We research adoption of digital technologies that transform processes for improved product quality, greater production efficiency, lower energy usage, lower emissions, and lower carbon footprint. Process automation involves less human intervention, which elevates process operation jobs to focus on operating systems, making them more rewarding.
Core research
Research under this theme ranges from establishing control systems in sugar factories to development of machine learning algorithms to automate the measurement of physical properties of input streams.
- Development of smart supervisory control systems
- Deep machine-learning of computer-vision data
- Process modelling and simulation using machine learning methods
- Sensor development, testing and calibration
Commercial research
- Implementation of supervisory/advisory control of pan and fugal stations
- Use of a purge sensor to improve the efficiency of batch centrifugal operation
- Evaluation of a colourimeter for measuring the purity of magma from C centrifugals
- Determining extraneous matter and billet length in sugarcane supplies using machine learning
- Online monitoring of C seed grainings using a microscope to improve pan stage performance
- Evaluating the suitability of two mud level sensing technologies for juice clarifiers
- Demonstrate the use of a microwave dry substance transducer for controlling high grade boilings
- At-line purity sensor to enhance the monitoring, control, and performance of pan stage
