Carrasco-Navarro, RocíoGaray-Gutiérrez, Adrian J.2023-04-142023-04-142022-11Garay-Gutiérrez, A. J. (2022). Discharge Moisture Prediction of the Corn Gluten Feed Drying Process Using Machine Learning Algorithms. Trabajo de obtención de grado, Maestría en Ciencia de Datos. Tlaquepaque, Jalisco: ITESO.https://hdl.handle.net/11117/8884Modern manufacturing processes have multiple sensors (or instruments) installed that provide constant data stream outputs; however, there are some critical performance and quality variables where installing physical sensors is either impractical, expensive, not hardy enough for hostile environments or the sensor technology is not sufficiently advanced. An example of such a problem is measure moisture of solid products in real-time. If this scenario happens, Machine Learning (ML) approaches are a suitable solution as are capable of learning and representing complex relationships. ML algorithms establish a mathematical relationship between the quantity of interest and other measurable quantities such as readings from already available sensors (e.g., SCADA, historian softwares, SQL Databases, etc.). This study details how ML algorithms (Such as Multiple Linear Regression, Support Vector Machine Regression and Regression Trees) are used to predict critical variable moisture in gluten feed (a by-product of the wet-milling of maize grain for starch or ethanol production) as a simple, robust and fast solution for the lack of this variable real-time information for a corn products manufacturer. The resulting model performance demonstrates the feasibility of the ML algorithms approach to predict moisture behaviour.engMachine LearningVirtual SensorsMultiple Linear RegressionSupport Vector Machine RegressionRegression TreesDrying Processinfo:eu-repo/semantics/masterThesis