Application of soft computing for the optimal parameter design of weldment

This research proposes an economic and effective experimental design method of multiple characteristics to deal with the parameter design problem with many continuous parameters and levels. It uses TOPSIS (Technique for Order Preference by Similarity to Ideal Solution) and ANN (Artificial Neural Network) to train the optimal function framework of parameter design. It combines SC (Soft Computing) of SA (Simulated Anneal) and GA (Genetic Algorithm) to search the optimal parameters combination for the optimal parameter of weldment. To improve previous experimental methods for multiple characteristics, this research method employs SA to search the optimal parameter such that the potential parameter can be evaluated more completely and objectively. Additionally, the model can learn the relationship between the welding parameters and the quality responses of different materials to facilitate the future applications in the decision-making of parameter settings for automatic welding equipment. The research results can be presented to the industries as a reference, and improve the product quality and welding efficiency to relevant welding industries.