Font Size: a A A

Automatic Detection And Recognition Of Defects In X-ray Non-destructive Flaw Detection

Posted on:2004-03-01Degree:MasterType:Thesis
Country:ChinaCandidate:E L WangFull Text:PDF
GTID:2208360092480708Subject:Communication and Information System
Abstract/Summary:PDF Full Text Request
X-ray defect detection is one of the primary methods in non-destructive testing of industrial products and is also widely applied. Now, detection of defects in the weld is still done by human interpreter. The problems of this process are subjective, inconsistent, labor intensive and fatigue of interpreter. It is desirable to develop a computer-aided system to assist human interpreter in evaluating the quality of weld and make the on-line detection objectivity, standardization, intelligent.As the reasons above, an X-ray real-time defect auto-detection system is realization in this thesis. Some researches have been lain out as follows:1. Components of the system are realized. The system is made up of signal transformation part, image processing part, acquirement and transport of the position of defect part.2. The measurement of defect and the common image processing methods are realized, such as histograms showing, invert transform, fake-color transform and curve transform.3. The noise of X-ray system is researched and the method of reducing the noise is taken up due to the environment of factory.4. A fast pick-up method of weld area is used before using the defect detection algorithm. The weld area and background area are separated by the fast pick-up method. So the operational time and the operational processing are reduced.5. After deeply research and analyze some defect detection methods, an algorithm of fuzzy pattern recognition is applied. The algorithm is based on spatial characteristics (spatial variance and spatial contrast) near the defect. Compared with other defect detection methods, the major advantages of this fuzzy method are as follows: easy, fast, simple, flexible and stable. It is shown through experiments that the system has low rate of wrong evaluation.6. Through the introduction of acquirement and transportation of defect's information, the auto-recognition of defect is realized.Now, there is no real-time defect auto-detection in X-ray system in domestic factory. In this thesis, defect auto-detection and auto-recognition is the emphases of research and it keeps ahead in domestic research.The X-ray real-time defect auto-detection system has been used in the Steel Pipe Factory of China National Petroleum Corporation for half a year and has achieved some benefits.
Keywords/Search Tags:NDT, weld defects, automatic detection, fuzzy algorithm, defect recognition
PDF Full Text Request
Related items