Project dates: 01/04/2021 - 01/07/2022
The cane supply to sugar mills comprises billets of the cane stalk, leaves, tops and roots. All components other than the billets are classified as extraneous matter (EM) and contribute little to the quantity of sugar that can be produced. In fact EM reduces the sugar yield from the supplied cane.
The physical properties of the cane supply are currently not measured (except on an intermittent basis at Tully Mill) and thus parameters such as EM content and billet dimensions are not routinely monitored. Thus, the industry is not in a position to manage these parameters, and to determine the true impacts on costs such as low bin weights, deterioration due to short billets, and milling costs associated with high EM (increased sucrose losses in bagasse, mud and molasses, chokes in milling, reduced liquor purity, reduced factory throughput, extended season lengths).
By having an on-line measurement of the physical properties of the cane supply the data can be used with harvesting information (field loss estimates, etc.) and transport information (bin weights, etc.) to determine optimum harvesting conditions and maximise cane value in each district. Differences in cane varieties, crop intensity, green or burnt cane, value of fibre (cogeneration and other uses), and haulage distances are just some of the factors to be considered to determine the preferred physical attributes of the cane supply to maximise value.
This project uses computer vision and machine learning methodologies to provide algorithms to measure EM mass% and billet dimensions for each cane consignment.
Other Team Members
IT, mechanical and electrical engineering staff, and EM laboratory staff at Tully Mill