Search

It is of great significance to detect the weld surface to ensure welding quality. Aiming at the problem of weld surface defect detection and 3D reconstruction algorithm, a method of defect detection and three - dimensional reconstruction based on laser scanning 3D point cloud has been proposed. The method of BP neural network is used to filter the point cloud data obtained by laser displacement sensor scanning, and the result is qualitatively and quantitatively analyzed. The three-dimensional reconstruction model of pit defects on weld surface is established. The reconstructed error is within the allowable range. The experimental results show that applying BP neural network to weld defect detection can effectively reduce the complexity of 3D reconstruction and improve the accuracy of 3D reconstruction of weld surface.

Magneto-optical imaging is based on the theory of leakage magnetic field and the Faraday magneto-optical effect. A magnetic dipole model of pit was established and verified by comparing with gray value of magneto-optical image of pit. The sag, pit, non-melting and non-defect of welded pieces made in the detection of magneto-optical were simulated by the two-dimensional finite element models. The magnetic induction intensity distributions of defects in the lift strength of 1mm were obtained in the simulations. Experiments on detecting the defects referred above by magneto-optical detection were carried out and magneto-optical images of the defects were acquired. The simulations were proved reliable when compared with magnetic field distribution of models and gray curves of magneto-optical images of the corresponding defects. Also, these models analyzed magnetic induction intensity distributions of different defects in different strengths of lift. Furthermore, it provided the theoretical and experimental basis for further study of the mechanism of magneto-optic imaging.