Amy Sprague
November 10, 2026
Georgia Tech’s Jianjun Shi shows how combining AI, statistics, and engineering knowledge can catch quality problems before they get costly.
ISE hosted Jianjun Shi, a member of the National Academy of Engineering and the Carolyn J. Stewart Chair and Professor at the Georgia Institute of Technology, for a research seminar titled "Engineering-Informed AI/ML Enabled Quality Improvement in Smart Manufacturing." Shi's talk tackled a question many manufacturers now face: how to turn the huge volumes of data from modern production systems into insights that actually improve product quality, process reliability, and performance.
Today's manufacturing facilities run on dense networks of sensors that track equipment, processes, and product characteristics. That data is abundant, but making sense of it is hard because it's complex, messy, and comes from many different sources.
Shi demonstrated that engineering-informed AI and machine learning can help. Instead of treating manufacturing as a pure data-prediction problem, his research showed how we can build physical principles, statistical reasoning, and engineering expertise directly into AI/ML methods. The result is models that hold up better against the messiness of real manufacturing settings, especially when processes interact in complex ways or quality needs to be monitored in real time.
Using examples from real industrial production data, Shi walked through recent methodological advances, the practical challenges of putting them to work on a factory floor, and ways to turn AI/ML research into real operational gains. He returned to one theme throughout: methodological innovation only matters if it's tested against real engineering problems and validated through actual implementation.
As manufacturing systems get more connected and autonomous, AI that's grounded in engineering knowledge will be crucial to keep systems reliable, interpretable, and useful for quality management. This is a core tenet for ISE, where faculty work on data analytics, intelligent decision-making, and the design and improvement of complex engineered systems.
In addition to his seminar, Prof. Shi met with ISE faculty and students to discuss their research and share his insights and advice. His visit provided a valuable opportunity for the ISE community to engage with a National Academy of Engineering member and internationally recognized leader in industrial process monitoring and quality control. The department greatly appreciated his visit and the perspectives he shared, particularly on how fundamental advances in statistics, AI, and engineering can lead to practical improvements in production quality, including aerospace manufacturing.
About Jianjun Shi
Jianjun Shi is the Carolyn J. Stewart Chair and Professor in the H. Milton Stewart School of Industrial and Systems Engineering at Georgia Tech. His research combines AI/ML, statistics, data science, and engineering knowledge to improve quality in advanced manufacturing. He is a member of the U.S. National Academy of Engineering, an Academician of the International Academy for Quality, and a Fellow of five professional societies: ASME, IISE, INFORMS, ISI, and SME. His honors include the 2025 ASA Deming Lecturer Award, the 2025 ASQ Shainin Medal, the 2022 ENBIS George Box Medal, the 2021 ASQ Walter Shewhart Medal, and the 2016 IISE David F. Baker Distinguished Research Award. He served as Editor-in-Chief of IISE Transactions from 2017 to 2020.
For more on his research, visit Jianjun Shi's faculty website.