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

The paper adopts an adaptive momentum adjustments algorithm to standardize various lighting parameters, so as to improve its adaptive capacity for the environment. By PCA algorithm, the original data space is compressed into an eigenvalue pattern space, then the data will gather in a lesser effective eigenvalue space. Using the modification of BP ANN to classify the data pattern space, it can realize the system´s self-teaching function, and improve the correct-inspection rate and real-time performance as well. This algorithm has been widely applied in the real-time inspection of industrial welding seam. It has strong ability of adaption and self-teaching, higher inspection rate and real-time performance.