• CN: 11-2187/TH
  • ISSN: 0577-6686

›› 2004, Vol. 40 ›› Issue (1): 151-154.

• Article • Previous Articles     Next Articles

12-D STATISTICAL VECTOR BASED NEURO-FUZZY SYSTEM FOR GMAW PROCESS MONITORING

Wu Chuansong;Hu Qingxian;Sun Junsheng;Polte T.;Rehfeldt D.   

  1. Shandong University Hannover University, Germany
  • Published:2004-01-15

Abstract: The test data of probability density distribution (PDD) and class frequency distribution (CFD) of electrical parameters in GMAW are further processed, and their statistical values of mean, variance and standard deviation are used to set up a 12-dimensional vector S12 for describing GMAW processes under different welding conditions. The merits of neural network and fuzzy logic technology are combined together to develop a neuro-fuzzy system FKCN, which can automatically recognize 24 test cases under 8 kinds of welding conditions with a correct rate of 100%.

Key words: GMAW, Intelligent recognition, Neuro-fuzzy system, Process monitoring

CLC Number: