Researchers at Oklahoma State University’s College of Engineering, Architecture, and Technology are developing advanced software to detect and diagnose faults in chemical distillation in real-time. Led by Dr. Zheyu Jiang, the team is collaborating with Fractionation Research Inc. (FRI) to address this important industry issue, according to an Oklahoma State University News report.
Distillation is a key process in chemical, petrochemical, and refining industries but is also a major energy consumer and emitter of greenhouse gases, accounting for 40-70% of energy use and emissions in chemical plants. Dr. Jiang's team noted that plants often rely on human experience to identify issues, causing delays. The current software also struggles to manage the complex data from sensors in these processes.
To address this, Jiang's team is developing FARM, a software that uses statistical features and deep learning for quick and accurate fault classification. “By developing advanced computational techniques and algorithms such as statistical process control, FARM allows chemical plants and refineries to detect any distillation process anomaly as soon as possible,” Jiang said in the report.
“The newly released U.S. Department of Energy Industrial Decarbonization Roadmap has identified distillation process innovation as a near-term action item to improve energy efficiency and decarbonization in chemical and refining industries. To achieve this goal, there is a huge opportunity to push the boundary of the safe operating window of distillation units toward higher energy efficiencies by implementing faster, more accurate real-time process monitoring technologies such as FARM.,” he said in a statement obtained by the Oklahoma State University News.
Graduate students are involved in the project, contributing to the development and testing of the software. Their work provides valuable experience and practical skills for their careers.
