Ivan Castillo serves as the Senior Data Scientist for the Chemometrics, AI and Statistics group within the Technical Expertise and Support (TES) organization. Since joining Dow in 2011, Ivan has applied data analytics, AI, and machine learning technologies alongside chemical engineering principles to support various projects for businesses and functions across Dow. These projects include unplanned shutdown investigations, accelerated catalyst aging issues, kinetics model improvement, customer technical service support, plant start-up support, advanced control and optimization improvement, capacity improvement, cycle time reduction, and fouling issues. Ivan also teaches and coaches advanced data analysis and statistics to facilitate data-driven problem-solving and promote data analytics usage at Dow.
Ivan has a Ph.D. in Chemical Engineering from the University of Texas at Austin, a M.S. in Electrical Engineering from Universidad de los Andes (Bogota, Colombia), with an emphasis in control and automation, and a B.S. in Electrical Engineering from Pontificia Universidad Javeriana (Bogota, Colombia). His research interests are fault detection and isolation, the application of machine learning approaches in chemical manufacturing, optimization, and control. Ivan has been recognized with eight Technology Center Awards, generating over $210MM NPV10 in value. Ivan currently serves as a member of the AIChE Program Committee Executive Board (EBPC) and Director for the Fuels and Petrochemicals Division (F&PD). He also served as the Industry 4.0 Topical Chair (from 2021 to 2023) and as the Meeting Program Chair (MPC) for the 2022 AIChE Spring meeting. In 2021, Ivan received the AIChE Herb Epstein Award for Technical Programming. Ivan is co-author of 40+ internal Dow technical reports (CRIs), 45+ external journal publications, 40+ conference meeting presentations and 4 patents.
This session examines methods that combine artificial intelligence with other approaches to improve predictive diagnostics in industrial production, particularly in scenarios with limited data and uncertainty. The discussion includes examples of AI applications for predicting heat exchanger fouling. The case study demonstrates how integrating physics-based models with machine learning can enhance reliability, reduce downtime, and support more cost-effective decision-making in energy management.
Check out the incredible speaker line-up to see who will be joining Ivan.
Download The Latest Agenda