Optimise and automate pre-production for wire based Directed Energy Deposition (w-DEDAM) production PhD or MSc by Research

About the Project

This project offers an opportunity to develop a next-generation intelligent manufacturing framework for wire-based directed energy deposition additive manufacturing (w-DEDAM). You, as a PhD/MSc by Research student, will work at the intersection of artificial intelligence, digital manufacturing, and optimisation to automate the pre-production process, traditionally reliant on expert judgement. By integrating multi-modal data, simulation, and AI-driven decision-making, the research aims to deliver robust, high-quality, and efficient production solutions. This is ideal for candidates interested in advancing smart manufacturing and solving complex, real-world engineering challenges.

This project sits within digital manufacturing and additive manufacturing, with a particular focus on wire-based directed energy deposition (w-DEDAM). It integrates disciplines including artificial intelligence, computational modelling, and manufacturing systems engineering. The research addresses the transition from experience-driven to data-driven and automated production workflows, which is a central challenge in modern manufacturing. Its relevance today is significant, as industries are increasingly adopting additive manufacturing for high-value, complex components while demanding improved consistency, reduced lead times, and enhanced sustainability. Automating the pre-production stage through AI and optimisation directly supports the development of intelligent, scalable, and reliable manufacturing systems, aligning with the broader movement towards digital manufacturing.

The aim of this project is to develop an automated, non-expert pre-production framework for wire-based directed energy deposition additive manufacturing (w-DEDAM). The research focuses on integrating expert knowledge with artificial intelligence, multi-objective optimisation, and digital tools to systematically define build strategies, process parameters, and toolpaths. The project seeks to deliver a robust and scalable solution that consistently achieves high-quality parts, minimal distortion, and improved productivity, while reducing reliance on manual decision-making and enhancing overall efficiency in additive manufacturing workflows.

The student is expected to acquire the following (including but not limited to) knowledge and skills from the research in this project:

• Fundamental understanding of w-DEDAM processes
• Pre-production workflow design, covering CAD model handling, feature recognition, build strategy definition, and toolpath planning.
• Multi-objective optimisation techniques, including formulation of optimisation problems, trade-off analysis, and algorithm development for manufacturing applications.
• Artificial intelligence and machine learning methods, particularly for data-driven modelling.
• Multi-modal data integration and management, combining geometric data, simulation outputs, experimental data, and expert knowledge into a unified framework.
• Digital manufacturing systems and platforms, with experience in developing or implementing integrated, automated workflows.

Funding Notes

Self-funded. The cost for running experiments and accessing to research facilities will be supported by the Welding and Additive Manufacturing Centre.