报告题目：From Sensors to Sensor Informatics

报告人：Robert X. Gao, Cady Staley Professor and Chair

(Department of Mechanical and Aerospace Engineering, Case Western Reserve University)
报告时间：2017年6月22日，下午1.30-2.30

报告地点：阳澄湖校区交通大楼一楼报告厅

报告人简历：

  Robert X. Gao is the Cady Staley Professor of Engineering and Department Chair of Mechanical and Aerospace Engineering at the Case Western Reserve University in Cleveland, Ohio, USA. Since receiving his Ph.D. from the Technical University of Berlin, Germany in 1991, he has been working on physics-based sensing methodology, multi-resolution signal processing, and energy-efficient sensor networks for improving the observability of systems and processes. Together with his students and research associates, he has published over 350 technical papers and 2 books. He holds 10 patents, and is a recipient of multiple honors and awards, including the IEEE Instrumentation and Measurement Society’s Technical Award (2013), NSF CA-REER award (1996), and multiple Best Paper/Outstanding Paper awards.

Prof. Gao is an elected Fellow of the IEEE, ASME, SME, and CIRP (International Academy for Production Engineering), a Distinguished Lecturer of the IEEE Instrumentation and Measurement Society, and a Corresponding Member of the Connecticut Academy of Science and Engineering. He was a Distinguished Lecturer of the IEEE Electron Devices Society, and served as an Associate Editor for four IEEE and ASME journals. Presently he serves as a Guest Editor for the Special Issue on Data Science-Enhanced Manufacturing of the ASME Journal of Manufacturing Science and Engineering.

报告摘要：

Recent advancement in data science has opened up new opportunities to complement advanced sensing technologies for more effective and efficient extraction of information embedded in raw sensor data to enable intelligence operation and control of machines and processes, leading to the low-cost production of high quality products. Actionable information generated by data analytics has the potential to increase the accuracy and reliability in predictive modeling of equipment failure rates and remaining useful life, consequently improving the robustness in preventative maintenance scheduling.

This seminar highlights research that integrates process-embedded sensing methods with advanced computational algorithms to improve the observability in manufacturing process monitoring and product quality control, using polymer injection molding as an example. The design, characterization, and realization of a multivariate sensor with acoustic wireless data transmission capability are introduced, which outperforms commercial sensors in predicting the quality attributes of injection molded parts, due to integration of advanced computational method. The presentation demonstrates the significance of integrating sensing physics with data analytics for advancing the science base for manufacturing.