Automated interpretation and assessment of sewer pipeline infrastructure

Myung Jin Chae, Purdue University

Abstract

Sewer systems form one of the most capital-intensive infrastructure systems in the U.S. Traditionally, methods used to assess the status and inventory conditions of underground infrastructures have been based on after-the-fact information. Often, these infrastructure assets get neglected until they suffer catastrophic failures, which are inconvenient and costly to repair. To determine the health of infrastructure systems, regular and accurate assessment is essential. Recent advances in optical sensors and computing technologies have led to the development of inspection systems for underground facilities such as water lines, sewer pipes, and telecommunication conduits. It is now possible for inspection technologies that require no human entry into underground structures to be fully automated from data acquisition to data analysis and eventually to condition assessment. This research describes the development of an automated data interpretation system for sanitary sewer pipelines. The proposed system utilizes neural networks and fuzzy logic systems to detect various types of defects in sanitary sewer pipelines. The framework of this system includes digital image preprocessing, image feature segmentation, utilization of multi-neural networks, and fuzzy logic systems for image feature pattern recognition. In this study, an attempt has also been made to link automated assessment to other aspects of wastewater infrastructure management. The proposed integrated infrastructure management is necessary to help asset managers to understand and monitor the condition of infrastructure assets and to make consistent and cost-effective decisions. Two approaches of the intelligent renewal, namely, integration with GIS (Geographical Information System) and integration with Markov chains deterioration model are discussed.

Degree

Ph.D.

Advisors

Abraham, Purdue University.

Subject Area

Civil engineering

Off-Campus Purdue Users:
To access this dissertation, please log in to our
proxy server
.

Share

COinS