º£½ÇÂÛ̳

Publications

, , Walker Charlie, , , Torres Ophelie

Next Research (2026)

Szczepański Rafał,

Sensors Vol 26 (2026)

, Le Quang Dan, , Morsi Nour, , Luo Chaomin

Complex Engineering Systems Vol 6 (2026)

Jiang Fengling, Cao Yujin, Zou Le, , Li Chenglong, Luo Chaomin

IEEE Transactions on Multimedia (2026)

, , Holliman Freddie, ,

Proceedings of the Design Society Vol 6, pp. 2313-2322 (2026)

Huang Congyue, Tan Wei, Ou Miaohua, , Li Yun

IEEE Internet of Things Journal Vol 13, pp. 16021-16034 (2026)

Professional Activities

Chair

29/8/2026

Examiner

16/6/2026

Organiser

5/6/2026

Examiner

5/6/2026

Guest editor

1/5/2026

Editor

29/4/2026

Projects

Huang, Jianglin (Principal Investigator) Yang, Erfu (Co-investigator) Irvine, Anthony (Research Co-investigator)

01-Jan-2026 - 01-Jan-2030

Yang, Erfu (Principal Investigator) Mehnen, Jorn (Co-investigator) Weston, Sam (Post Grad Student)

01-Jan-2026 - 30-Jan-2029

Huang, Jianglin (Principal Investigator) Yang, Erfu (Co-investigator) Rahimi, Salaheddin (Co-investigator)

The "AI Surrogate Modelling to Enhance the Digital Twin of Titanium Cogging" is a fully funded PhD project at the University of º£½ÇÂÛ̳, linked with the EPSRC Centre for Doctoral Training (CDT) in Materials 4.0 and the Henry Royce Institute.
The research unites physics-based modelling, machine learning, and experimental validation. It is designed to tackle the computationally intensive nature of physical simulations in heavy manufacturing.
Key aspects of this research include:
1) Digital Twin Advancement: The project develops rapid predictive models to simulate the hot forging and cogging of titanium.
2) The FutureForge Facility: The research applies these surrogate models directly to real-world data generated by the FutureForge platform, which is a pioneering hot forging research facility located at º£½ÇÂÛ̳'s Advanced Forming Research Centre (AFRC).
3) Optimization and Speed: Machine learning (surrogate) models act as fast, mathematical stand-ins for heavy Finite Element Analysis (FEA), enabling real-time decision support, microstructural prediction, and process optimization without standard computational delays.

01-Jan-2026 - 30-Jan-2030

Yang, Erfu (Principal Investigator) Mehnen, Jorn (Co-investigator) Xie, Wenkun (Co-investigator)

01-Jan-2026 - 31-Jan-2027

Yang, Erfu (Principal Investigator) McGeown, William (Co-investigator) Buchanan, Sarah (Fellow) Ait Ameur, Mohamed Adlan (Post Grad Student)

This project will build CONNECT-HRC-AI Healthcare as an inclusive, visible and sustainable RKEI culture network for human-robot-AI healthcare research and knowledge exchange at º£½ÇÂÛ̳. The purpose is to use conference engagement as an evidence-gathering and external-learning stage that informs a wider programme to connect existing expertise, make contributions visible, and create practical collaboration pathways. The project responds directly to the RKEI culture challenge identified at º£½ÇÂÛ̳: relevant activity already exists, but people, capabilities, opportunities and everyday contributions are often fragmented, unevenly visible and difficult to connect.
The network will build on initial collaborative work between DMEM and the Department of Psychology, using existing MICA/social robotics and AI-in-the-loop healthcare research as a concrete anchor (Ait Ameur et al., 2025). However, the purpose of the network is to broaden this collaboration beyond a single doctoral project, laboratory, or discipline. Human-robot-AI healthcare brings together engineering and robotics, computer science and AI, psychology and cognitive science, health and wellbeing research, ethics, design, data governance, technical support, professional services and knowledge exchange, clinicians, formal care partners, and lived-experience or community voices. It therefore provides a strong test case for the kind of inclusive, visible, and sustainable collaborative research culture that the RKEI Network aims to enable.
The project will build on existing º£½ÇÂÛ̳ activity rather than create a disconnected new group. It will follow a structured mapping approach inspired by existing institutional network analysis: identify relevant people, themes, projects, facilities, datasets, methods and gaps; validate this map through expert-led workshops; and convert it into collaboration pathways, pitch ideas and future grant routes. Participants will be selected through a combination of targeted invitations across faculties and roles, open expressions of interest, doctoral/researcher networks, KE contacts and existing health, cognitive science, digital, design and robotics links.

01-Jan-2026 - 14-Jan-2026

Yang, Erfu (Principal Investigator) Millar, Richard (Co-investigator)

Student: Tye Cameron-Robson

01-Jan-2025 - 30-Jan-2028