1. Syscad Neural Network Models for LSR Dynamic Sugar Crystal Growth Prediction.
- Author
-
Marin, Tanai, Smyth, Emily, McFeaters, John, and McFeaters, Eleanor
- Subjects
- *
ARTIFICIAL neural networks , *MACHINE learning , *CRYSTAL growth , *CONVOLUTIONAL neural networks , *SUPERVISED learning - Abstract
Sugar crystal growth is a non-linear process dependent on the complex interaction of several variables. This causes the development of first-principal models of the process to be exceedingly difficult and often inaccurate. Louisiana Sugar Refining has partnered with SysCAD to develop a machine learning model of crystal growth to incorporate into the digital twin infrastructure being developed at LSR. The collaboration has successfully developed a supervised training machine learning model based on Deep Feed Forward (DFF) and Convolutional Neural Network (ConvNet) models to simulate the crystal growth in vacuum pans. Initially, a proof-of-concept model showed promising results using both DFF and ConvNet architectures, which lead to the expansion of these models to include the entire white and recovery boiling schemes. In this paper we present the concept of using neural network dynamic models, their analysis, and results of predicted particle size distribution parameters compared to real field observations. These fully optimized models will be implemented as standard unit operation models in SysCAD to enhance the larger process simulation model used by LSR to monitor and predict process conditions in real-time. This machine learning technique will also be expanded to develop a concept model for other non-linear phenomena in the sugar industry including colour. [ABSTRACT FROM AUTHOR]
- Published
- 2024