It’s a mammoth and expensive task to maintain the infrastructure that delivers perhaps the most essential of our essential services: water. But predictive analytics is saving money, water and disruption by helping utilities pinpoint the pipes in their networks at greatest risk of failure.
Pipe dream ensures failure isn’t an option
Researchers
Distinguished Professor Fang Chen
Associate Professor Wang Yang
Research centre
Data Science Institute
Faculty
Faculty of Engineering and Information Technology
Funded by
Sydney Water
Western Water
UnityWater
Queensland Urban Utilities
SA Water
UK Water Industry Research
{info} Learn more about UTS research
Australia, for instance, has over 140,000 kilometres of water pipes, enough to go around the earth nearly four times. This infrastructure is mostly out of sight, out of mind—until a pipe breaks and we lose water or are inundated by it.
Then, the disruption of a major pipe failure can affect everyone from the utility that has to conduct urgent maintenance, the business and residential customers without water, through to commuters stuck in traffic as urgent repairs are made.
Longer term, the expense of pipe repair and renewal has the potential to impact all of us through higher bills. With water, preventing leaks and loss is also vital to drought resilience.
Ageing infrastructure
“The built world, just like human beings, gets older every day,” says Professor Fang Chen, Executive Director of the Data Science Institute at the University of Technology Sydney (UTS). Australia’s water pipes are now, on average, 80 years old.
Just like a human octogenarian, this infrastructure needs closer monitoring and “preventive medicine” to keep it going strong, she says. With pipe replacement costing thousands of dollars a metre, and given budget constraints, “the only choice is smarter maintenance”.
Professor Chen and Associate Professor Yang Wang lead an award-winning team of scientists in the UTS Data Science Institute focused on data-driven solutions for industry. As well as water, the institute’s Smart Infrastructure team works with the owners of pipes delivering sewerage and gas services around the world.
Collaborating with more than 30 utilities in Australia and internationally, they’ve examined 1 million pipe failure records for 10 million pipes over the past decade
Using advanced machine learning techniques and multiple sources of data, “we help owners understand their infrastructure’s performance, we help them to predict infrastructure failure, and we help them to reduce costs by carrying maintenance out in a more efficient way”, Assoc Prof Wang says.
The only choice is smarter maintenance
— Prof Fang Chen, UTS
In the water sector, this work has helped reduce the cost of utilities responding to failures in critical water mains by more than 20 per cent. What’s more, they can now allocate a much greater share of budget to proactive work that improves the network and prevents disruption in the first place, versus reactive maintenance that responds to leaks and ruptures once they happen.
This sort of impact earned the team an “Oscar” for science in the form of the Australian Museum Eureka Prize for Excellence in Data Science in 2018.
Picking pipes
One utility provided the UTS researchers with data extending back 20 years, to the start of its digital records, so they could develop a pipe failure prediction tool to help it better target its maintenance and renewal budget.
The tool uses data on factors such as when pipes were laid, what they’re made of, the physical environment in which they exist—in a sandy or clay base, for instance—along with operational parameters such as running pressure and presence of chemicals. Incident or failure records showing what has happened in the past and why also feed into the tool.
“With the big, critical water mains, for example, the cost of human inspection cost is high and utilities can't afford to inspect all of them each year,” Prof Yang says. “With our prediction tool we can identify and visualise high-risk pipes on a map-based platform to help them prioritise pipes for further condition assessment.”
We can visualise high-risk pipes … to help them prioritise pipes for further condition assessment
— Assoc Prof Yang Wang, UTS
Ahead, the prediction tool will also help utilities select pipes for the application of cutting-edge technology such as acoustic sensors that monitor for vibrations caused by leaks. In turn, sensor technology will add even more information into the predictive analytics tool, Prof Chen says.
The researchers are also extending their work into areas such as the analysis of demand for water, the development of intelligent energy saving in pumping stations, and fine-tuning of sewer chemical dosing.
Researchers
Professor Fang Chen is a leader in artificial intelligence and data science with an international reputation and industry recognition. She led the team won the 2018 Australian Museum Eureka Prize for Excellence in Data Science. Fang has created many innovative research and solutions, transforming industries through AI and data science. She has helped industries worldwide advance towards excellence by increasing productivity, innovation, profitability and customer satisfaction. This has won her industry recognition, including being named NSW Water Professional of The Year in 2016. She has 300+ refereed publications, including several books, and has filed 30+ patents internationally.
Associate Professor Wang Yang is driving a team on advanced analytics for smart infrastructure at Data Science Institute, University of Technology Sydney. His research interests include machine learning and data analytics techniques, and their applications to asset management, intelligent infrastructure, cognitive and emotive computing, and computer vision. Yang has more than 100 publications and has won five awards from academy and industry.
Research outputs
B. Zhang, T. Guo, L. Zhang, P. Lin, Y. Wang, J. Zhou, and F. Chen, “Water Pipe Failure Prediction: A Machine Learning Approach Enhanced By Domain Knowledge”, In J. Zhou and F. Chen eds. Human and Machine Learning: Visible, Explainable, Trustworthy and Transparent, Chapter 18, pages 363-383, Springer, 2018. https://www.springer.com/gp/book/9783319904023
Liang, B., Weeraddana, D., Li, Z., Lu, S., Fan, X., Wang Y., Chen F., … & Hayward M. (2018). Pipeline Failure Data Analytics and Prediction. Ozwater 2018.
Lin, P., Zhang, B., Wang, Y., Li, Z., Li, B., Wang, Y., & Chen, F. (2015, October). Data driven water pipe failure prediction: A bayesian nonparametric approach. In Proceedings of the 24th ACM International on Conference on Information and Knowledge Management (pp. 193-202).
Li, Z., Zhang, B., Wang, Y., Chen, F., Taib, R., Whiffin, V., & Wang, Y. (2014). Water pipe condition assessment: a hierarchical beta process approach for sparse incident data. Machine learning, 95(1), 11-26.