Corning is a leading innovator in material science, with a 167-year record of creating life-changing products. Today, Corning's main market segments include optical communication, consumer electronics, display technology, automotive and life sciences vessels. In this lecture, applications of model predictive control, optimization and machine learning approaches to an industrial process will be discussed and reviewed. These technologies are a strategy to maintain a competitive advantage by improving operational performance and quickly diagnosing the process. The typical glass manufacturing process consists of the following main units: melting of batch material, refining the melt, mixing and temperature conditioning of the melt, and forming the melt into a glass product. The dynamic behavior of these processes strongly influences the quality of the final product. Furthermore, insights on supporting and maintaining of applications deployed will be touched on. Bio: Richard Mastragostino is a process control engineering supervisor at Corning, where he leads a team which develops, implements and supports advanced computational technologies to improve operational performance at facilities globally. He received his M.A.Sc of Chemical Engineering from McMaster University in 2012. His thesis focused on constructing optimization-based formulations for operability analysis and control of chemical process supply chains.