Panel Sessions

The PHM Society provides an opportunity to hear and interact with recognized industry leaders in relevant areas for our PHM work. These 90 minute panel sessions will consist of presentations and open discussion by 4-6 panelists directly engaging with the conference audience on the different topics listed below.

These sessions add an enriching dimension to the conference experience and a welcome networking alternative to traditional paper presentations, which dominate some conferences. We believe balancing the conference time in this fashion provides participants a much more engaging experience and increased opportunity to gain unique knowledge.

Panel Session Topics:

  • PHM for Manufacturing: Assessing Operations to Advance PHM Capabilities
  • Joint AI Center Predictive Maintenance: PHM Projects and Lessons Learned
  • Natural Language Processing as a PHM tool
  • Unlocking the Potential of Automotive PHM
  • Cybersecurity and PHM: Challenges and Solutions
  • Predictions of Rare Events in very Complex Systems
  • Qualifying Data and Data Use—Integrity, Models, and Ownership
  • PHM for Space Applications
  • PHM Standards—Why are they important for your work and how to participate
  • Education and Professional Development—Workshopping a PHM Taxonomy
  • MRO / Hanger of the Future

Panel Committee Chairs:

Brian A. Weiss (National Institute of Standards and Technology)

Panel Session Details

PHM for Manufacturing: Assessing Operations to Advance PHM Capabilities
Lead: Brian A. Weiss (National Institute of Standards and Technology)

Description: Manufacturing has evolved over the last few decades to leverage emerging and advanced technologies. Many of these technologies enable the growth of PHM capabilities including the advancement of monitoring, diagnostics, and prognostics to enhance decision-making and maintenance strategies. Manufacturers recognize that these emergent PHM capabilities can enhance their maintenance strategy - optimize planned downtime and minimize unplanned downtime - to achieve more reliable, and ultimately, more profitable operations. For manufacturers to realize advanced PHM within their facilities, they face a challenging reality - How do they assess their PHM capabilities and the value it obtains? And, more importantly, what is the value they want to achieve and the corresponding PHM capabilities to be added?

This panel will focus on how manufacturers can assess their current PHM capabilities and how they can determine what levels of PHM are most desired by their organization. This will be paired with individual value propositions in terms of the expected return on investment of additional PHM capabilities along with a discussion of current maintenance expenses.

List of Panelists:
  • TBD



Joint AI Center Predictive Maintenance: PHM Projects and Lessons Learned
Lead: Maria Seale (US Army Engineer Research and Development Center)

Description: The US Department of Defense (DoD) Joint Artificial Intelligence Center (JAIC) was established in 2018 to enhance the ability of DoD components to research and launch new initiatives in Artificial Intelligence. Predictive Maintenance (PMx) was one of the inaugural National Mission Initiatives of the JAIC, due to its large-scale potential impact across multiple services. JAIC PMx launched its efforts in early 2019, with multiple, cross-cutting projects centered on predictive maintenance for rotorcraft. This considerable endeavor encompasses topics ranging from engine health modeling, to maintenance logbook data mining using natural language processing, to cross-correlation of flight and maintenance data for identifying factors relevant to component failure, and more. This panel will feature representatives from JAIC PMx and participating organizations to discuss PHM challenges in the current projects, and lessons learned for future applications.

List of Panelists:
  • TBD



Natural Language Processing as a PHM tool
Leads: Michael Brundage (National Institute of Standards and Technology) and Maria Seale (US Army Engineer Research and Development Center)

Description: Natural language documents often contain a wealth of knowledge that is becoming more accessible and analyzable with improvements in natural language processing (NLP) solutions. The out-of-the-box NLP solutions frequently perform well for general, non-technical documents with proper structure (e.g., literary books, news articles) or "big data" datasets (e.g., twitter or yelp). Technical documents, on the other hand, do not always exhibit these traits, often being "small" in size, as compared to "big data" datasets, and containing misspellings, domain specific jargon, abbreviations and non-standard sentence structure. However, these documents frequently contain important insights that remain hidden because the out-of-the-box solutions perform poorly on unstructured, technical data. There is a need for new technical language processing (TLP) solutions that adapt current NLP solutions for the maintenance domain.

As an example, extracting information from maintenance work orders (MWOs), where a record is created each time maintenance work is performed on an asset in an industrial environment has proven successful. Each record contains a short statement of the problem and/or the work required and/or work done. These MWOs contain all of the problems of technical documents: unstructured format with misspellings, domain specific jargon, and abbreviations, but the MWOs are also unique because the maintenance domain has a relatively small corpus of terms and subsequent meanings as compared to the general English language.

This panel will look into different TLP solutions for extracting data out of different technical documents by learning from and adapting current NLP solutions for maintenance.

List of Panelists:
  • TBD



Unlocking the Potential of Automotive PHM
Lead: Steven W. Holland (VHM Innovations, LLC)

Description: The automotive industry has proven to be one of the most fertile application domains for PHM technology in terms of financial impact, analytics sophistication and sheer scale. Successful examples have been implemented for both manufacturing systems and the automotive vehicles, themselves. The case has been made for even greater opportunity in coming decades as the continuing electrification of vehicles takes place. Similarly, the potential impact for fleets is anticipated to be huge. This applies to conventional automotive and trucking fleets as well as for future autonomous fleets. But, the pace of PHM introduction continues to lag behind what it might be. This panel seeks to understand the key enablers for recent industry successes as well as the barriers that have limited more rapid progress. The discussion will be centered on strategies that effectively exploit those enablers while mitigating the barriers.

List of Panelists:
  • TBD



Cybersecurity and PHM: Challenges and Solutions
Leads: Timothy Zimmerman (National Institute of Standards and Technology) and Radu Pavel (TechSolve)

Description: PHM systems, along with numerous other systems and technologies, were not inherently designed with cybersecurity in mind. These types of systems must be protected from vulnerabilities that may arise as a result of their increased connectivity, use of wireless networks and sensors, and the wide distribution of sensitive PHM data. Exacerbating the problem, especially in the industrial process control domain, is the potential for negative performance impacts resulting from the integration of common cybersecurity technologies into existing systems. Internet of Things (IoT)-based PHM provides its own set of unique security challenges including data integrity, data leakage, privacy, and the potential for unauthorized access.

This panel will explore the fusion of cybersecurity and PHM, how to enable secure operation of PHM systems while maintaining system performance, and discuss the integration of existing cybersecurity standards and guidance on PHM systems. The panel also seeks to understand specific cybersecurity challenges faced by operators of PHM systems and their potential solutions.

List of Panelists:
  • TBD



Predictions of Rare Events in very Complex Systems
Leads: Dnyanesh Rajpathak (General Motors), Yilu Zhang (General Motors), Ian Gibbs (General Motors), and Wei Tong (General Motors)

Description: No industry is immune to serious product defects while at the same time all industries learn valuable lessons from them. Given the complex nature of systems, events may occur that do not fall within valid operation and performance, leading to (un)known risks which significantly impact consumers (and in some cases human lives). As the space of modern equipment becomes complex, organizations collect vast amounts of data concerning their products. Some influential instances include social media data, design specifications data, image data, warranty and repair data, flight data, telemetry data, manufacturing data, and so on. Hints from the data frequented by customers are a viable resource to learn early signals of potential problems. Even when constrained to a specific domain there is significant variance in the type of data, methods of collection, and differential likelihood of data containing a signal for a rare issue.
A substantial challenge is faced (by traditional approaches) at accurately detecting rare, but high impact emerging signals by limiting false alarm rates. Preempting and quickly reacting to potential emerging issues due to rare events through their quick detection and isolation of failure modes help to limit an adverse impact on consumers.

This panel will bring together a diverse group of speakers from industry, research center, and academia to explore the barriers, challenges, and provide insights into efficient and effective identification of rare events. With our panelist and audience participation we hope to address:

  • How to realize whether a signal truly represents a rare event?
  • How can we characterize a rare event from different application domains and industries?
  • What are the common and unique characteristics of rare events observed in different industries?
  • As system complexity increases, such as with autonomous vehicles in the automotive industry, how can we better identify novel rare events?
  • What methods, practices, and challenges that are related in collecting high quality, noise free data in predicting rare events?
  • Effective utilization of disparate data and heterogenous data types (e.g. (un)structured text data and sensory or signal data) in prediction of rare events.
  • Given that there are varying degrees of measurement and selection biases observed around the data, what approaches help determine whether a signal truly represents an emerging fault?
  • Mechanisms causing such events typically involve non-linear systems with highly complex physics. How might one measure effectiveness of features considered to limit false alarm rates?
List of Panelists:
  • TBD



Qualifying Data and Data Use—Integrity, Models, and Ownership
Lead: Michael Sharp (National Institute of Standards and Technology)

Description: PHM Reliable information and data are the foundations of the PHM philosophy. Qualifying that data and how it is used builds trust in end users and provides expectations and limits with developers and solution providers. Understanding information, such as where the data comes from and how it can be used, is integral to the creation of viable models and trustworthy information capable of providing actionable decision support. This panel seeks to discuss the mechanisms for qualifying data collection, documentation, and use as it applies to specific domain applications within the PHM community. Although some qualifications of data are agnostic of application, others questions such as ‘how much data do I need’ or ‘is this an acceptable level of uncertainty’, can only be answered within the context of the end goals and application. The goal of this panel is to present and discuss mechanisms for measuring quality of collection, use, and return on investment for data and any associated models primarily with current goals in mind, while leaving room for potential expansion in the future.

Topic Areas:

  • Data Qualification: Establishing trust and expectations within the data
    • Data Collection
      • What is considered ‘Big Enough’ data in context of a given PHM application
    • Data Provenance
      • Documenting data for use beyond its original intent
    • Managing information from unreliable sources
      • Human agents, Natural Language Processing (NLP), Etc.
    • Quantifying and propagating uncertainty within a data stream
      • Sensor noise, process noise, model misspecification, etc.
  • Data Utilization Qualification: Understanding ROI for data applications
    • Qualifying Data Driven AI and Other ‘Black-Box’ Solutions for PHM
      • Designing actionable KPIs
    • Identifying Measurable Outcomes of Data Driven Solutions
      • Justifying continued support for PHM technologies
    • Public Benchmark Datasets
      • Utilizing and contributing open information for competitive advantage
List of Panelists:
  • TBD



PHM for Space Applications
Leads: Derek DeVries (NGC) and Andrew Hess (The Hess PHM Group)

Description: The planned use of manned and long-term crewed space platforms, as well as quick to launch and reusable space vehicles, is increasing at a very accelerating rate. After the legacy NASA developed Space Shuttle and LEO ISS; among many things, there are near term NASA plans for: a lunar Gateway station, a permanent lunar base, asteroid present, and Mars bases. Vehicles and platforms to accomplish these far reaching goals will include: crewed space and surface based stations and habitats; various types of launch, long range transportation, and orbit to surface vehicles; and all kinds of support subsystems and technologies. Beside NASA and other government directed organizations; commercial based entities are aggressively developing systems to achieve these same and additional space related goals. These commercial focused applications include tourist to space and LEO, space based hotels, and lunar and deep-space resource mining. This panel will focus on issues and challenges associated with these applications; and how PHM capabilities can be applied to reduce risks, increase efficiencies, and ensure resilient sustainment of these vehicles, platforms, habitats, and systems.

List of Panelists:
  • TBD



PHM Standards—Why are they important for your work and how to participate
Lead: Jeff Bird (TECnos)

Description: The PHM Society mission emphasizes free and unrestricted access to PHM knowledge, promotion of interdisciplinary and international collaboration in PHM and leading the advancement of PHM as an engineering discipline. Standards need to be seen and readily used by the PHM community as enablers for development and implementation of PHM technology. The extensive and long-term work by a wide variety of Standards Developing Organizations like ASME, IEC, IEEE, ISO, NIST, SAE, SCC is essential but perhaps not accessible by new and even seasoned members of our community. From the PHM18 panel, “there must be hundreds of standards applicable in PHM”. A review last year looked at standards in a digital age.

The panel format will be a review and discussion for standards impact: Reviewing the Society standards information portal content- as a start on what products and coordination the Society can provide to make PHM standards enablers for your work. We will discuss your questions like: What are some success stories? How to get involved in the development and review of evolving guidelines, best practices and standards? How users and smaller organizations participate? How are the community’s pain points shared? What should the Society’s role be- Requests for Concepts, Portal, Success Stories, Gap Analysis? Completion of these objectives will be planned within the Standards User Group established in the Society.

List of Panelists:
  • TBD



Education and Professional Development—Workshopping a PHM Taxonomy
Leads: Jeff Bird (TECnos) and Karl Reichard (Penn State University)

Description: The PHM Society mission emphasizes free and unrestricted access to PHM knowledge, promotion of interdisciplinary and international collaboration in PHM and leading the advancement of PHM as an engineering discipline. ‘Products’ for PHM education and professional development accessible to the whole community contribute to all of these aims (see the Society EPD information portal at www.phmsociety.org/publications ). The PHM Taxonomy under development offers a common basis for understanding PHM domains, and skill levels and advancement. The PHM Continuing Professional Development Guidelines offer personal and organizational career planning and enhancement for the PHM community as a whole.

This workshop format will validate and advance the scope, content and applications of these two products to serve the widest domains of PHM and its stakeholders. Draft versions of the products will be made available in advance through updates to the existing PHM Society forums and building on the proceedings of last year’s panel at.

Completion of these tools will be planned within the EPD User Group established in the Society.

List of Panelists:
  • TBD



MRO / Hanger of the Future
Lead: Frank Zahiri (U.S. Air Force)

Description: The key focus for the PHM MRO Sector panel will be on the capabilities for an integrated aircraft sustainment process in order to enhance and increase customer support. The panel will include experts in life cycle management, product support, supply chain management, and maintenance services. They will bring expertise in the area of improving aircraft availability and reduction of associated costs thru MRO/Hanger of the Future. Collaboration on key elements in the sustainment process is essential and can be achieved by integrating with an optimized supply chain process thereby driving efficiencies. The speed at which aircraft move through the hanger results in higher availability. This examination of the processes which impact aircraft maintenance , include maintenance production execution, maintenance planning and optimization, asset health and performance monitoring, supply chain and logistics. Driving digital transformation on the shop floor (digital factory), modelling (combine data-driven and physics-based), quality and test will be presented to support execution of maintenance, repair, overhaul, modifications/retrofit, and modernization of processes.

List of Panelists:
  • TBD
  
 
 
 

follow us

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