Kinematics Modeling and Real-Time Seam Tracking for Welding Mobile Robot

Abstract

Kinematics modeLing of the developed welding mobile robot is presented and a real time seam tracking algorithm based on fuzzy neural network is proposed. At first, the kinematics behavior of mobile robot body and cross sLiders action to the welding torch are investigated by the Denavit-Hartenberg(D-H) Homogeneous transformation method, and a full kinematics model is estabLished. And then a seam tracking controller based on fuzzy-gaussian neural network (FGNN) is described by applying a Gaussian function as an activation function, lateral sLider position and heading angle of the robot act as input signals, and adjusted angle for welding torch acts as output, a speciaLized learning architecture is used so that membership function can be tuned in real time by applying the back propagation algorithm of FGNN controller. The experiment results show that the proposed controller has excellent tracing accuracy (within ±0.5mm), and can satisfy the requirement of practical welding project.