We work in dynamic process modelling, model-based control, and machine learning, developing methods that link data and physics to improve real-world systems. Our research spans mineral processing and emerging decarbonisation technologies, focusing on how hybrid models and digital twins can enable real-time prediction, optimisation, and control. These tools are key to advancing the efficiency and sustainability of industrial processes that drive the global energy transition.

New PhD studentship (Stipend + UK Fees) — apply by December 31, 2025: View details on FindAPhD →

Research Themes

Predictive Control & Optimisation with Machine Learning

Predictive Control & Optimisation with Machine Learning

Nonlinear/economic MPC with state and parameter estimation, Gaussian-process surrogates and reinforcement learning for safe, sample-efficient, performance-driven operation under uncertainty.

Hybrid Models & Digital Twins

Hybrid Models & Digital Twins

Physics-informed and machine-learning models combined into reliable virtual replicas for real-time monitoring, anomaly detection, and control of complex processes.

Sustainable Industrial Systems: Minerals & Clean Energy

Sustainable Industrial Systems: Minerals & Clean Energy

Digita tools application across froth flotation, heap leaching, and SAG mills, and in clean-energy systems including blue hydrogen, battery control (RL-MPC), and AI-assisted lifecycle analysis.

Our Team

Principal Investigator

Current

Past

Publications

Artificial intelligence and robotics in the hydrogen lifecycle: A systematic review Permalink

Published in International Journal of Hydrogen Energy, 2025

Recommended citation: Quintanilla, P., Elhalwagy, A., Duan, L., Masoudi Soltani, S., Lai, C. S., Foroudi, P., Huda, M. N., & Nandy, M. (2025). Artificial intelligence and robotics in the hydrogen lifecycle: A systematic review. International Journal of Hydrogen Energy, 113, 801-817. https://doi.org/10.1016/j.ijhydene.2025.03.016

Modelling for froth flotation control: A review Permalink

Published in Minerals Engineering, 2021

Recommended citation: Quintanilla, P., Neethling, S. J., & Brito-Parada, P. R. (2021). Modelling for froth flotation control: A review. Minerals Engineering, 162, 106718. https://doi.org/10.1016/j.mineng.2020.106718

A Proposal to Include the Information of Disturbances in Modifier Adaptation Methodology for Real Time Optimization Permalink

Published in Computer Aided Chemical Engineering, 2018

Recommended citation: Navia, D., Puen, A., Quintanilla, P., Bergh, L., Briceño, L., & de Prada, C. (2018). A Proposal to Include the Information of Disturbances in Modifier Adaptation Methodology for Real Time Optimization. Computer Aided Chemical Engineering, 43, 1081-1086. https://doi.org/10.1016/B978-0-444-64235-6.50189-3

Awards

Software

Bubble Analyser interface

Bubble Analyser is a comprehensive open-source app that processes images of bubbles, enabling users to quantify bubble size distribution. The tool is free to use and modify under the GNU General Public License, making it accessible to everyone.

Developed in collaboration with Imperial College London and IntelliSense.io, Bubble Analyser was designed with expandability and an easy-to-use interface in mind. It is also available as an executable version for easy deployment.

With Bubble Analyser, you can efficiently analyse bubble images and extract quantitative insights into complex processes. Visit BubbleAnalyser.com →