The Emergence of Artificial Intelligence – Machine Learning in Buried Water Main Asset Management

Posted by Doug Hatler on Sep 19, 2018 9:55:57 AM

Every four years, the American Society of Civil Engineers’ Report Card for America’s Infrastructure depicts the condition and performance of American infrastructure in the familiar form of a school report card—assigning letter grades based on the physical condition and needed investments for improvement. In 2017, ASCE graded the United States’ infrastructure a D+. That’s a dismal grade.

In drinking water, US water utilities are experiencing 240,000 breaks each year. A recent study by Utah State University found that water main breaks in the US and Canada have increased 27% over the past six years. Service interruptions, soaring costs, pressure to raise water rates and the strain on available resources is unprecedented and is expected to worsen in the near future. 

The American Water Works Association (AWWA) in its momentous publication, “Buried No Longer,” states that “…restoring existing water systems as they reach the end of their useful lives and expanding them to serve a growing population will cost at least $1 trillion over the next 25 years, if we are to maintain current levels of water service.”

So, if you are running a water utility in the United States, how do you address this impending “Pipeageddon?”  It starts with an inventory of your buried water main assets and assessment of their condition. Many utilities have inventoried and digitized their assets through the implementation of Geographic Information Systems (GIS) and Computerized Maintenance Management Systems (CMMS) or Enterprise Asset Management (EAM) systems. These deployed solutions help utilities more productively capture, store, retrieve, manage, analyze and visualize asset data spatially. They also help track the maintenance of all assets, schedule and track maintenance tasks and keep a historical record of work performed throughout the lifecycle of an asset. One significant gap in GIS, CMMS, and EAM systems is that they cannot directly assess the condition of an asset. This is usually left to engineers and third-party contractors to perform condition assessments.

Condition assessments of buried water mains typically fall into two categories: physical and desktop. Physical condition assessments are accurate for the pipe tested but tend to be slow, expensive and labor intensive. Multiple physical measurements are required for correlation and confirmation. The results are difficult to extrapolate to system wide recommendations. Desktop methods are more straightforward, but many of these methods are based on arbitrary assumptions and weights (i.e., older pipes are more in need of replacement than newer pipes).

A more robust approach would be a large-scale comparison of myriad factors to generate a more refined and accurate prediction based on the disparate interactions between component variables. Artificial Intelligence (AI), specifically, Machine Learning, has emerged as a technology to make a significant impact in buried water infrastructure asset management.  AI – Machine Learning consumes large, complex data sets containing more variables humans can process with current tools. This objective, data-driven method overcomes inherent subjectivity and biases and provides results that help utilities make better replacement decisions.   Moreover, the availability of digital asset data from GIS, CMMS, and EAM systems enables a machine learning solution for pipe condition assessment to be fast, accurate and affordable.

Fracta Process

At Fracta, we are working with utilities and engineering firms around the United States to incorporate AI - Machine Learning condition assessments into proper infrastructure and asset management programs. This new technology and methodology will undoubtedly contribute to the reduction of the economic impacts incurred from water main breaks, and drive more efficient allocation of capital by water utilities. Use of best practices and a more accurate, objective tool will align maintenance and capital repair and replacement strategies to more efficiently leverage scarce financial and human resources. They also inject financial integrity to the planning process and refine the investment strategy so a utility will be in a better position to defend planning efforts and fund needed capital pipe replacement projects.

Fracta…Bringing Artificial Intelligence to Infrastructure.  Fast, Accurate and Affordable.

Topics: Condition Assessment

Subscribe for more news & updates from Fracta