Speaking

The City of Huber Heights, Ohio, operates a water distribution system of 205 miles of predominantly cast iron and ductile iron pipe. While their system was already experiencing a relatively high break rate before 2019, the break rate from 2019 through 2021 unexpectedly doubled.

Several possible causes of the spike in breaks were evaluated. The City had commissioned three new booster stations, decommissioned one of its two water treatment plants, and commissioned a new softening process at its primary plant, all of which impacted flows, pressures, and water quality over the last five years. Determining the extent to which breaks were impacted by these changes and understanding if those impacts were temporary or permanent was critical to determine the appropriate investment levels in future watermain replacements designed to control the break rate.

B&N leveraged the City’s comprehensive GIS pipe attribute data set and empirical break database dating back to 2010 to identify its riskiest pipes. The 12 years of break in the database were all associated with a corresponding pipe, including reviews for watermain break work orders for a decade.

Leveraging machine learning algorithms, asset and break data were imported into a state-of-the-art break-prediction online platform to make pipe-by-pipe failure predictions. Before performing the analyses, multiple software-guided quality control steps were taken to verify and improve data quality and ensure the most accurate predictions.

Break predictions were coupled with each pipe’s consequence of failure data to generate a risk profile. With a list of pipes prioritized by risk, B&N modeled the break rate and risk resulting from alternative replacement investment levels and identified an affordable annual budget to stabilize the break rate.

After this session, participants will better understand what factors influence watermain break rates, how advanced predictive methods address the inherent flaws of traditional 1- to 5- scoring systems to rate pipe risks leading to much more accurate results, and how to determine the appropriate investment level to control breaks and risks.