Future Mobility Panel
Chair: Ryan Walker (Mercedes)
Temporary Title: Future Mobility: Synergies and perspectives
What the different mobility industries learn from others?
Challenges and opportunities in increased connectivity on reliability
How will automation advances impacting CM/CBM/PHM in each mobility?
What each mobility aspire to?
Greg Rapson, Head of Systems Engineering, Mercedes F1
Vincent Gros, Senior Expert Maintenance Operations, Airbus
Rolf Claude, Head Engineering Services – RAM/LCC, Stadler Service AG
Technical Language Processing Panel
Chair: Melinda Hodkiewicz, University of Western Australia
Title: Natural Language Processing, Knowledge Graphs and Ontologies
Topics: Discussion with the authors of the special session with focus on the following questions:
Why did you choose this use case for TLP, what was the value for industry?
What were the main challenges in developing your pipeline?
What were or do you anticipate the challenges in deployment to users?
Matteo Iannitelli, Data Scientist and Analytics Engineer, GE Oil & Gas
Maria Vatshaug Ottermo, Research Scientist, SINTEF Digital
Tyler Bikaun, University of Western Australia
Prof. Piero Baraldi, Politecnico di Milano
Standards in PHM Panel
Chair: Jeff Bird, PHM Society Standards Committee, TECnos, Canada
Title: Explainable Standards for Explainable Prognostics and Health Management
How can innovation, sustainability, business case rationalization and trustworthiness be boosted by standards and best practices?
How can best practices and standards be more accessible and responsive to all parts of the research, development, commercialization and asset management value chain?
How do ‘new’ technology domains like AI and machine learning benefit from or challenge more traditional PHM practices for explainability and standards?
Invited- Rolls Royce Service Integrity and Aletheia Framework
Dr. Danilo Giordani, Politecnico di Torino
Prof Yvonne Lu, University of Oxford
Dr. Gabriel Michau, Stadler Rail
Deep Learning Panel
Chair: Neil Eklund, Palo Alto Research Center (PARC), USA
Title: Applied Deep Learning
Topics: “Industry 4.0” promises to merge advanced production and operations techniques with smart digital technologies to transform how parts and products are designed, made, used, and maintained. One key enabler of this industrial revolution be predictive maintenance, which allows asset owners to reduce secondary damage and unscheduled downtime. As the amount of asset data available continues to explode, deep learning is likely to play a central role in PHM. This panel will focus on the practical application of deep learning in PHM, and will be very interactive, with plenty of opportunity for questions from the audience.
Xiang Li, University of Cincinnati
Anarta Ghosh, United Technologies Research Center
Cees Taal, SKF
PHM Methodology and Reliability Panel
Chair: Zhimin Xi (Rutgers, The State University of New Jersey, US)
Title: PHM Methodology and Model Reliability
There are a variety of PHM modelling methods such as physics-based, data-driven, hybrid, and deep learning. What are general guidelines to use these methods?
What are potential problems for these methods?
How to access the model credibility or validity?
When predicted lifetime or failures are wrong, is this the PHM method problem or due to the uncertain nature?
If the PHM model is not accurate, are there ways to diagnose the model reliability?
Dr. Michael H. Azarian (CALCE, University of Maryland, US)
Dr. Diganta Das (CALCE, University of Maryland, US)
Dr. Pierre Dersin (PHM Director, Alstom)
Dr. Kamal Medjaher (Professor, Tarbes National School of Engineering, France)