Improving Defect Detection Reliability in Ultrasonic Testing through Artificial Intelligence
This PhD project addresses the challenge of data interpretation in Phased Array Ultrasonic Testing (PAUT) by investigating how Artificial Intelligence (AI) and Machine Learning (ML) can improve the reliability and consistency of defect detection. The research will explore synthetic data generation, AI-driven defect detection, explainable AI for safety-critical NDE, and AI-assisted reporting. The student will have the opportunity to spend 3 months at IHI company facilities in Japan.
Project Description
About the Project
Phased Array Ultrasonic Testing (PAUT) is a cornerstone of modern Non-Destructive Evaluation (NDE) across industries such as aerospace, energy, and automotive. By enabling electronic beam steering and focusing, PAUT brought improved inspection capability for complex geometries and is widely used for safety-critical components due to its flexibility, safety, and compatibility with automation. Recent advances in robotic automation have largely addressed the data acquisition challenge in UT and PAUT. Robotic inspection systems now enable high-speed, repeatable scanning while generating large, spatially encoded datasets (A-scans, B-scans, and C-scans). As a result, the primary bottleneck has shifted from data acquisition to data interpretation.
Manual analysis of large PAUT datasets remains time-consuming, subjective, and dependent on operator expertise, particularly when detecting subtle defects in anisotropic materials such as composites. This PhD project addresses this challenge by investigating how Artificial Intelligence (AI) and Machine Learning (ML) can improve the reliability and consistency of defect detection in NDE data.
Research Environment and Collaboration
The project will be undertaken at the University of Strathclyde, within the Department of Electronic and Electrical Engineering and the Centre for Ultrasonic Engineering (CUE).
The student will have funding and the opportunity to spend 3 months at IHI company facilities in Japan to closely interact with their industrial sponsor and to also facilitate the knowledge exchange.
The PhD candidate will work in a strong interdisciplinary research environment spanning NDE, ultrasonics, robotics, and AI, and will engage with academic experts and industrial stakeholders involved in automated inspection of safety-critical structures. The research will have access to state-of-the-art facilities, including the Sensor Enabled Automation, Robotics & Control Hub (SEARCH- https://search.eee.strath.ac.uk/index.html#features4-a ), which provides advanced robotic platforms, ultrasonic inspection systems, and integrated sensing and automation infrastructure.
Research Ambition and Scope
The overarching ambition of this PhD is to shift UT and PAUT inspection from expert-dependent manual interpretation toward intelligent, reliable, and trustworthy AI-assisted analysis. The work will explore how modern AI techniques can enhance defect detectability, reduce false calls, and support operator decision-making while maintaining transparency and confidence in the results. The research will focus on the following interconnected themes:
• Advanced synthetic data generation for UT/PAUT
• AI-driven defect detection and characterization
• Explainable and trustworthy AI for safety-critical NDE
• AI-assisted reporting and knowledge integration
Essential criteria
• A first or upper-second class degree (or equivalent) in Electrical Engineering, Mechanical Engineering, Mathematics, Physics, Computer Science, Data Science, Mechatronics, or a related discipline
• Strong interest in data analysis, machine learning, or signal processing
• Motivation to work on applied research with real industrial impact
Desirable skills
• Familiarity with Ultrasonic Testing, PAUT, or NDE techniques
• Experience with machine learning, deep learning, or computer vision
• Experience with Python and common ML frameworks (e.g. PyTorch)