Title :
A fuzzy radial basis function neural network for predicting multiple quality characteristics of plasma arc welding
Author :
Chi, Sheng-Chai ; Hsu, Li-Chang
Author_Institution :
Dept. of Ind. Manage., Huafan Univ., Taiwan
Abstract :
We have developed an intelligent decision support system for plasma arc welding based on a fuzzy radial basis function (RBF) neural network. This approach may solve the following problems: (1) the time-consuming learning of backpropagation neural networks, (2) the fluctuation of the values of parameters during welding, and (3) fuzzy linguistic-term judgment for welding quality. Based on the results obtained from Taguchi experiments, the developed fuzzy neural network can be trained to establish a quality prediction system for plasma arc welding. The developed system can also be applied to predict the welding quality for different designs of welding parameters, which are not trained. In addition, the system may support the plotting of a diagram of the 3D suitability region of the three remaining parameters when one parameter is fixed
Keywords :
Taguchi methods; arc welding; backpropagation; decision support systems; expert systems; fuzzy neural nets; mechanical engineering computing; radial basis function networks; 3D suitability region diagrams; Taguchi method; backpropagation; fuzzy linguistic-term judgment; fuzzy radial basis function neural network; intelligent decision support system; learning; multiple quality characteristics prediction; neural network training; plasma arc welding; welding parameter value fluctuations; welding quality; Backpropagation; Decision support systems; Fluctuations; Fuzzy neural networks; Fuzzy systems; Intelligent networks; Intelligent systems; Neural networks; Plasma welding; Radial basis function networks;
Conference_Titel :
IFSA World Congress and 20th NAFIPS International Conference, 2001. Joint 9th
Conference_Location :
Vancouver, BC
Print_ISBN :
0-7803-7078-3
DOI :
10.1109/NAFIPS.2001.943671
