Neuro-Fuzzy Approaches for Sanitary Sewer Pipeline Condition Assessment

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 paper describes the development of an automated data interpretation system for sanitary sewer pipelines. The interpretation system obtains optical data from the Sewer Scanner and Evaluation Technology (SSET), which is known to be the current leading-edge technology in inspecting sanitary sewer pipelines. The proposed system utilizes artificial neural networks to recognize various types of defects in sanitary sewer pipelines. The framework of this system includes modification of digital images for preprocessing, image feature segmentation, utilization of multiple neural networks for feature pattern recognition, and the fusion of multiple neural networks via the use of fuzzy logic systems.