Rhodri Williams
School of Mechanical, Aerospace and Civil Engineering
EngD Researcher
rwilliams15@sheffield.ac.uk
+44 114 2XX XXXX
+44 114 2XX XXXX
Sir Frederick Mappin Building
Full contact details
Rhodri Williams
School of Mechanical, Aerospace and Civil Engineering
Sir Frederick Mappin Building
Mappin Street
Sheffield
S1 3JD
School of Mechanical, Aerospace and Civil Engineering
Sir Frederick Mappin Building
Mappin Street
Sheffield
S1 3JD
- Profile
-
Advances in machine learning for informed operations of manufacturing ecosystems
Supervised by: Dr George Tsialiamanis, , Prof. Lizzy Cross, Dr Lindsay Lee,
Sponsored by:
Having spent time working in industry, I was particularly drawn to the EngD because it offers a unique blend of opportunities to engage directly with industry-led research and development projects while remaining closely connected to academic research. I’ve always had a strong love of learning, and the EngD provides an ideal environment to continue developing my knowledge through both independent and collaborative research. The substantial taught component also appealed to me, offering continued opportunities for both professional and academic growth. This combination presents a rare opportunity to deepen industry-specific expertise, expand a broad range of technical skills, and contribute to solving real-world industrial and academic challenges through applied research.Practitioners in the manufacturing sector currently rely heavily on conservative, heuristic-based decision-making. The aim of this research is to support a transition toward more informed, condition- or risk-based decision-making through the adoption of digital technologies. To achieve this, the project focuses on the selection and integration of data collected before, during, and after the manufacturing process, using data-driven modelling approaches such as machine learning.The research will develop predictive models that combine multiple data modalities to enhance reliability and trustworthiness. It will also explore the creation of population-level models capable of making efficient predictions across related systems, and investigate methods for integrating these model outputs into real manufacturing processes. The specific context of this work focuses on tool wear prediction, identifying when tools are no longer fit for purpose to enable more sustainable and cost-effective manufacturing operations.This research is particularly exciting because it sits at the intersection of digital transformation, artificial intelligence, and sustainable manufacturing. It explores how data can be applied not only to optimise existing processes but also to improve the way decisions are made across engineering systems. In doing so, it aims to support the development of more efficient, resilient, and environmentally responsible manufacturing practices.My research aims to make a tangible difference to engineering and manufacturing by improving production quality while reducing wasted resources, downtime, and costs. Through the development of advanced prognostic models, it enables smarter, data-driven decision-making within machining and tool wear processes. The work also contributes to the broader advancement of sustainable technologies, applying responsible approaches to machine learning and artificial intelligence. Ultimately, this research supports the transition toward more efficient, sustainable, and environmentally responsible manufacturing practices that benefit both industry and society.
- Qualifications
-
MEng General Engineering
- Research interests