Long-Term Pipeline Failure Prediction Using Nonparametric Survival Analysis

TL;DR

This paper develops a machine learning-based approach using nonparametric survival analysis to predict long-term water main failures in Australian cities, aiming to improve maintenance planning and reduce disruptions.

Contribution

It introduces a novel application of Random Survival Forests for long-term pipeline failure prediction and quantifies uncertainty in these predictions.

Findings

Random Survival Forest outperforms other algorithms and heuristics.

The model provides reliable long-term failure predictions.

Uncertainty quantification enhances decision-making.

Abstract

Australian water infrastructure is more than a hundred years old, thus has begun to show its age through water main failures. Our work concerns approximately half a million pipelines across major Australian cities that deliver water to houses and businesses, serving over five million customers. Failures on these buried assets cause damage to properties and water supply disruptions. We applied Machine Learning techniques to find a cost-effective solution to the pipe failure problem in these Australian cities, where on average 1500 of water main failures occur each year. To achieve this objective, we construct a detailed picture and understanding of the behaviour of the water pipe network by developing a Machine Learning model to assess and predict the failure likelihood of water main breaking using historical failure records, descriptors of pipes and other environmental factors. Our results indicate that our system incorporating a nonparametric survival analysis technique called "Random Survival Forest" outperforms several popular algorithms and expert heuristics in long-term prediction. In addition, we construct a statistical inference technique to quantify the uncertainty associated with the long-term predictions.