Ai-enabled control framework for membrane filtration in sweetener refining
An AI-driven monitoring and control solution for membrane-based filtration in starch-based sweetener refining, integrating machine learning and Model Predictive Control to optimize filtration efficiency, reduce resource consumption, and enhance impurity removal.
Overview
The AI-enabled control framework is designed to enhance membrane-based filtration in starch-based sweetener refining. This innovative solution employs an AI-driven monitoring and control system that integrates seamlessly with existing infrastructure. By utilizing plant and experimental data, it builds a dynamic digital twin of the filtration unit. This model captures the evolution of process measurements, filtration performance, and impurity removal. The Model Predictive Control (MPC) system then optimizes operating actions in real-time, aligning with plant-specific priorities to improve clarification efficiency, reduce water and energy usage, and minimize consumables and product loss.
Technical specifications
- Dynamic digital twin: Utilizes machine-learning-based system identification to replicate filtration dynamics.
- Model Predictive Control: Real-time optimization of filtration operations based on configurable objectives.
- Integration capabilities: Compatible with existing membrane filtration systems and control infrastructure.
- Enhanced efficiency: Focuses on reducing fouling, water, and energy consumption while maintaining high impurity removal.
- Sensor integration: Allows for the addition of inline sensors as required for enhanced data collection.
Technology readiness level
This technology is currently at Technology Readiness Level 5. It has been validated in a laboratory environment and is undergoing pilot deployment to further test its capabilities in a real-world setting. Future plans include a phased validation process, culminating in a comprehensive scale-up and extension.
About The University of Melbourne
The University of Melbourne is a comprehensive institution spanning STEM, health and clinical practice, business and law, and the creative and social disciplines. Co‑located hospital and research precincts, together with an inner‑city innovation ecosystem, place companies, startups, and researchers in shared labs, prototyping spaces, and studios. Engineering and technology programs connect with advanced manufacturing facilities, while structured industry projects and placements link partners with talent and translational problem‑solving. Work is supported by competitive funding from the Australian Research Council and the National Health and Medical Research Council, with additional backing from state programs and industry partners; a dedicated technology transfer office manages IP, licensing, and startup formation.
delivered to your inbox.