fairfolio
Saved Projects

Evaluating Sewer Pipe Longevity Through Deep-Learning Methods and Physical Stressor Simulations: A Novel Way To Prevent Sanitary Sewer Overflow

CSEF · 2023 Earth & Environmental Sciences Second Award

Roy Debayon · 11

Overview

The objective of this study is to predict the longevity of the sewer pipes and determine the optimal type of pipe in the case of replacement. The scope of the conditions was within the LA region, which contains the largest sewer pipe network in the nation. The most prevalent internal pipe defects were tested experimentally to determine their effects on different pipe material. The defects tested experimentally were: Grease collection, root intrusion, and corrosion caused by acidic conditions. Conditions were measured in 4 different types of pipes: high density polyethylene (HDPE), polyvinyl chloride (PVC), Vitrified Clay Pipe (VCP), and Concrete. After running experiments to test grease deposition, root intrusion, and resistance to corrosion, it was determined that the plastic based pipes (HDPE & PVC) performed the best in all 3 scenarios. NavigateLA, a data source containing information on existing LA sewer systems, was used to collect the information necessary to determine pipe longevity. Literature analysis of the NASSCO pipe guidelines reveal that the conditions that affect the longevity and health of the pipe are: pipe material, surface topography, internal pipe structural defects, adjacent soil conditions, and installation length, available on Navigate-LA. Next, features determined from the NASSCO guidelines were implemented as independent variables to create a deep-learning program to predict the lifespan of the pipes. This was created through Google Collab and PyTorch. Through neural network programming, machine learning programs were able to accurately predict the useful life of sewer pipes in Los Angeles County, within the optimum 5-10 year range.

Source coverage

This record comes from a published award list, not a complete project archive. Its abstract comes from CSEF's public project showcase as archived by the Internet Archive before judging (https://web.archive.org/web/20230401224130/https://ca-csef.zfairs.com/showcase/ShowcaseInfo?f=838e60b7-ea75-46e8-865c-fde4864244b3); the version presented may differ.

Awards (1)

Competition history

  • CSEF 2023 Earth & Environmental Sciences · Entry S0917

Resources

Related projects

Closest projects by meaning, across every fair and year in the corpus.

Browse more like this

Source: California Science & Engineering Fair public projects

Save projects to your library

Sign in with Google to keep track of projects you find interesting, organized into folders. An account also raises your daily allowance for “Has this been done?”, and lets you create a key for the MCP server with a much higher limit than anonymous use. Browsing stays public.

Continue with Google