Optimise and Automate Pre-production for Wire Based Directed Energy Deposition (w-DEDAM) Production PhD

Funding for: UK Students

Funding amount: A bursary will be provided of up to £22,500, tax-free plus fees for four years

Supervisors: Dr Jian Qin   

This 4-year, fully funded PhD project centres on the automation and optimisation of the pre-production process for wire-based Directed Energy Deposition Additive Manufacturing (w-DEDAM). It is supported by EPSRC Industrial Cooperative Awards in Science & Technology (CASE) training grants and WAAM3D Ltd, our industry partner. Additionally, the industrial partner offers a 3-month placement annually during the project. The project aims to explore cutting-edge digital technologies for w-DEDAM pre-production, including machine learning, deep learning, Design for Additive Manufacturing (DfAM), and advanced optimisation algorithms.

Wire-based directed energy deposition additive manufacturing (w-DEDAM) systems have effectively constructed qualified parts, now extensively employed in many industrial applications. To ensure a stable, reliable, high-quality and environmentally sustainable deposition process, the pre-production process is crucial which includes multiple activities, in terms of pre-forming original Computer Aided Design (CAD) models, recognising and segmenting design features, simulating geometry and mechanical properties, defining build sequences, and planning paths with appropriate process parameters.

Currently, the entire pre-production process is heavily reliant on the expertise and experience of additive manufacturing (AM) engineers. The decisions have also been decided based on prior experience, which may result in various part quality, lead time, and the use of material. This current artificial process is also time-consuming and fraught with uncertainties, often prone to human errors during decision-making. Therefore, there is an urgent need to fully optimise and automate this pre-production process with the combination of expert knowledge and artificial intelligence (AI) driven digital tools.

This project aims to explore and discover a non-expert pre-production process for w-DEDAM which can be implemented automatically based on expert knowledge and AI-driven digital tools combined with multi-objective optimisation. It will routinely provide an optimal production solution in terms of productivity, minimal or no distortion and high quality.

The student will be based at the Welding and Additive Manufacturing Centre, known for its impactful research into advanced fusion-based processing/manufacturing methods and other relevant technologies. This project is closely linked to many ongoing academic and industry projects, ensuring the student will be part of a diverse and vibrant research community. Additionally, there will be opportunities to work with the Centre’s industrial partners, such as WAAM3D and WAAMMat.

Entry Requirements

Applicants should have an equivalent of first or second class UK honours degree in a related discipline or subject area (e.g., electrics, mechanical, mechatronics, and manufacturing,). This project would suit a candidate with a genuine interest in design for additive manufacturing and additive manufacturing automation. Previous experience with CAD model segmentation and analysis, simulation for metal additive manufacturing and/or multiple objective optimisations is also desirable. The candidate should be self-motivated, proactive, and good at communication and teamwork.

About the sponsor

Sponsored by EPSRC, Cranfield University and WAAM3D, this DTP studentship will provide a bursary of up to £22,500 (tax free) plus fees* for four years.

Closes: 28/08/2024

Advert information