AI-Driven Process Modelling and Control for Manufacturing

I develop Machine Learning and hybrid physics–data models that make manufacturing processes more predictable, stable and efficient, from process understanding through to real-time control.

What I can offer to a Doctoral Network:

• Data-driven and physics-informed models of manufacturing processes, built from process, sensor and simulation data

• Soft sensors, predictive quality and anomaly detection for monitoring and control

• Model-based and learning-based control strategies for closed-loop process adjustment

• A supervision and training environment for one or more doctoral candidates, with strong industry links

Ideal partners: academic groups and companies in process and product engineering, control and automation, and industrial data platforms who want to embed AI in their production processes.