Estimation of Weld Pool Sizes in GMA Welding Process Using Neural Networks

In gas metal arc (GMA) welding processes, the geometrical shape and size of the weld pool are utilized to assess the integrity of the weld quality. Monitoring of these geometrical parameters for on-line process control as well as for on-line quality evaluation, however, is an extremely difficult problem. The paper describes the design of a neural network estimator to estimate weld pool sizes for on-line use in quality monitoring and control. The neural network estimator is designed to estimate the weld pool sizes from surface temperatures measured at various points on the top surface of the weldment. The main task of the neural network is to realize the mapping characteristics from the point temperatures to the weld pool sizes through training. The chosen design parameters of the neural network estimator, such as the number of hidden layers and the number of nodes in a layer, are based on an estimation error analysis. A series of bead-on-plate welding experiments were performed to assess the performance of the neural network estimator. The experimental results show that the proposed neural network estimator can estimate the weld pool sizes with satisfactory accuracy.

[1]  Geoffrey E. Hinton,et al.  Learning internal representations by error propagation , 1986 .

[2]  Kumpati S. Narendra,et al.  Identification and control of dynamical systems using neural networks , 1990, IEEE Trans. Neural Networks.

[3]  Hirokazu Nomura.  Back Bead Width Control in One Side SAW using Flux Copper Backing : Correlation between Back Bead Width and the Voltage as measured between Base Plate and Copper Backing (Report 1) , 1987 .

[4]  임태균,et al.  저항 점 용접에서 신경회로망을 이용한 용융부의 크기 예측에 관한 연구 ( Estimation of Nugget Size in Resistance Spot welding Using a Neural Network ) , 1990 .

[5]  G. Karsai,et al.  Artificial neural networks applied to arc welding process modeling and control , 1989, Conference Record of the IEEE Industry Applications Society Annual Meeting,.

[6]  Ryoichi Kajiwara,et al.  Relation between surface temperature and reverse side bead width in girth TIG welding for stainless steel tube - Study on penetration control of weld (Report III) , 1986 .

[7]  Hyungsuck Cho.  A neural network method for recognition of part orientation in a programmable bowl feeder , 1990 .

[8]  David Dornfeld,et al.  Sensor Integration Using Neural Networks for Intelligent Tool Condition Monitoring , 1990 .

[9]  H.E. Rauch,et al.  Neural networks for routing communication traffic , 1988, IEEE Control Systems Magazine.

[10]  Robert J. T. Morris,et al.  Neural Network Techniques for Object Orientation Detection: Solution by Optimal Feedforward Network and Learning Vector Quantization Approaches , 1990, IEEE Trans. Pattern Anal. Mach. Intell..

[11]  Bernard Widrow,et al.  Neural nets for adaptive filtering and adaptive pattern recognition , 1988, Computer.

[12]  George Chryssolouris,et al.  A Comparison of Statistical and AI Approaches to the Selection of Process Parameters in Intelligent Machining , 1990 .

[13]  M. Kawato,et al.  Hierarchical neural network model for voluntary movement with application to robotics , 1988, IEEE Control Systems Magazine.

[14]  博一 野村.  フラックス銅裏当て方式(FCB)片面溶接における裏ビード幅自動制御 , 1985 .

[15]  James L. McClelland,et al.  Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations , 1986 .

[16]  Yoh-Han Pao,et al.  Adaptive pattern recognition and neural networks , 1989 .

[17]  Hyungsuck Cho,et al.  Transient Temperature Distribution in Arc Welding of Finite Thickness Plates , 1990 .

[18]  M Morita,et al.  Observation and digital control of the molten pool in pulsed MIG welding , 1988 .

[19]  Miriam Zacksenhouse,et al.  Weld Pool Impedance Identification for Size Measurement and Control , 1983 .