Abhinav Saxena
Abhinav has been working in the area of diagnostics and prognostics for the last 12 years. He started his research career as a grad student at Georgia Tech, and then as a Research Scientist at NASA Ames Research Center's Prognostics Center of Excellence. In the first phase of his career, he was involved in fundamental research on how things break - specifically studying the fundamental mechanisms of failed systems so that these processes could be modeled and used for predicting remaining useful life. He studied and developed experimental test-beds to collect run-to-failure data from a variety of systems such as electromechanical actuators, mechanical gears and bearings, electronic semiconductor devices, power storage devices and composite structures, as applied in a variety of domains. At GE Research, Abhinav has applied AI and ML technologies to a variety of business problems that span power, healthcare, transportation and aviation, and has worked on several projects with digital on productizing ML capabilities.
Abhinav is very active in the prognostics and health management (PHM) professional community. He has published over 100 research articles and is also a co-author of the book on Prognostics. He has been on several conference organizing committees and journal special issues. He is currently the Chief Editor of the International Journal of Prognostics and Health Management (IJPHM). In 2017, Abhinav was conferred the fellowship of the PHM Society, a rare honor that the PHM Society bestows based on contributions to the research field in the past 15 years. He is also Adjunct Professor, Division of Operations and Maintenance Engineering, Luleå University of Technology, Sweden and an active member of SAE Standards working committee.
He has a Ph.D. in Electrical and Computer Engineering from Georgia Institute of Technology, Atlanta.
After over a seven to eight years of fundamental research, I have thoroughly enjoyed the variety and depth of practical problems that I have been exposed to at GE. Here we are not only we are dealing with real-world industrial problems with the constraints of data quality, access, deployment etc. but also strive to develop, use and push state-of-the-art in AIML solutions that generally don't exist out there...