Experimental evaluation of intelligent fault detection system for inspection of sewer pipes

Abstract

Automation is an important issue in industry, particularly in inspection of underground facilities. This paper describes experimental evaluation of intelligent system for automatically detecting faulty areas in a real sewer pipe system. The proposed system can detect various types of faults and be implemented in a real time system. Its detection performance is 100%, when the false positive rate is 34%. This ratio is acceptable for sewer inspection, and the reduction of time and cost is also realized.