PHM Society Short Course – PHM Fundamentals: Monitoring/Sensing to Fault Diagnosis, Failure Prognosis and Case Studies

Register for short courses here


Date: Saturday, September 21, 2019 – Sunday, September 22, 2019
Time: 8:00 AM – 5:00 PM

The PHM Society offers an updated two-day intensive short course titled, PHM Fundamentals and Case Studies— From Monitoring/Sensing to Fault Diagnosis/Failure Prognosis and Case Studies, on PHM tools, methods, applications and case studies on September 21-22 in Scottsdale, AZ, USA right before the PHM19 conference. This follows from the first offering at the PHM14 conference in Fort Worth, TX with 48 attendees and regular ratings of 4/5. It was also run in 2015 in San Diego, 2016 in both Bilbao, Spain and Denver USA, in St. Petersburg, USA in 2017 and Philadelphia in 2018. And Utrecht, Netherlands in July 2018.

As in the previous offerings, the course will be taught by recognized international experts in the PHM field and will cover the current state of the art in PHM technologies, sensors and sensing strategies, data mining tools, CBM+ technologies, novel diagnostic and prognostic algorithms as well as a diverse array of application examples/case studies. It is addressed to engineers, scientists, operations managers, educators, small business principals and system designers interested to learn how these emerging technologies can impact their work environment.

Through a lecture (with Q&A), networking and workshop format with
specialist experts, participants will:

  1. Establish a baseline for defining the extent and capabilities of PHM,
    specifically needs and organization
  2. Identify specific details of PHM Applications (metrics, sensors, cost
    benefits, reliability) and PHM Methods (diagnostics, prognostics, data
    driven methods and uncertainty)
  3. Identify issues and needs and a way forward including Continuing
    Professional Development
  4. Examine case studies of PHM applications across diverse domains to
    identify solutions and impacts
  5. Plan a PHM application in two mini workshop settings with expert group
    leaders

Note: A PHM Society Certificate can be provided for 1.4 Continuing Professional Development Units to each participant completing the course, on request.

Course Leaders:
Prof. G. Vachtsevanos, and Dr. Karl Reichard

Course Presenters:
Specialists using packaged PHM Society curriculum, case studies and
mini-workshop topics.

Course Administrator:
Jeff Bird jeffbird@rogers.com

Course Location:
At the Conference venue: The Scottsdale Resort at McCormick Ranch, 7700
East McCormick Parkway, Scottsdale, Arizona 85258. (Phone 1-480-596-7517)

Course Preparation

  1. Background reading and references: http://www.phmsociety.org/references/documents/recommended-reading
  1. Workshop topic: We will work in small groups on small realistic
    problems: Day one: developing PHM requirements- needs, metrics and on
    the second day- data and modeling approaches, operational issues. You
    are encouraged to bring a problem statement from your organization:
    Problem definition, asset of interest, health management objectives,
    and customer(s).

DAY 1 Topic/Format Speaker
800 to 820 Welcome and Introductions (All participants) Jeff Bird, TECnos
820 to 900 Introduction to PHM
(Taxonomy, scope, basics, standards- for all talks
Jeff
900 to 945 Deriving Requirements for PHM
(Basics and illustrative examples)
Abhinav Saxena, GE
945 to 1030 PHM Performance Metrics
(Basics and illustrative examples)
Abhinav
1030 to 1045 Break with refreshments and snacks provided
1045 to 1130 Diagnostics Methods
(Basics and illustrative examples)
1130 to 1145 Open Questions and Introduction to Mini-workshop Jeff, All
1145 to 1230 Lunch provided
1230 to 100 Case Study for requirements/metrics Abhinav
100 to 145 Prognostics
(Basics and illustrative examples including uncertainty)
Abhinav Saxena, GE
145 to 230 Data Analytics Methods
(Basics and illustrative examples)
José Celaya, Schlumberger
230 to 315 Prognostics and Data Analytics Case Studies
(2 case studies for prognosis and data analytics applications)
Abhinav, José
315 to 330 Break with refreshments and snacks provided
330 to 415 Sensors and Data Processing
(Available/Required data and organization)
Karl Reichard, Penn State University
415 to 500 Analysis mini workshop
(Small group data design activity with worksheets)
All for breakouts
500 to 515 Summary of workshop results (Each group reports results) Jeff
730 pm -? Non-hosted dinner with all participants

 

DAY 2 Topic/Format Speaker
830 to 915 CBM+ and IVHM Technologies
(Basics and illustrative examples)
Karl
915 to 1000 PHM Cost Benefit Analysis
(Basics with cost-benefit analysis, examples)
Jeff
1000 to 1030 Plenary- Issues and Needs
(Review to compile collected issues from all participants)
All
1030 to 1045 Break with refreshments and snacks provided
1045 to 1130 Reliability and Life Cycle Management
(Linking reliability and PHM approaches)
George Vachtsevanos, Georgia Tech University
1130 to 1145 Case Study Workshop Introduction
(Small group activity builds on data design mini)
Jeff
1145 to 1245 Lunch provided
1245 to 145 Fielded Systems Case Studies-1
(2 case studies for CBM and Reliability)
Karl

George

145 to 215 Fielded Systems Case Studies-2
(3rd case study for CBA)
Jeff
215 to 320 Case Study Mini workshop
(Small group activity and reporting)
All for breakouts
320 to 340 Break with refreshments and snacks provided
340 to 400 Way forward
(Paths, Resources, Continuing Professional Development)
Jeff, George and Karl
400 to 415 Wrap-up with Evaluation Forms All

 

Presenters

Experienced PHMers will present the tuned PHM Society content and also lead the mini-workshop small group discussions. Interactions are encouraged during breaks and lunch among the course participants.

Jeff Bird is currently a consultant with TECnos Consulting Services, Ottawa, Canada. His present avocations include advancing the art, science and business of prognostics and health management in diverse fields. Specifically, he leads PHM Society board initiatives in Education and Professional Development as well as Standards. He recently completed one career spanning 30 years as a Research Officer at the Gas Turbine Laboratory of the National Research Council Canada. His published research there was on gas turbine dynamics and performance, health monitoring and management, adverse environments, and uncertainty. Previously he worked as an Operational Research scientific officer in the Department of National Defence where he enjoyed contributing to airlift and search and rescue planning. He studied at the University of Toronto (Engineering Science- Aerospace) and at Carleton University (Mechanical, Aerospace and Systems).

Dr. José Celaya is a Senior Data Scientist with the Schlumberger Software Technology Innovation Center. He previously was a research scientist with SGT Inc., a senior member in the Prognostics Center of Excellence and the Diagnostics and Prognostics Group Co-Lead at 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, Mexico.

Dr. Karl Reichard has over 25 years of experience in the design and development of advanced measurement, control and monitoring systems. He received the Ph.D., M.S. and B.S. degrees in Electrical Engineering from the Virginia Polytechnic Institute and State University (Virginia Tech). Dr. Reichard is a Dr. Reichard is an Associate Research Professor with the Pennsylvania State University Applied Research Laboratory and the Penn State Graduate Program in Acoustics. His research experience includes the development of embedded and distributed sensing and control systems for machinery and system health monitoring, acoustic surveillance and detection, active noise and vibration control and electro-optics. Dr. Reichard is a member of the Board of Directors of the Prognostics and Health Management Society, and a member of the IEEE and the Acoustical Society of America. He is the author of over 50 papers and articles published in journals and conference proceedings.

Dr. Abhinav Saxena is a Senior Scientist in AI & Learning Systems organization at GE Global Research Center. Abhinav is currently involved with developing PHM solutions for various industrial systems at GE and driving integration of PHM analytics in GE’s industrial internet platform. Abhinav is also an adjunct professor in the Division of Operation and Maintenance Engineering at Luleå University of Technology, Sweden. Prior to GE, Abhinav was a Research Scientist with SGT Inc. at NASA Ames Research Center for over seven years. Abhinav’s interests lie in developing PHM methods and algorithms with special emphasis on data-driven methods for practical prognostics. He has done extensive work on PHM performance evaluation, PHM requirements, and verification and validation of prognostics. He actively participates in several SAE standards committees, IEEE prognostics standards committee, and various PHM Society educational activities, and is a Fellow of the PHM Society. He is also the chief editor of International Journal of Prognostics and Health Management since 2011 and actively participates in organization of PHM Society conferences.

Dr. George Vachtsevanos is currently serving as Professor Emeritus at the Georgia Institute of Technology. He served as Professor of Electrical and Computer Engineering at the Georgia Institute of Technology from 1984 until September, 2007. Dr. Vachtsevanos directs at Georgia Tech the Intelligent Control Systems laboratory where faculty and students conduct research on PHM, CBM+, intelligent control of aerospace systems, novel fault-tolerant control technologies and their application to aerospace systems, industrial processes and unmanned autonomous systems. His research has been supported by government and industry. He is a board member of the Prognostics and Health Management Society. He has published over 300 technical papers and is the recipient of the 2002-2003 Georgia Tech School of ECE Distinguished Professor Award and the 2003-2004 Georgia Institute of Technology Outstanding Interdisciplinary Activities Award. He is the lead author of a book on Intelligent Fault Diagnosis and Prognosis for Engineering Systems published by Wiley in 2006.

Presentation Outlines

1. Introduction to Prognostics and Health Management

· Why the PHM Society?

· PHM – What and Why

· PHM Taxonomy View

· Standards for PHM

· Overview of the course

2. Requirements and Specifications for PHM at the Vehicle Level

  • Motivation
  • Requirements
  • Stages in Developing Needs

· Concept of Operations and Use Cases

  • Requirements Flowdown
  • Verification and Validation
  • References

· Conclusions with Case study to follow

3. PHM Metrics and Performance Evaluation

  • Introduction
  • Prediction Methods
  • Performance Metrics
  • A Working Example
  • Source of Errors in Prognostics
  • What Comparisons are Valid?

· Metrics Parameters

  • Conclusion

4. Diagnostics Methods

· Main Concepts in Model-based Diagnosis

· Examples: Model Based Diagnostic Design

  • Conclusion

5. Requirements and Specifications for PHM- Case Study

  • Problem Statement
  • Methods Investigated
  • Chosen Methods
  • Results and Impact
  • Further development
  • References
  • Conclusions

6. Monitoring and FDI Power Supply Subsystem – Case Study

· Problem – Failure of Power Supply Module

  • Solution Approach
  • Bond Graph Review

· Power Supply and Degradation Modeling

  • Experimental Study
  • Fault Detection and Isolation

7. Prognostics

· Prognostics Overview

· Prognostics and Reliability Analysis

· Prognostics and Decision making

· Estimation for Prognosis

· Dynamic nonlinear Models, Bayesian filtering and state estimation

  • Failure Prognosis

· Effects of measurement uncertainty, Feature growth. Analysis example

· Parameter Uncertainty

· Outer Correction Loop, Characterization of Future Use

  • Conclusions

8. Data-Driven / Analytics Methods

· Nature of PHM

· Feature Extraction

· Feature Selection

· Anomaly Detection

· Random Forest Anomaly Detection

· Diagnosis – Building a State of the Art System

9. Case Study: A Hybrid Approach to Bearing Spall Prognostics for Military Aircraft

  • Review of PHM
  • Engine System Prognosis Program
  • Data Collection
  • Spall Detection
  • Spall Modeling

· Size, Propagation, RUL estimation

  • Complete System

10. Case Study: Model-based Prognosis of End-of-Discharge and End-of-Life for Lithium-Ion Batteries in Electric Aircraft

  • Motivation
  • Modeling
  • Solution Approach
  • Experiments
  • Predictions including Uncertainty
  • End of Discharge, End of Life

11. Sensors and Sensing Strategies

  • Systems Background
  • Transducer Specifications
  • Example – Diesel Pump Station
  • Sensor Evolution
  • Conclusions

12. Analysis Mini Workshop

· Introduction and Objective: Plan the data elements of a PHM project

· Problem statement and grouping

· Within each group, identify a volunteer discuss a real-world PHM problem

· Work through the issues/questions in groups with facilitators

· Group presentations

13. CBM+ Technologies – An Overview

  • What is CBM+?

· Key components of CBM+

· CBM+ from a system perspective

  • Standards

· Prognostic considerations

14. Cost-Benefit Analysis for HUMS & CBM in the Civil Helicopter Market

· Benefit of HUMS & CBM Services

  • Specifics of the Commercial Helicopter Market
  • Cost Benefit Assessment
  • Examples
  • Concluding Remarks

15. Plenary Needs and Issues

  • PHM Needs
  • Discussion Issues

16. Reliability-Centered Life Cycle Management of Engineering Systems

  • Background
  • Motivation

· Technical Approach: Overview Architecture, Life Modeling, Model-based
Prognostics, Reliability Analysis, Life Decision Support

  • Challenges – Where do we go from here?

17. Fielded System Case Study: Li-ion Battery (LIB) System Lifecycle Management

  • Problem
  • Motivation
  • Technical Approach
  • Results and Impact

· Challenges – Where do we go from here?

18. Fielded System Case Study: Real-Time Fault Prediction and Avoidance for Commercial Aircraft Engines

  • Nature Of PHM

· The Approach: Data Fusion

  • Results
  • Classifier Evaluation

19. Fielded System Case Study: Stryker Brigade Combat Team Embedded Data Collection and Analysis System

  • Goals and Tasks

· Degradation Analysis and Failure Modes

  • Data Organization
  • Asset Readiness

· Global, Regional, Local, Unit, Platform

  • Fault Codes and Sensor Data
  • Conclusions

20. Mini Workshop

· Introduction with Objective: Plan the elements of a PHM project

· Problem statement and grouping

· Within each group, identify a volunteer to discuss a real-world PHM
problem

· Work through the issues/questions with facilitators

· Group presentations

21. Way Forward… Where do YOU go from here? Where do WE go from here?

    • PHM Needs
    • Way Forward
    • Why – Professional Development?
    • Basis for CPD Recognition- AMA?
    • Activity Types?
    • Way forward – Big picture
    • Discussion Issues?