An In-Pipe Leak Detection Robot With a Neural-Network-Based Leak Verification System

Abstract

This paper presents a custom designed in-pipe inspection robot that is developed for a pipe of diameter 0.203 m, commonly found in the oil and gas industry. Several pressure sensors are incorporated on board the robot that are used for detecting leaks. The robot has a propeller arrangement that not only drives the robot forward but also helps simulate a flow in an empty pipe, and thus aids the detection of leaks. Furthermore, the leak detection system is augmented by a neural network-based verification framework that improves the robustness of leak detection by allowing the operator to check their identification of a leak by passing it through a neural network-based system. This paper presents the details of the construction of the actual robot and presents experimental data, which show successful neural-networks-based detection of leaks in various scenarios.