Classified recognition for metal magnetic memory signals of welding defects in API 5L X65 pipeline steel

Feature extraction and selection from signals is a key issue for metal magnetic memory testing technique. In order to realize the classification of metal magnetic memory signals of welding defects, four fractal analysis methods, such as box- counting, detrended fluctuation, minimal cover and rescaled-range analysis, were used to extract the feature signal after the original metal magnet memory signal was de-noising and differential processing, then the Karhunen-Lo~e transformation was adopted as classification tool to identify the defect signals. The result shows that this study can provide an efficient classification method for metal magnetic memory signal of welding defects.