Seam Tracking Based on Fuzzy-Gaussian Neural Network for Mobile Welding Robot

Abstract

To solve the seam tracking problem of the welding mobile robot, adaptive fuzzy controller and fuzzy-Gaussian neural network (FGNN) controller are designed to complete coordinately controlling of cross-slider and wheels. The fuzzy-neural control algorithm was described by applying a Gaussian function as an activation function, taking lateral slider position and the error between the robot moving direction and the seam direction as the inputs signals, and the adjusted angle for welding torch as the output, a specialized learning architecture was used so that membership function would be tuned in real time by applying the FGNN controller. The simulation results on MATLAB show that the proposed controller has excellent tracing accuracy (within 0.5mm) and can satisfy the requirement of practical welding project.