Rai earns 2019 Best Paper Award

Rahul Rai.

by Nicole Capozziello

Published October 15, 2019

Rahul Rai, an associate professor in the Department of Mechanical and Aerospace Engineering, was recognized with a 2019 Best Paper Award from the Prognostics and Health Management (PHM) Society.

"Rahul has established himself as a national leader in research focused on the intersection of machine learning and mechanical engineering problems. His recent work in physics-based machine learning is allowing unprecedented insight into a multitude of cyber-physical systems problems, including design, control, diagnosis and prognostics."
Kemper Lewis, Moog Professor of Innovation and chair
Department of Mechanical and Aerospace Engineering

The PHM Society is an international organization that aims to provide free and unrestricted access to PHM knowledge, promote collaboration, and advance PHM as an engineering discipline.

The paper, titled “Classification Based Diagnosis: Integrating Partial Knowledge of the Physical System,” was co-authored with Ion Matei, Johan de Kleer, Alexander Feldman, and Maksym Zhenirovskyy. The research work was supported by the Defense Advanced Research Projects Agency (DARPA) Physics of Artificial Intelligence program and was carried out in collaboration with the Palo Alto Research Center.

“The physics-based machine learning PHM approach outlined in the paper opens the door to unprecedented applications in a multitude of cyber-physical systems, diagnostics, and prognostics applications,” says Rai.

The field of prognostics and health management aims to monitor the current health status and remaining useful life of cyber-physical systems while also reducing the maintenance cost. One common example is applications in modern-day printers; with the help of PHM, technologies can inform the user (on-screen) when there is an issue, such as a paper jam, and then outline the necessary steps to diagnose and rectify the problem.

"Rahul has established himself as a national leader in research focused on the intersection of machine learning and mechanical engineering problems,” says Kemper Lewis, chair of the Department of Mechanical and Aerospace Engineering and Moog Professor of Innovation. “His recent work in physics-based machine learning is allowing unprecedented insight into a multitude of cyber-physical systems problems, including design, control, diagnosis and prognostics."

Rai received his bachelor’s in engineering from the National Institute of Foundry and Forge Technology (NIFFT) in Ranchi, India, his M.S. in manufacturing engineering from the University of Missouri-Rolla, and his PhD in mechanical engineering from the University of Texas at Austin in 2006. He was awarded the 2017 Young Engineer award from the American Society of Mechanical Engineers’ (ASME) IDETC/CIE Division.

At UB, Rai is the director of the MADLab, an MAE research lab that is dedicated to establishing new computational methods to provide innovative solutions to manufacturing, engineering design and system design problems. The lab’s current projects include Physics LEArning (PLEA): A Hybrid Physics Guided Machine Learning Approach for Predictive Modeling of Complex Systems and COVIA: Computer Vision base Intelligent Assistant for Mistake Proofing of Complex Maintenance Tasks on Navy Ships.

The 2019 Best Paper Award was presented at the 11th annual PHM Conference, the society’s flagship event. The conference took place in Scottsdale, Ariz. from September 21-26, 2019.