Defects Detection Algorithm For On-line Automatic Detection Of Welding Defects

Welding is an important technology in the shipbuilding. The defects, such as blowholes and incomplete penetration, may appear in the welding process occasionally. The quality and the security of products can be affected by these defects. Therefore, defects detection in welding seam is extremely important. Now, the on-line detection of the welding defects is still done by human interpreter. This way of detection is subjection and labor intensive of interpreter. It is desirable to find an effective automatic defects detection method to assist human interpreter in evaluating the quality of weld and to make the on-line detection objective, standard and intelligent. Our research is based on this.The key problem of on-line automatic detection is detecting the defects exactly and efficiently. A new defects detection method is studied in this paper and the following research is mainly done:(1) Since much noise is contained in the X-Ray image, morphological filter is used to suppress the noise. This method can increase the precision of detection.(2) The welding flaws of "crack", "lack of fusion" and "incomplete penetration" are usually linear structures with the direction along the weld seam. Therefore, we make use of the oriented filter in our detection approach. The results indicate that this method is effective.(3) The conservation of the X-Ray image and the detection information is very important in the on-line automatic detection system. The DICOM standard is used to conserve the X-Ray image and the detection information.In order to confirm the validity of the method in this paper, we have detected the weld seam images with some defects, which are obtained from the factory. The X-Ray image and the detection information are conserved in the format of DICOM. The results show that our method is valid and satisfied.