Principal component analysis based artificial neural networks for arc welding quality control

In this paper,the application of principal component analysis (PCA) and artificial neural networks (ANN) to the multivariate statistical analysis and quality control was introduced.The pool width control of MAG weld with high current was taken as an example.Through the PCA of 6 welding parameters,4 main factors were extracted.The relationship between main factors and original parameters was discussed.The PCA values were taken as the new training sample set and the output results indicated both the convergent speed and the training accuracy of PCA-based ANN were much better than those of basic BP ANN.