Interview Of The Week

Interview Of The Week: Jay Lee, Industrial AI Expert

Jay Lee (PhD) is Clark Distinguished Professor and Director of Industrial AI Center in the Mechanical Engineering Dept. of the University of Maryland College Park. He is a member of The World Economic Forum’s Global Future Counil on Advanced Manufacturing and Production, a member of the Board of Governors of the Manufacturing Executive Leadership Council of National Association of Manufacturers (NAM), Board of Trustees of MTConnect and a senior advisor to McKinsey.

Lee took a leave from a professorship at the University of Cincinnati to serve as Vice Chairman and Board Member for Foxconn Technology Group during 2019-2021 to lead the development of Foxconn Wisconsin Science Park. ( In addition, he advised Foxconn business units which went on to receive five Forum Lighthouse Factory Awards since 2019.

From 2001 to 2019 Lee served as Founding Director of the National Science Foundation (NSF) Industry/University Cooperative Research Center (I/UCRC) on Intelligent Maintenance Systems ( which developed research memberships with over 100 global companies since 2000 and was selected as the most economically impactful I/UCRC in the NSF Economic Impact Study Report in 2012. Lee is also the Founding Director of the Industrial AI Center ( ). He developed a number of start-up companies, including Predictronics ,through NSF iCorp in 2013 and has won first place five times in the PHM Society Data Challenges competition.

Lee also previously served as Director for Product Development and Manufacturing at United Technologies Research Center (now Raytheon Technologies Research Center) as well as Program Director for a number of programs at the NSF. He was selected as one of 30 Visionaries in Smart Manufacturing by SME in Jan. 2016 and 20 most influential professors in Smart Manufacturing in June 2020, and received the SME Eli Whitney Productivity Award and the SME/NAMRC S.M. Wu Research Implementation Award in 2022. His book on Industrial AI was published by Springer in 2020. Lee recently spoke to The Innovator about how to can scale industrial artificial intelligence (AI).

Q: What is holding manufacturers back from using AI at scale?

JL: AI learning is based on features. You can’t use the same algorithm to evaluate machines with different features, so you need to reconfigure for each machine. That is why so far there has been little success to scale up AI implementation in industrial applications.

Q: What is the solution?

JL: To scale up the AI deployment, you need a process with systematic disciplines. Industrial AI is a systematic methodology and discipline which combines four technologies: data technology, analytics technology, platform technology and operations technology, to provide highly accurate generic solutions to industry problems  These interoperable systems consist of information gathering ability, intelligent analytics, and actuation mechanisms that interact with the physical world to support real-time decision-making and guarantee system performance. By leveraging the capabilities of industrial Internet systems along with industrial AI technology, a sophisticated quality management system known as Stream-of-Quality or SOQ can be implemented.

Q: How does this work in practice?

JL: For example, a manufacturer has 20 different machines with 20 different applications need to connect all the systems together so that the algorithms can select features from process parameters rather than be dedicated to one machine. This allows AI to act in the connected server and eliminate the current bottle necks. If you apply SOQ, you can program for one quality at the end by making predictions backwards and forwards.

Q: Can you expand on that?

JL: SoQ integrates product quality using a blockchain-based information stream from various stages of manufacturing to increase the accuracy of performance predictions, prevent common failures and increase the traceability of process-to-process relationships. It keeps track of product quality at each stage and uses machine learning algorithms to predict the final product’s quality by correlating individual stages’ uncertainty with various quality attributes at part, process, and performance levels.  This allows companies to use AI in a consistent, sustainable way. In Japan, Kaizen has been used as a standard practice to focus on continuous improvement because they had no connected data. But if you have connected data, it eliminates the need for reactively performing continuous improvement based on problems. You don’t have to wait for a problem and solve it with AI. AI should find the problem you don’t even know you have. For example, before a part is cut you know how accurate the machine will be. If the AI detects a spindle problem and predicts that the machine is 10% off the mark. you can fix the problem before you produce the parts. We worked with Toyota’s Georgetown, Kentucky plant to implement AI for facility monitoring to achieve maintenance cost reduction of 50% in 2006.  It has achieved zero-downtime for its compressor systems since 2006.

Q: What advice do you have for manufacturers who want to scale up AI?

JL:  The SOQ process needs connected data from multiple sources: Critical performance metrics defined by humans interacting with manufacturing machines; multisensory data gathered from different machines’ locations during production; properties of the material used for manufacturing and their safe operating thresholds; information about stage-specific operating conditions that are used for the physical transformation of material;and knowledge about the effect of ambient conditions that are external to the manufacturing process but still influence the final product’s quality. Make the combined data explainable, not just understandable. Once you establish this baseline then you can apply industrial AI and SOQ to achieve worry-free manufacturing. If done well your plant can serve as a lighthouse, giving guidance to other industry players.

This article is content that would normally only be available to subscribers. Sign up for a four-week free trial to see what you have been missing.

To access more of The Innovator’s Interview Of The Week articles click here.



About the author

Jennifer L. Schenker

Jennifer L. Schenker, an award-winning journalist, has been covering the global tech industry from Europe since 1985, working full-time, at various points in her career for the Wall Street Journal Europe, Time Magazine, International Herald Tribune, Red Herring and BusinessWeek. She is currently the editor-in-chief of The Innovator, an English-language global publication about the digital transformation of business. Jennifer was voted one of the 50 most inspiring women in technology in Europe in 2015 and 2016 and was named by Forbes Magazine in 2018 as one of the 30 women leaders disrupting tech in France. She has been a World Economic Forum Tech Pioneers judge for 20 years. She lives in Paris and has dual U.S. and French citizenship.