This research group focuses on the integration of artificial intelligence, process simulation, and systems engineering to advance sustainable, efficient, and intelligent chemical engineering across molecular, process, and industrial scales.
The group develops hybrid modelling frameworks that combine first-principles engineering, process simulation, and data-driven methods to enable AI-assisted process design, digital twins, real-time monitoring and control, fault detection, and multi-objective optimization. Application areas include low-carbon fuels, sustainable chemicals, biomass conversion, carbon utilization, and energy-efficient manufacturing. Techno-economic and environmental assessment (TEA–LCA), multi-criteria decision-making, and data envelopment analysis are applied to rigorously evaluate technology performance and quantify trade-offs among cost, efficiency, safety, and environmental impact supporting robust decision-making from laboratory development through to industrial scale-up.
At the molecular level, biomolecular simulations — including molecular docking and molecular dynamics — are applied to drug discovery from traditional herbal extracts, while density functional theory and machine learning–based approaches are used for advanced material and catalytic system design.
ENARIA LabThe Energy-Efficient Automation and Research in Artificial Intelligence Laboratory (ENARIA Lab) is a dedicated platform for industrial digital transformation within this group. It integrates deep learning architectures with physics-based process models to deliver scalable, interpretable, and industry-ready solutions. Research priorities include predictive maintenance and remaining useful life estimation, real-time energy efficiency optimization, process automation and safety enhancement, and intelligent decision support for sustainable and resilient chemical process operations.
