An adaptive inspection-method for industrial welding seam based on ISOMAP algorithm and the modification of BP ANN

This article adopts the adaptive momentum adjustments to standardize various lighting parameters, so as to improve its adaptive property for the circumstance. By nonlinear dimensionality reduction, the original data space are compressed into eigenvalue pattern space, then the original data are gathered in a less and effective eigenvalue expression. By using the modification of BP ANN to classify the data pattern space, it can do self-teaching and improve the correct inspection rate and realtime performance. This algorithm has been applied in the realtime inspection of industrial welding seam. It has a strong ability of adaptive, self-teaching, high inspection rate and real-time performance.