Page 45 - FCW, January/February 2020

color-coded based on defect type. The report also provides details on where the defect starts and ends on the pipe.
The benefits of automation
Human technicians review the vid- eos with the highest scores — mean- ing the pipes with the most problems — and the lowest scores to check for false positives and negatives. They feed any discrepancies into the neural net- work model to improve its detection capabilities.
“As it pulls frames from a new video, it applies them to the neural network to classify the defect,” Kuczynski said.
Currently, the algorithm can spot nearly 50 defects, main-
ly in vitrified clay and
concrete pipes, although
Kuczynski said the agen-
cy is testing the algorithm
to find problems in cured-
in-place pipes, in which
a liner is inserted into a
pipe and heated to stick
to the pipe’s sides as rein-
forcement. The detection
rate for vitrified clay is
92% to 95% accurate and
slightly lower for con-
crete, he added.
Traditionally, DC Water
has used CCTV cameras,
vehicles and operator stations to inspect sewer pipes. A technician feeds the cam- era into the sewer, and operators navi- gate it. They watch the video being trans- mitted back and manually tag defects. Afterward, a certified engineer reviews the video and confirms and scores the defects to produce a report.
That process could take an entire day, but Kuczynski said the automated approach can reduce an hour’s worth of manual work to 10 minutes.
DC Water spent 18 months building Pipe Sleuth with Wipro and has been using it for about a year. So far, the agency has run about 20 of its 1,900 miles of sewers — some of which are more than 80 years old — through the
software at a cost of about $3 to $4 per linear foot, he said. By comparison, using CCTV costs $7 per linear foot.
In the past, the agency inspected about 19 miles per year, or roughly 1% of its inventory, but the goal is to increase that to 4% or 5%. “Our hope is that over time, as we move more and more of our scanning to the automated process...then we’ll increase the num- ber of pipes we scan but at a much lower cost,” Kuczynski said.
Another benefit to Pipe Sleuth is consistency, he added. “All of the video goes through the same algorithm to do all of the detection, whereas when you’re using CCTV, you’re using a num-
A customizable tool for other jurisdictions
In August 2019, DC Water, through its nonprofit Blue Drop marketing arm, and Wipro began jointly mar- keting Pipe Sleuth for use by other jurisdictions. They have a trial agree- ment with Northumbrian Water in the United Kingdom, which has about 20,000 miles of pipe and has used Pipe Sleuth on about 30 miles so far.
The plan is for a portion of the rev- enue to be reinvested into the prod- uct, with the remainder being split between the two entities. Two licens- ing models are being considered: out- right and a cost per video scanned.
“It’s
basically facial recognition... for sewer pipes.”
Thomas Kuczynski, DC Water
The algorithm works with any scan- ning technology and any basic video for- mat, so it’s indifferent to the source of the video or what’s being recorded, making it easily customizable for uses beyond sewer pipes.
“It could theoreti- cally be applied to almost anything,” Kuczynski said. “We’ve talked about doing some inspections of
ber of different operators who have a personal bias to what they’re doing,” Kuczynski said. Additionally, “the soft- ware doesn’t get distracted or tired. It processes the video stream irrespec- tive of what’s going on around it, so we think we get a higher-quality result out of it.”
What’s more, officials can use the scoring to prioritize repairs. “As we increase the amount of pipe that we scan, we increase the number of our known defects, so...we can better target investments,” he said. “We get a better return on that investment because we’re fixing more of the really bad stuff versus fixing just what we know.”
various structures using a similar type of technology. I know some folks are using it for...identifying potholes.”
Washington, D.C., is not the only jurisdiction using robots to trek through sewers. Waxahachie, Texas, and the University of Texas at Arling- ton are working on a project to use robots to collect data on several miles of the city’s sewer pipelines.
In the U.K., Thames Water has tested autonomous robots outfitted with cameras to gather sewer pipe imagery, and in a European Union- funded initiative called SIAR, a robot was used in Barcelona to cre- ate a 3D scan that be analyzed auto- matically. n
January/February 2020 FCW.COM 45