Abstract
AbstractPipe failure models can aid proactive management decisions and help target pipes in need of preventative repair or replacement. Yet, there are several uncertainties and challenges that arise when developing models, resulting in discord between failure predictions and those observed in the field. This paper aims to raise awareness of the main challenges, uncertainties, and potential advances discussed in key themes, supported by a series of semi-structured interviews undertaken with water professionals. The main discussion topics include data management, data limitations, pre-processing difficulties, model scalability and future opportunities and challenges. Improving data quality and quantity is key in improving pipe failure models. Technological advances in the collection of continuous real-time data from ubiquitous smart networks offer opportunities to improve data collection, whilst machine learning and data analytics methods offer a chance to improve future predictions. In some instances, technological approaches may provide better solutions to tackling short term proactive management. Yet, there remains an opportunity for pipe failure models to provide valuable insights for long-term rehabilitation and replacement planning.
Highlights
Pipe failures result in billions of litres lost from water networks each day, which wastes water, causes damage to infrastructure, and interrupts continuous service
Challenges of managing data Many Water Distribution Networks (WDN) consist of an antiquated asset base nearing the end of their engineering life span (Snider & McBean 2019)
Due to the lack of historical data, attempts have been made at pooling data from different water companies to increase the size of data sets, such as the UKWIR National Mains Failure Database (NMFD) (UKWIR 2020)
Summary
Pipe failures result in billions of litres lost from water networks each day, which wastes water, causes damage to infrastructure, and interrupts continuous service. Considerable effort is being concentrated on minimising water loss and improving services through performance commitments aimed to reduce pipe failures (Ramirez et al 2020; Robles-Velasco et al 2020). Water companies are moving towards data analytics and statistical models (referred to hereafter as pipe failure models) to provide insights for proactive management decisions. Pipe failure models represent a distinct field of data analytics, and commencing with Shamir & Howard (1979), they are still considered innovative today with the emergence and application of machine learning approaches and big data. Uncertainties are an integral part of prediction modelling, and underlying many pipe failure studies are issues surrounding data quality and quantity and model
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
