Jianjun Shi
Carolyn J. Stewart Chair and Professor
H. Milton Stewart School of Industrial and Systems Engineering
Georgia Institute of Technology

Monday, November 10
12 – 1 p.m.
Location: Callaway/GTMI bldg.,
Room 114

Lunch provided for in-person attendees on a first come first serve basis.

If you can’t join us in-person, just us virtually via Zoom.

Whether you are joining us virtually or in person, please register here prior to attending.

Presententation Title: Quality Feedback Control: Concepts, Methodologies, and Implementations

Bio: Jianjun Shi is the Carolyn J. Stewart Chair and Professor in H. Milton Stewart School of Industrial and Systems Engineering, with joint appointment in the George W. Woodruff School of Mechanical Engineering, Georgia Institute of Technology. His research interests focus on data fusion for quality improvements, with emphasis on integration of system informatics, advanced statistics and machine learning, and control theory for the design and operational improvements in advanced manufacturing applications. The technologies developed in Dr. Shi’s research group have been widely implemented in various production systems with significant economic impacts.

Dr. Shi is a member of the National Academy of Engineering (NAE), an Academician of the International Academy for Quality, and a Fellow of ASME, IISE, INFORMs, ISI, and SME. He received numerous awards and recognitions, including the ASA Deming Lecturer Award, the ASQ Shainin Metal, the ENBIS George Box Medal, the ASQ Walter Shewhart Medal, the SME/NAMRI S. M. Wu Research Implementation Award, the ASQ Brumbaugh Award, IISE David F. Baker Distinguished Research Award (2016), and the IIE Albert G. Holzman Distinguished Educator Award. He is the founding chair of the Quality, Statistics and Reliability (QSR) Division at INFORMS. He served as the Editor-in-Chief of the IISE Transactions (2017-2020), the flagship journal of the Institute of Industrial and Systems Engineers.

More information about Jianjun Shi can be found at https://sites.gatech.edu/jianjun-shi/

Abstract: This presentation introduces the new concept of “Quality Feedback Control” for In-Process Quality Improvement (IPQI). IPQI emphasizes active defect mitigation in smart and autonomous manufacturing systems, and “Quality Feedback Control” is an enabling technology to achieve IPQI. Different from conventional automation that typically uses differential or difference equations with the machine output status as the feedback control, the “Quality Feedback Control” paradigm directly uses the product quality measurement as the feedback information to manipulate the inputs of machine(s) that impact the product quality. Due to the heterogeneous nature of quality data (e.g. multichannel functional curves, high resolution images, high speed videos, or 3D scanning data with millions of unstructured point clouds, etc.) and associated diverse data acquisition strategies, a set of fundamental issues need to be addressed to innovatively model the quality outputs with the control inputs, and further use this model to develop effective control strategies. This presentation lays out the foundation for the “Quality Feedback Control” paradigm and discusses its research opportunities, challenges, and advancements with an emphasis on how machine learning and quality feedback control have reshaped the landscape of IPQI.

Examples of ongoing research projects, including applications in automotive, aerospace, semiconductor, steel mills, and 3D printing, are used to illustrate and exemplify the frontiers of this research area. All examples come from real world data and industrial production systems.