Title :
Neurofuzzy model based control of weld fusion zone geometry
Author :
Zhang, Y.M. ; Li, B. ; Kovacevic, R.
Author_Institution :
Center for Robotics & Manuf. Syst., Kentucky Univ., Lexington, KY, USA
Abstract :
A closed-loop system is developed to control the weld fusion which is specified by the top-side and back-side bead widths of the weld pool. The welding current and speed are selected as the control variables. It is found that a nonlinearity exists in the process being controlled. A neuro-fuzzy model is used to model this nonlinear dynamic process. Based on the dynamic fuzzy model, a predictive control system has been developed to control the welding process. Experiments confirmed that the developed control system is effective in achieving the desired fusion state despite the different disturbances
Keywords :
arc welding; closed loop systems; electric current control; fuzzy control; neurocontrollers; nonlinear dynamical systems; predictive control; velocity control; arc welding; closed-loop system; current control; multivariable systems; neuro-fuzzy model; nonlinear dynamic process; nonlinearity; predictive control; speed control; state estimation; weld fusion control; Control systems; Fuzzy control; Fuzzy systems; Geometry; Nonlinear dynamical systems; Predictive control; Predictive models; Process control; Solid modeling; Welding;
Conference_Titel :
American Control Conference, 1997. Proceedings of the 1997
Conference_Location :
Albuquerque, NM
Print_ISBN :
0-7803-3832-4
DOI :
10.1109/ACC.1997.609225
