Chemical Industry Leader BASF Taps LSU to Create “Soft Sensors” Using AI
September 20, 2022
Optimizing Chemical Manufacturing Operations
BASF, the largest chemical producer in the world, is collaborating with LSU chemical engineers to better understand and predict its own production ebbs and flows using artificial intelligence, or AI.
BASF’s chemical manufacturing plant in Geismar, Louisiana, is one of the company’s six largest integrated production sites across 80 countries. It supplies products to a wide variety of industries, including agriculture, construction, energy and health. Chemicals such as solvents, amines, resins, glues, electronic-grade chemicals, industrial gases, basic petrochemicals and inorganic chemicals are produced at Geismar in about 30 interconnected production units, each containing its own subunits.
While BASF is rich in data, it can be challenging to turn production data into operational knowledge. That’s why BASF engineers turned to LSU to develop AI and machine learning solutions to help organize their data and understand how changes in one production unit might force different operating conditions in other, connected units.
BASF now works with LSU to develop something called soft sensors. Unlike physical sensors, which can melt or just be impossible to use in the sometimes extreme operating conditions of a chemical manufacturing plant, soft sensors are entirely driven by data.
“With machine learning and AI, we have a new opportunity to solve problems we couldn’t solve before, where we cannot find a solution with conventional tools,” said LSU Professor José Romagnoli.
The project adds to an ongoing partnership between LSU and BASF to develop emerging engineering talent for Louisiana.
LSU researchers are using AI and machine learning to identify connections between continuously changing operating conditions at BASF’s Geismar chemical manufacturing plant and optimize production. BASF, the largest chemical producer in the world, has a longstanding partnership with LSU related to talent development, research and diversity and inclusion programs. The image above was generated by AI based on keywords: chemical tubes, pipelines, plant, interconnected.
– LSU
“It just made perfect sense for us to collaborate with LSU. Instead of waiting 12 hours for a lab sample or for the next shift to take a new sample, LSU can help us find a way to predict what is happening inside our units, just based on data and AI.”
Kerr Wall, digitalization manager in the monomers division at BASF Geismar