A Genetic Algorithm-Based Artificial Neural Network Approach for Parameter Selection in the Production of Tailor-Welded Blanks

  • Authors:

  • Yun Liu;De Xu;Xiuqing Wang;Min Tan;Yongqian Zhang

  • Affiliations:

  • The Key Laboratory of Complex Systems, and Intelligent Science, Institute of Automation, Chinese Academy of Sciences, Beijing, 100080, P.R. China;The Key Laboratory of Complex Systems, and Intelligent Science, Institute of Automation, Chinese Academy of Sciences, Beijing, 100080, P.R. China;The Key Laboratory of Complex Systems, and Intelligent Science, Institute of Automation, Chinese Academy of Sciences, Beijing, 100080, P.R. China;The Key Laboratory of Complex Systems, and Intelligent Science, Institute of Automation, Chinese Academy of Sciences, Beijing, 100080, P.R. China;The Key Laboratory of Complex Systems, and Intelligent Science, Institute of Automation, Chinese Academy of Sciences, Beijing, 100080, P.R. China

  • Venue:
  • ISNN '07 Proceedings of the 4th international symposium on Neural Networks: Advances in Neural Networks, Part III
  • Year:
  • 2007

Quantified Score

Hi-index 0.00

Visualization

Abstract

Laser cutting and welding is an efficient way to produce Tailor-Welded Blanks (TWBs). A genetic algorithm (GA)-based artificial neural network (ANN) approach is designed for parameter selection of laser cutting and welding to produce TWBs. These parameters include laser power for cutting and welding, speed for cutting and welding, and pressure of assistant gas. Experimental results demonstrate that the proposed parameter selection approach combines the merits of GA and ANN, and solves the problem of local optimum in ANN and low convergence speed in GA. As a result, it tackles the difficulty in parameter selection of laser cutting and welding and paves the way for TWBs' production.