Methodology for the detection and characterization of corrosion under insulation for pipe using digital radiography and computer vision techniques

Radiographic Testing is a versatile non-destructive testing method that uses either x-rays or gamma rays to examine the internal structure of components identifying any defects in various industries. Digital radiography has replaced screen-film radiography and is used extensively in inspections of insulated pipes in petrochemical industries. The principal task of this project is to assess the corrosion under insulation. Radiography data is frequently examined by qualified human inspectors. This manual method is time-consuming, costly, and operator-dependent. Furthermore, manual analysis effort in inspections is a limiting issue in terms of robustness and capacity. Computer vision aims to carry out and automate tasks that replicate human capabilities. Therefore, this study, in collaboration with TORNGATS Services Techniques, intends to integrate the cutting-edge method using computer vision, with the digital radiographic technique to develop a digital information model for processing, analyzing, and communicating inspection data. The proposed approach will be used by the industrial partner (TORNGATS Services Techniques) to provide cost-effective automated digital radiography inspection services for clients, thus satisfying the significant industrial demand in the Canadian petrochemical industry.

Faculty Supervisor:

Xavier Maldague

Student:

Partner:

TORNGATS Technical Services Inc

Discipline:

Engineering

Sector:

Professional, scientific and technical services

University:

Université Laval

Program: