AI-Enabled Process Engineering

Artificial intelligence (AI) is revolutionizing process engineering by improving efficiency, optimization and sustainability in various industries. Advanced AI techniques, including machine learning, deep learning and neural networks, enable real-time data analysis, predictive modelling and automated decision-making, reducing human intervention and improving process control. AI-driven approaches optimize reaction conditions, resource utilization and energy efficiency, minimizing waste and environmental impact. In addition, AI improves fault detection and predictive maintenance, which significantly increases operational reliability and safety. The integration of AI with digital twins and cyber–physical systems further accelerates innovation in process design, scale-up and automation. Despite the transformative potential, challenges remain, particularly in terms of data availability, the interpretability of models and integration into existing infrastructures. For all these reasons and for the impact on sustainable solutions for industrial applications, we are presenting this new section of Processes. Download Section Flyer

Topics include, but are not limited to, the following: 

Advanced Process Optimization and Control

• Multi-agent reinforcement learning for plant-wide control;
• Swarm intelligence for heat exchanger network synthesis;
• Explainable AI (XAI) in complex control decision support;
• Adversarial robustness testing of ML-based controllers. 

AI/ML-Driven Process Modeling and Simulation

• Reinforcement learning-guided catalyst discovery pipelines;
• Graph neural networks (GNNs) for chemical reaction pathway prediction;
• Surrogate modeling of computational fluid dynamics (CFD) using deep operators;
• ML-enabled soft sensors for real-time bioprocess monitoring. 

Computer-Aided Process Intensification

• Automated microreactor configuration screening via genetic algorithms;
• ML-guided discovery of novel process intensification pathways;
• AI-powered exergy analysis for energy-efficient retrofits;
• Digital prototype testing of modular chemical plants. 

Cross-Domain Applications

• Energy and sustainability;
• ML-accelerated discovery of CO₂ capture solvents;
• Digital twin-enabled smart grid integration of electrolyzers;
• AI-powered life cycle assessment (LCA) automation tools. 

Materials and Manufacturing

• Generative AI for metal–organic framework (MOF) discovery;
• Digital thread implementation in additive manufacturing;
• ML-driven inverse design of polymer membranes;
• Quantum computing for battery material screening;
• AR-assisted maintenance of catalytic cracking units. 

Food and Agriculture

• Computer vision systems for automated food safety inspection;
• Digital twin optimization of vertical farming LED spectra;
• ML-enabled precision fermentation monitoring;
• AI-driven formulation of plant-based meat analogs.