Modern manufacturing industries face increasing pressure to reduce energy consumption and material waste while maintaining high efficiency and reliability. Advanced control strategies,such as Koopman-based Model Predictive Control (Koopman MPC), offer significant improvements in optimizing industrial processes. However, despite its strong theoretical foundation, no practical software tool enables engineers to implement Koopman MPC in real-world applications.

This research mobility aims to bridge this gap by developing a Koopman MPC-driven software toolbox that allows engineers to transition from raw process data to optimal control strategies seamlessly. The software will provide a user-friendly, AI-powered solution for improving efficiency in energy-intensive manufacturing plants.

The project will focus on:

1. Developing and testing a prototype software tool for industry applications.

2. Validating its effectiveness using an experimental industrial setup or a digital twin.

3. Quantifying its performance improvements in energy savings, material efficiency, and process reliability compared to current state-of-the-art control methods.

4. Publishing findings in a high-impact journal or presenting at a major conference, ensuring broad dissemination and industrial adoption.

This initiative directly supports EIT Manufacturing’s goal of promoting Low Environmental Footprint Systems & Circular Economy for Green Manufacturing by enabling industries to minimize waste and optimize resource usage. The outcome of this research will not only advance scientific understanding but also pave the way for real-world industrial adoption, contributing to a more sustainable, AI-driven future for manufacturing.