As part of their Capacity Management Operation & Maintenance (CMOM) program, the Town of Newburgh, Indiana annually cleans and inspects 10% of their sanitary collection system. Much of the inspection video captured provided a good picture of the overall pipe condition but had not yet been coded per the National Association of Sewer Service Companies (NASSCO) Pipeline Assessment Certification Program (PACP) requirements. Reevaluating sewer pipeline inspections can be a costly and time-consuming undertaking, which is why Newburgh took an innovative approach to restructuring its pipeline inspection process with the help of artificial intelligence (AI).
Artificial Intelligence, Real Solutions
B&N’s AI tool, PipeAIdTM, was used to process inspection data for 40,000 linear feet of pipe for the town. PipeAId provides an objective look at a pipe’s condition by using machine learning algorithms paired with computer vision to detect and classify sewer defects. This provided Newburgh with a subjective and unbiased condition assessment of their buried assets enabling them to maximize a pipe’s useful life and either rehabilitate or replace it before a failure occurs.
PipeAId gave the Town of Newburgh both perpendicular and longitudinal views which provided a more detailed analysis while mitigating the chances that defects and other observations would be miscoded or missed altogether. Using historical CCTV data that Newburgh provided from five to 10 years ago, B&N also was able to compare it to data collected over the past year to determine the rate of deterioration. It was found that the level of deterioration was not enough to warrant rehabilitation or replacement and that Newburgh’s proactive point repair program has been effective at extending the sewer’s useful life.
In addition to the traditional reports generated as part of sewer inspection work, PipeAId has geographic information system (GIS) outputs that could be integrated with Newburgh’s GIS to show the size, material, date of inspection, condition of pipes and the location of each defect/observation. This provides a high level of transparency of a pipe’s condition and reliable information to support data-driven decisions to support Newburgh’s rehabilitation, replacement and maintenance strategies. The mapping also serves as an effective tool for the field staff to facilitate conversations with residents and better inform stakeholders and residents about the town’s proactive CMOM program.
Looking Ahead
The Town of Newburgh now has a higher degree of certainty that incident codes are identified correctly. As time goes on, PipeAId becomes smarter because it utilizes a robust dataset of each computer vision model that is continuously supplemented with inspection data. As the program gains a deeper understanding of each defect, the time required for reviewing sewer inspection data is greatly reduced. Sewer inspection officials have already noted a difference.
“This AI system is taking our sewer pipe assessment program to the next level, and we look forward to a far more efficient and cost-effective sewer inspection process. By using the CCTV data that we’re already gathering and translating it into a more useful format, it’s making the utility’s efforts more valuable, providing a high level of service to our customers.”
– Steve Shoemaker, Sewer Commissioner