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.

As one of the groups leading research in studying strategies for AI integration into the NDE automation workflow, SEARCH has developed a knowledge base for AI technologies best suited for ultrasonic data analysis, defect detection and characterization at different levels of data structures; time series, images, and volumetric. Among these are supervised object detection for ultrasonic amplitude C-scans, unsupervised anomaly detection on ultrasonic B-scans, and a self-supervised AI model for processing full volumetric ultrasonic data. Specifically, a Faster Region-based Convolutional Neural Network was used for object detection, trained exclusively on simulated data to mitigate data scarcity issues. Meanwhile, the anomaly detection model, implemented as a convolutional autoencoder, and the self-supervised AI model, designed as a forecasting model for time-series data, were both trained on pristine CFRP samples. These past successful developments have created the drive and ambition for the academic/industry team to extend this work into a new phase where AI models can excel at NDE data interpretation, and also provide domain-specific knowledge to guide NDE operators at stages of testing, data acquisition, interpretation, and reporting.

Research environment & collaboration

The project will be undertaken at the Sensor Enabled Automation, Robotics and Control Hub (SEARCH) at University of Strathclyde, within the Department of Electronic and Electrical Engineering and the Centre for Ultrasonic Engineering (CUE). 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 SEARCH, which provides advanced robotic platforms, ultrasonic inspection systems, and integrated sensing and automation infrastructure.
You 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.

 Research ambition & 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