中國分類號： TE973；TP391.41
文獻標識碼： A
DOI： 10.19358/j.issn.2096-5133.2020.10.013
引用格式： 鄭林，張紅星，句海洋. 基于稀疏建模和SVM的管道缺陷分類方法研究[J].信息技術(shù)與網(wǎng)絡(luò)安全，2020，39(10)：67-74.

Research on pipeline defect classification based on sparse modeling and SVM

Abstract： The defect identification and evaluation of buried steel pipeline is a long-term challenge in the field of pipeline detection, and the prerequisite for efficient identification of defects is the accurate extraction of pipeline damage signals. Aiming at the characteristics of buried pipeline defect signals, a method of pipeline defect signal extraction and recognition is proposed, which is based on sparse modeling and support vector machine(SVM). A dictionary is obtained by learning from the original signal, the dictionary is used to construct a sparse model of the defect signal using a regularized orthogonal matching pursuit algorithm, and the feature vector of the signal is obtained according to the compressed sensing theory. Furthermore, multi-classification SVM is used to establish a mapping relationship between the feature vector of the defect signal and the actual defect type of the pipeline, and Genetic Algorithm-Particle Swarm Optimization is used to guide the selection of SVM parameters. The results showed that the proposed classification method can realize the accurate division of the damage degree of pipeline defects, which has been successfully verified in the laboratory and applied to the engineering field detection of an oil field in North China.

Key words : sparse modeling；SVM；pipeline defect；classification method