问题,提出一种基于滑模观测器的分散主动容错控制方法。通过引入一个新增状态将传感器故障等效为执行器故障,针对新系统构造滑模观测器,并用模糊神经网络去逼近可重构机械臂各关节间的非线性项及关联项,进而实现对不同类型传感器故障及执行器故障的重构。最后对2个不同构型的三自由度可重构机械臂进行仿真。研究结果表明:该方法不需进行故障诊断,通过实时重构故障,能够及时实现主动容错控制。仿真结果验证了所提方法的有效性。To solve the trajectory tracking problem of reconfigurabie manipulator with sensor faults and actuator faults,adecentralized active fault-tolerant control method based on sliding mode observer was investigated.The sensor faults were equated to the actuator faults by introducing a new state.Based on these works, a sliding mode observer aiming at the new system which nonlinear terms and interconnection terms were approximated by fuzzy neural network was constructed,and the different types of sensor faults and actuator faults were reconstructed. Finally, two 3-DOF （degree of freedom） reconfigurable manipulators of different configurations were simulated.The results show that using the proposed method,the fault diagnosis does not need to be carried out and the active fault-tolerant control can be timely realized through real-time reconstruction fanlts.The simulation results validate the effectiveness of the proposed method.

关 键 词：可重构机械臂 滑模观测器 主动容错控制 传感器故障 执行器故障 模糊神经网络 

分 类 号：TP24[自动化与计算机技术—检测技术与自动化装置]