Pipelines Failure Prediction Modelling for Onshore Gas Transmission Pipelines Using Machine Learning

Dea Amrializzia, Andy Noorsaman

Research output: Chapter in Book/Report/Conference proceedingConference contribution


Transmission pipeline is the safest and most effective way to transport large amounts of natural gas over long distances. Although transportation using pipelines is the safest, transmission pipeline failures can cause damage, financial losses, and injuries. A good preventive maintenance schedule is desired, which aims to predict break pipes proactively. In this paper, we present a prediction model of onshore gas transmission pipeline failure using machine learning with R software. The model presented is developed based on historical failure that includes structured and unstructured from the onshore gas transmission pipelines from approximately 2010-2020 released by the US Department of Transportation. The applying process can be divided into various steps: data pre-processing, model training, model testing, performance measuring, and failure predicting. By using machine learning, we can conclude that it is an effective method to work with a complex dataset for predicting pipe failures. It can provide significant improvement for the safe economic operation of pipelines.
Original languageEnglish
Title of host publicationIESC2020: International Engineering Students Conference 2020
PublisherEasy Chair
Number of pages7
Publication statusPublished - 2020


Dive into the research topics of 'Pipelines Failure Prediction Modelling for Onshore Gas Transmission Pipelines Using Machine Learning'. Together they form a unique fingerprint.

Cite this