| In the field of industrial inspection, because of a variety of problems that arise in the welding process, welding can lead to contain pore and crack defects and so on, affect the product's quality. So defect detection of the welding image is very important. The influence of the traditional X-ray weld image of testing technology and experience, weld defect detection gradually transition to the computer intelligent identification from artificial detection. Using the X-ray real-time detection system of on-line detection and analysis.We can effectively overcome the errors caused by artificial detection, thus make online testing work objectification, standardized.This topic research on portable digital weld film detector, the foundation of the digital image processing technology, and discusses the portable image acquisition and processing system development, research, and technical realization. And the paper determines the choice of straightness, edge sharp, the ratio of circumference and area and filling index, symmetry and relative grayness as the recognition of the analysis parameters, the weld image recognition system is established based on the BP neural network by the application of Matlab for fault type of pattern recognition.Firstly, the paper introduces digitized weld film development situation of detector at home and abroad and the overall design. System is divided into four parts:pass agencies, stepping control, image acquisition system, and the lighting design. Detail description of pass agencies and the stepping motor control's function and design. It introduces image processing and pattern recognition of weld defect plate. |
PDF Full Text Request