Acceleration reflects vibration of a robot,and the vibration signal can reflect the operation state of the robot. Generally,detection of robot mechanical arm failure requires installing sensors on each joint. This stu...Acceleration reflects vibration of a robot,and the vibration signal can reflect the operation state of the robot. Generally,detection of robot mechanical arm failure requires installing sensors on each joint. This study proposes a method to diagnose the fault by single acceleration sensor only,which is installed at the end of the robot. The operation state of the robot is evaluated by analyzing vibration characteristics of its acceleration. First,a data acquisition function of a programmable multi-axis controller is applied to extract practical motion signals of the robot joints during operation,and practical motion signals are analyzed. Second,synthetic methods to determine acceleration of the end joints of SCARA robots in a Cartesian space is used based on the theory of the Jacobian matrix and the frequency domain of final acceleration is investigated. The relationship between end-and joint-vibration frequencies under given speeds is determined. Then,the method is verified by comparing characteristic frequencies of joint acceleration and synthetic acceleration in Cartesian coordinate system at different speeds. Finally,some faults can be diagnosed by comparing the acceleration vibration frequency extracted by a single acceleration sensor installed at the end of robot with the normal running state. Thus,this method can be used to monitor the signal variation of each joint without installing sensors on each robot joint.展开更多
基金Supported by the National Natural Science Foundation of China(No.51775284)Natural Science Foundation of Jiangsu Province(BK20151505)Joint Research Fund for Overseas Chinese,Hong Kong and Macao Young Scholars(61728302)
文摘Acceleration reflects vibration of a robot,and the vibration signal can reflect the operation state of the robot. Generally,detection of robot mechanical arm failure requires installing sensors on each joint. This study proposes a method to diagnose the fault by single acceleration sensor only,which is installed at the end of the robot. The operation state of the robot is evaluated by analyzing vibration characteristics of its acceleration. First,a data acquisition function of a programmable multi-axis controller is applied to extract practical motion signals of the robot joints during operation,and practical motion signals are analyzed. Second,synthetic methods to determine acceleration of the end joints of SCARA robots in a Cartesian space is used based on the theory of the Jacobian matrix and the frequency domain of final acceleration is investigated. The relationship between end-and joint-vibration frequencies under given speeds is determined. Then,the method is verified by comparing characteristic frequencies of joint acceleration and synthetic acceleration in Cartesian coordinate system at different speeds. Finally,some faults can be diagnosed by comparing the acceleration vibration frequency extracted by a single acceleration sensor installed at the end of robot with the normal running state. Thus,this method can be used to monitor the signal variation of each joint without installing sensors on each robot joint.
