Tutorials

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. Note that tutorial slide are can be downloaded from this web page (see attachments below)

Thursday, 1:30 PM – Model-Based Prognostics – An Introduction
Indranil Roychoudhury, SGT, NASA Ames

Abstract: This tutorial will cover the basics of model-based prognostics, and include concepts such as modeling approaches, estimation and prediction algorithms, and how uncertainty is represented and quantified. Other topics covered will include structural model decomposition, system-level prognostics, prognostics of hybrid systems, and distributed prognostics. Several case studies, such as water recovery systems to the prediction of safety margins in the national airspace system will be used to explain different concepts of prognostics and demonstrate their application to real-world systems.

Bio: Dr. 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. Since August 2009, he has been with SGT, Inc., at NASA Ames Research Center as a Computer Scientist. 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 the AIAA and a Senior Member of the IEEE.

Tuesday, 3:00 PM – Design, Development, and Testing of PHM Software
Chris Teubert, NASA Ames Research Center

Abstract: This tutorial will describe the process of designing, developing, and testing PHM software, from the definition of requirements to deployment and maintenance. The emphasis will be on the design and creation of the software product, not the PHM algorithms. Description will include real-life examples from the Diagnostics and Prognostics group at NASA Ames Research Center for the creation of a prognostics application leveraging the Generic Software Architecture for Prognostics (GSAP). Topics covered include selection of software development processes, requirement definition and management, software architecting, design, testing, and maintenance for PHM Applications. The tutorial will include open discussions where attendees are encouraged to provide input from their experiences with PHM application design. Following this tutorial, attendees should have a better understanding of the process of creating PHM applications, with recommendations and advice from individuals experienced with PHM application design.

Bio: Christopher Teubert is a software engineer and group lead of the Diagnostics and Prognostics group at NASA Ames Research Center. He specializes in the application of prognostics algorithms and the design of prognostics applications. He is also the principal investigator for the Generic Software Architecture for Prognostics (GSAP) and Prognostics as a Service (PaaS) projects. Christopher received his B.S. in Aerospace Engineering from Iowa State University in 2012 and is currently working on his M.S. in Computer Science and Engineering at Santa Clara University. Christopher worked as a research engineer with Stinger Ghafarrian Technologies (SGT) at NASA Ames Research Center from 2012-2016 and has worked as a civil servant at NASA Ames since 2016.

Thursday, 8:00 AM – Electrical Power Systems Condition Monitoring for Improved Electronic Systems Health Management & System Resilience
Patrick Kalgren, Singularity – Intelligence Amplified, LLC

Abstract: Electrical power generation, conditioning, distribution, and management systems are critical to full operational capability of airborne, land, sea, and space systems. Prognostics and health management technologies offer the opportunity to decrease operating costs and increase availability, dependability, efficient utilization, and resilience of these critical infrastructure systems. This tutorial explores technologies and strategies to enable condition awareness and ensure reliable operations; discusses technical progress made in the recent past for electronic power systems health management, considers practical applications of the new technologies, and suggests strategies to foster industry acceptance and adoption of PHM capability in support of increasingly complex grid and microgrid energy solutions.

Bio: Patrick W. Kalgren is a founding partner and the manager of research & engineering at Singularity – Intelligence Amplified. He has a successful background in research and development of new technologies for electronic and power systems health management, self-aware processing systems, and decision support applications. Patrick’s contributions in electronic system prognostics and health management and novel data fusion and reasoning, combining physics-based and data driven techniques for PHM, have yielded two awarded patents and four additional patents pending, Mr. Kalgren has published more than 50 papers, and presented invited lectures and tutorials at multiple engineering society events. Patrick has a B.S. degree in Computer Engineering from Penn State University and is a member of Tau Beta Pi, The IEEE, and the American Helicopter Society

Thursday, 10:30 AM – Deep Learning for PHM
Emilien Dupont, Schlumberger

Abstract: Deep Learning has been evolving very quickly over the last few years. This tutorial will aim to give a general introduction to modern Neural Networks and present some of the most recent techniques and why so many great success have come out of Deep Learning in recent years. We will also talk about Deep Learning in the context of PHM and how these techniques can be applied to various problems with time series data. Finally, we will discuss how to blend different types of data (e.g. text, image, time series…) into a single model in the context of predictive maintenance using Deep Learning.

Bio: Emilien is working as a Data Scientist in the Machine Learning team at the Schlumberger Software Technology and Innovation Center (STIC) in Menlo Park, CA. Emilien graduated with an MS in Computational and Applied Mathematics from Stanford University. Prior to this Emilien obtained a BSc in Theoretical Physics from Imperial College London. He works with applications of Machine Learning, and Deep Learning in particular, to problems in Oil and Gas. He also does research on generative models and variational inference.