Efficient Qualitative Risk Assessment Of Pipelines Using Relative Risk Score Based On Machine Learning

This research paper presents the use of machine learning techniques in pipeline risk assessment. Sohaib et al. proposed a method for detecting leaks in circular water storage tanks using acoustic emissions. Mazumder et al. used machine learning algorithms to analyze the risk of failure of a steel pipeline. Yang et al. demonstrated urban gas data-driven pipeline accidents and consequences assessment using machine learning. Liu and Bao reviewed automated conditions for the assessment of pipelines with machine learning. Wu et al. presented FTAP: A feature-transferring autonomous machine learning pipeline.