Treffer: Visualization and machine learning analysis for daily raw sugar manufacturing data.

Raw sugar factories in Louisiana generate tremendous amounts of daily manufacturing data which are diligently compiled and shared among the employees, supervisors, and stakeholders of the factory. These daily reports contain lots of detailed information pertaining to the material amounts and transitions (e.g., sugarcane, juice, syrup/molasses, and raw sugar). With the goal of potentially improving efficiency in raw sugar manufacturing, we have developed a platform for data visualization and analysis of relevant trends. Using software packages like R and Python, data transcription is automated to collect relevant parameters from daily manufacturing reports shared by factories and to compile the data into spreadsheets. An application has also been developed that allows for users to select any two parameters for plotting and visualization of potential trends across a given grinding season or collection of seasons. In addition to the development of this application for data visualization, we are also using principles of big data and machine learning analyses to explore for trends and correlations that may be of significant interest in improving sugar quality and manufacturing efficiency. For example, Pearson correlations can quickly be generated over any number of collected parameters to identify where trends might exist. Machine learning techniques like regularized regression can be performed to determine the relative importance of different input variables on a given set of output variables. Preliminary results from these computational analyses will be presented and discussed. Overall, data analysis and visualization are critical to understanding process flows and operations and are the first step towards the incorporation of artificial intelligence and automation in agriculture and manufacturing industries. [ABSTRACT FROM AUTHOR]

Copyright of Journal of the American Society of Sugar Cane Technologists is the property of American Society of Sugar Cane Technologists and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)