Self-learning fuzzy neural networks and computer vision for control of pulsed GTAW

The objective of this research is to apply intelligent control methodology to improve weld quality. Based on fuzzy logic and artificial neural network theory, a self-learning fuzzy and neural network control scheme has been developed for real-time control of pulsed gas tungsten arc welding (GTAW). Using an industrial TV camera as the sensor, the weld face width of the weld pool, i.e., the feedback signal in the closed loop system, is obtained by computer image processing techniques. The computer vision providing process status information in real-time is an integral part of self-learning fuzzy neural control system. Such a system enables adaptive altering of welding parameters to compensate for changing environments. The experiments on the control of the pulsed GTAW process show that the scheme presented in this paper can be used to control complicated variables such as encountered in welding processes.

[1]  N. M. Carlson,et al.  Control of GMAW: detection of discontinuities in the weld pool , 1992 .

[2]  Jyh-Shing Roger Jang,et al.  Self-learning fuzzy controllers based on temporal backpropagation , 1992, IEEE Trans. Neural Networks.

[3]  E. H. Mamdani,et al.  Practical application of a heuristic fuzzy rule-based controller to the dynamic control of a robot arm , 1985 .

[4]  Wjm Walter Kickert,et al.  ANALYSIS OF A FUZZY LOGIC CONTROLLER , 1978 .

[5]  John Y. Cheung,et al.  Design of a fuzzy controller using input and output mapping factors , 1991, IEEE Trans. Syst. Man Cybern..

[6]  L. Wu,et al.  Self-learning fuzzy neural networks for control of uncertain systems with time delays , 1997, IEEE Trans. Syst. Man Cybern. Part B.

[7]  Q. L. Wang,et al.  Separately excited resonance phenomenon of the weld pool and its application , 1993 .

[8]  W. H. Giedt,et al.  THE TRANSITION FROM SHALLOW TO DEEP PENETRATION DURING ELECTRON BEAM WELDING , 1990 .

[9]  H. R. van Nauta Lemke,et al.  Application of a fuzzy controller in a warm water plant , 1976, Autom..

[10]  Shigeo Abe,et al.  Neural Networks and Fuzzy Systems , 1996, Springer US.

[11]  Peter J. Gawthrop,et al.  Neural networks for control systems - A survey , 1992, Autom..

[12]  Hamid R. Berenji,et al.  Learning and tuning fuzzy logic controllers through reinforcements , 1992, IEEE Trans. Neural Networks.

[13]  B. Widrow,et al.  Neural networks for self-learning control systems , 1990, IEEE Control Systems Magazine.

[14]  Ebrahim H. Mamdani,et al.  A linguistic self-organizing process controller , 1979, Autom..

[15]  J.A. Bernard,et al.  Use of a rule-based system for process control , 1987, IEEE Control Systems Magazine.

[16]  Chuen-Chien Lee,et al.  A self‐learning rule‐based controller employing approximate reasoning and neural net concepts , 1991, Int. J. Intell. Syst..

[17]  S. J. Marburger,et al.  Arc welding penetration control using quantitative feedback theory , 1992 .

[18]  Julian Morris,et al.  Artificial neural networks in process estimation and control , 1992, Autom..

[19]  Celal Batur,et al.  Adaptive expert control , 1991 .

[20]  B. A. Chin,et al.  Infrared Sensing for Adaptive Arc Welding Infrared thermography is used to sense depth of penetration , 1989 .

[21]  S. I. Rokhlin,et al.  Computerized radiographic sensing and control of an arc welding process , 1990 .