A coupling model of multi-feature fusion and multi-machine learning model integration for defect recognition

Abstract

As Oil and gas pipelines are vulnerable to physical defects such as dents, cracks and corrosion leading to the risk of pipeline leakage. In this context, the recognition of these pipeline defects by using magnetic flux leakage (MFL) signal can provide a reliable reference and a good evaluation standard for predicting the remaining life of in-service pipelines. Nevertheless, the complexity of the MFL signal brings severe challenges to the recognition accuracy. This study, therefore, proposes a new coupling model for defect recognition based on multi-feature fusion and multi-machine learning model integration. This model is divided into three analysis phase, namely feature extraction phase, feature fusion phase and defect recognition phase. In the first phase, three kinds of features are extracted to obtain as much defect MFL signal information as possible. In the second phase, a multi-feature fusion method based on Dempster-Shafer (DS) evidence theory and Apriori algorithm is proposed, eliminating redundant features and realizing information complementation between different feature sets. In the third phase, we introduce a multi-machine learning model integration network (Stacking) to improve the defect recognition accuracy, which is inputted by the feature subset obtained from multi-feature fusion. By combining multi-feature fusion method with the Stacking mechanism, this coupling defect recognition model realizes the recognition of defect MFL signals. Experimental work shows that the proposed model improves the recognition accuracy and has the advantages of strong anti-jamming ability.