One of the unique features of the PHM conferences is free technical tutorials on various topics in health management taught by industry experts. As educational events tutorials provide a comprehensive introduction to the state-of-the-art in the tutorial’s topic. Proposed tutorials address the interests of a varied audience: beginners, developers, designers, researchers, practitioners, and decision makers who wish to learn a given aspect of prognostic health management. Tutorials will focus both on theoretical aspects as well as industrial applications of prognostics. These tutorials reach a good balance between the topic coverage and its relevance to the community.

Uncertainty Management for PHM
Shankar Sankararaman, PwC

Abstract: This tutorial will focus on the significance, interpretation, quantification, and management of uncertainty in prognostics, with an emphasis on predicting the remaining useful life of engineering systems and components. Prognostics deals with predicting the future behavior of engineering systems, and is affected by various sources of uncertainty. In order to facilitate meaningful prognostics-based decision-making, it is important to analyze how these sources of uncertainty affect prognostics, and thereby, compute the overall uncertainty in the remaining useful life prediction. However, several state-of-the-art industrial techniques do not consider a systematic approach to the treatment of uncertainty. This tutorial will explain the paramount importance of uncertainty quantification and management in prognostics, focusing both on testing-based life prediction and condition-based prognostics. In particular, the suitability of classical (frequentist) and subjective (Bayesian) approaches to uncertainty will be discussed, and it will be explained that the Bayesian interpretation of uncertainty is more suitable for condition-based prognostics and health monitoring. Numerical examples will be used to demonstrate that uncertainty quantification in remaining useful life prediction needs to be approached as an uncertainty propagation problem that can be solved using a variety of statistical methods. Several uncertainty propagation methods will be explained in detail, through immersive implementation (in Python). Finally, practical challenges pertaining to uncertainty quantification and management in prognostics will also be discussed.

Presenter Bio: Shankar Sankararaman received a B.S. in civil engineering from the Indian Institute of Technology, Madras, in 2007, and later obtained a Ph.D. in civil engineering from Vanderbilt University, Nashville, TN, USA, in 2012. Soon after, he joined NASA Ames Research Center, Moffett Field, CA, where he developed algorithms for system health monitoring, prognostics, decision-making, and uncertainty management. His research focuses on the various aspects of uncertainty quantification, integration, and management in different types of aerospace, mechanical, and civil engineering systems. His research interests include probabilistic methods, risk and reliability analysis, Bayesian networks, system health monitoring, diagnosis and prognosis, decision-making under uncertainty, and multidisciplinary analysis. He is a member of the Non-Deterministic Approaches (NDA) technical committee at the American Institute of Aeronautics, the Probabilistic Methods Technical Committee (PMC) at the American Society of Civil Engineers (ASCE), and the Prognostics and Health Management (PHM) Society. Shankar has co-authored a book on prognostics and published over 100 technical articles in international journals and conferences. Presently, Shankar works as a consultant with PwC where he leads machine learning and predictive analytics efforts for various industrial and business challenges.

Introduction to Prognostics
Matteo Corbetta, SGT, NASA Ames Research Center

Abstract: This tutorial will focus on the fundamentals and basic concepts of prognostics and health management, giving emphasis to condition-based approaches. The audience will be introduced to the key elements that compose a prognostic framework, their interaction, uncertainty and effect on the prediction of the system evolution over time. The session will continue with an overview of data-driven and model-based approaches for prognostics, and will also propose two case studies on prognostic and failure prediction written in Python programming language. The participants will have direct access to the Python scripts and will be able to run them on their personal laptop*. The tutorial will summarize the theory behind the two algorithms, and will guide the audience through the code for a thorough understanding, from data preprocessing to output representation.
*The examples will require Python 2.6 or later, and libraries NumPy, SciPy, and matplotlib, installed on the machine.

Presenter Bio: Matteo Corbetta is a Research Engineer with SGT Inc., at NASA Ames Research Center, Calif. His research activity focuses on developing algorithms for diagnostics, prognostics, and uncertainty quantification for critical engineering assets. His recent works involves applications in autonomous aerial systems, aerial vehicle diagnostic and prognostic, and urban air mobility. Prior to joining NASA, he worked as R&D Condition Monitoring Systems Engineer at Siemens Gamesa Renewable Energy, Denmark, and as a Postdoctoral Researcher at Politecnico di Milano, Italy. He obtained Ph.D., M.Sc., and B.Sc. in mechanical engineering from Politecnico di Milano in 2016, 2012 and 2009.

Prognostics and Health Management on the Cloud—An Introduction
José Celaya and Indranil Roychoudhury, Schlumberger

Abstract: This tutorial will motivate the use of cloud computing services as a development tool for prognostics applications. It will then cover the implementation of a physics-based prognostics approach on the Google Cloud Platform, and demonstrate how this cloud-friendly PHM approach can be used to predict the Remaining Useful Life (RUL) of an IIoT testbed from the Oil & Gas industry that is representative of a 3-well-pad. Topics covered would be physics-based fault detection, fault isolation, fault identification, and RUL prediction and their ‘cloud-friendly’ implementation.

Presenter Bios: Indranil Roychoudhury received the B.E. (Hons.) degree in Electrical and Electronics Engineering from Birla Institute of Technology and Science, Pilani, Rajasthan, India in 2004, and the M.S. and Ph.D. degrees in Computer Science from Vanderbilt University, Nashville, Tennessee, USA, in 2006 and 2009, respectively. Currently, Dr. Roychoudhury is an AI Scientist at the Schlumberger Software Technology Innovation Center in Menlo Park, California. Prior to that, he was with SGT, Inc., at NASA Ames Research Center as a Computer Scientist from 2009 - 2018. His research interests include hybrid systems modeling, model-based diagnostics and prognostics, distributed diagnostics and prognostics, and Bayesian diagnostics of complex physical systems. Dr. Roychoudhury is a member of the Prognostics and Health Management Society and a Senior Member of the IEEE.

José R. Celaya is a Principal Scientist and Machine Learning Technical Lead Manager at the Software Technology and Innovation Center, Schlumberger. Previously, he was the Lead Scientist and Co-lead at the Diagnostics and Prognostics Group and a founding member of the Prognostics Center of Excellence, both at the Intelligent Systems Division of NASA Ames Research Center. He received a Ph.D. degree in Decision Sciences and Engineering Systems in 2008, a M. E. degree in Operations Research and Statistics in 2008, a M. S. degree in Electrical Engineering in 2003, all from Rensselaer Polytechnic Institute, Troy New York; and a B. S. in Cybernetics Engineering in 2001 from CETYS University, México.


follow us

PHM Society on Facebook Follow PHM Society on Twitter PHM Society on LinkedIn PHM Society RSS News Feed