Research Review on Drainage Pipe Defect Identification Technology
Liangxiao Zhang *
North China University of Water Resources and Electric Power, China.
*Author to whom correspondence should be addressed.
Abstract
As urban underground drainage networks age, various internal defects gradually develop in pipelines, compromising their operational efficiency. Consequently, condition assessment of drainage systems has become essential for municipal authorities. However, manual inspection methods remain prevalent due to inefficiency and subjectivity, often leading to misjudgments. To address these challenges, researchers have integrated pipeline detection technologies with machine learning and deep learning frameworks, achieving automated and efficient defect identification. This paper systematically reviews existing methodologies and research achievements in drainage pipeline defect recognition, providing a comprehensive overview of current approaches.
Keywords: Drainage pipes, defect identification, machine learning, deep learning