Detection and sizing of metal-loss defects in oil and gas pipelines using pattern-adapted wavelets and machine learning

详细信息    查看全文

• 作者：Mohamed Layouni^a ; ^b ; ^{layouni@ece.concordia.ca} ; Mohamed Salah Hamdi^a ; ^{mshamdi@abmmc.edu.qa} ; Sofiè ; ne Tahar^b ; ^{tahar@ece.concordia.ca}
• 关键词：Oil and gas pipelines ; Safety assessment ; Pattern-adapted wavelets ; Pattern recognition ; Neural networks ; Machine learning ; Defect location ; Defect sizing ; Magnetic flux leakage
• 刊名：Applied Soft Computing
• 出版年：2017
• 出版时间：March 2017
• 年：2017
• 卷：52
• 期：Complete
• 页码：247-261
• 全文大小：6086 K
• 卷排序：52

文摘

Oil and gas pipelines are subject to many types of metal-loss defects. Those defects can pose a high risk to the operational safety of the pipeline. This paper proposes a solution to detect, locate, and estimate the size of defects. The proposed solution uses pattern-adapted wavelets and artificial neural networks. The proposed solution is general and applies to a wide range of defect shapes.