Predicting the risk of pipe failure using gradient boosted decision trees and weighted risk analysis

Abstract

Pipe failure prediction models are essential for informing proactive management decisions. This study aims to establish a reliable prediction model returning the probability of pipe failure using a gradient boosted tree model, and a specific segmentation and grouping of pipes on a 1 km grid that associates localised characteristics. The model is applied to an extensive UK network with approximately 40,000 km of pipeline and a 14-year failure history. The model was evaluated using the Receiver Operator Curve and Area Under the Curve (0.89), briers score (0.007) and Mathews Correlation Coefficient (0.27) for accuracy, indicating acceptable predictions. A weighted risk analysis is used to identify the consequence of a pipe failure and provide a graphical representation of high-risk pipes for decision makers. The weighted risk analysis provided an important step to understanding the consequences of the predicted failure. The model can be used directly in strategic planning, which sets long-term key decisions regarding maintenance and potential replacement of pipes.

Artificial intelligence underpins urban water infrastructure of the future: A holistic perspective

“…In water distribution systems, the deployment of online leakage detection and decision support tools can help pinpoint leaks (Zhou et al, 2019;Zaman et al, 2020;Wang et al, 2020b) and contamination event detection (Arad et al, 2013), and thus reduce the impacts of failure (Romano et al, 2014;Nikoloudi et al, 2021) through rapid interventions even before water services are affected. Machine learning can identify key factors of pipe failure related to infrastructure, operation and environmental factors, and thus help develop strategies for predictive maintenance (Barton et al, 2022). Machine learning can significantly improve leak localisation accuracy, even with a small amount of newly monitored data when implemented real-time (Zhou et al, 2019).…”

Evaluation of Pipe Materials in Water System Networks Using the Theory of Advanced Multi-Criteria Analysis

“…Using the number of pipe breaks per kilometer to measure damage to Kobe's water pipes shows that, on average, pipes break during earthquakes: AC 1.73, CI 1.49, PVC 1.38, and DI 0.47. The water distribution network had CI failures of 0.27, AC failures of 0.17, DI failures of 0.05, PVC failures of 0.17, and PE failures of 0.03 per km per year between 2005 and 2018 [114]. In a UK city, breaks in pipes, broken down by material, such as cast iron (45%), polyethene (22.3%), and asbestos cement (19%), of varying diameters (data from 1995-2018) are as follows: CI accounts for 69.3%, polyethene for 4.6%, and AC for 14.9% [56].…”

An Ensemble Learning Model for Forecasting Water-pipe Leakage

“…These studies include some of the most popular statistical models, such as linear regression (LR), poison regression (PR), and evolutionary polynomial regression (EPR). As machine-learning techniques, they use gradient boost trees (GB) [4][5][6][7] , Bayesian belief networks 8-10 , Support Vector Machines (SVMs) [11][12][13] and Arti cial Neural Networks (ANNs) 11,[14][15][16][17][18][19] . These studies have consistently found that ML models can provide valuable insights into the condition of these pipelines and help prioritize maintenance and repair efforts based on forecasting the failure rate of water pipes; however, ensemble approaches for water pipe leakage predictions have yet to be thoroughly investigated.…”