Panel Session Topics
Panel Session 1
| Full Flight Sensor Data sharing within the stakeholders of PHM | |
| Organizer | Masaru (ken) Nishiwaki (ANA) |
| Panelists | 1. Darren Macer (Boeing) 2. Gavin Chew (Collins Aerospace) 3. Sebastian Lang (Lufthansa Technik) 4. Manabu Tono (ANA) |
| Abstract | In case of Prognostics & Health Management (PHM) for commercial airplanes, gigabytes of Full Flight Sensor Data have to be collected, distributed and analyzed within the stakeholders immediately so that the outcome of the PHM can be provided in a timely manner. In this panel session, attendees will have an opportunity to hear about how the sensor data can be shared and analyzed efficiently to support airline operations. Panelists: Airplane OEM (Boeing), Component OEM (Collins Aerospace), MRO (Lufthansa Technik) and Airline (ANA) Possible topics: 1. Challenges to share the Full Flight Sensor Data within the stakeholders under certain policies (Ownership of the data, Restriction of sharing, etc.) of each entity 2. Technical challenges to distribute, aggregate and analyze the gigabytes of data in a timely manner 3. Opinions against “Concept of Centralized Data” (Common data center in the aviation industry) to explore more potential utilizing Full Flight Sensor Data (Point of view: Data anonymization, Data Aggregation, etc …) 4. Others |
Panel Session 2
| Quantum Computing meets PHM | |
| Organizer | Ken Ueno (Toshiba), Seiji Tsutsumi (JAXA) |
| Panelists | 1. Noriaki Shimada* (IBM Quantum/IBM Research) 2. Nobuyuki Yoshikawa* (Mitsubishi Electric) 3. Takao Tomono* (Toppan Inc.) |
| Abstract | This panel discussion aims to gather leading experts in the field of quantum computing on PHM to share their insights, discuss recent developments, and predict future trends in this rapidly evolving field. Participants will explore the transformative potential of quantum computing and how it can revolutionize the PHM. We will delve into real-world applications, discussing the challenges and opportunities associated with harnessing quantum capabilities for health prognostics and system maintenance. Possible topics: 1. Introduction to Quantum Computing: A basic overview of quantum computing, its principles, and its applications. 2. Quantum Computing in PHM: An exploration of the impacts of quantum computing on PHM. 3. Challenges and Opportunities: A discussion on the technical and logistical challenges associated with integrating quantum computing into PHM systems, as well as the opportunities it presents. 4. Case Studies: Presenting real-life examples of quantum computing applications in PHM, demonstrating its effectiveness and potential benefits. 5. Future Perspectives: An open discussion about the future of quantum computing in PHM, including potential advancements, trends, and implications. |
* invited
Panel Session 3
| Predictive Maintenance Challenges and Solutions: Vendor Insights | |
| Organizer | Michio Inoue (MathWorks) |
| Panelists | 1. Byeng Dong Youn* (ONEPREDICT) 2. Chris Stecki* (PHM Technology) 3. Eric Bechhoefer* (GPMS Inc) 4. Rachel Johnson* (MathWorks) |
| Abstract | In this panel session, attendees will have the opportunity to hear from leading predictive maintenance software vendors and solution providers. They will discuss the challenges and opportunities in a variety of industries, provide insights on the latest innovations, and offer practical advice for successful implementation. Possible topics: 1. Provide a brief overview of your company and predictive maintenance products/services. 2. What do you believe are the biggest challenges facing organizations who want to implement predictive maintenance solutions today? 3. How do you handle situations where the data may not be available? 4. What techniques have you found to be most effective for designing predictive maintenance algorithms? 5. Can you share an example of a successful implementation, and the value it provided to your customer? 6. What do you see as the next frontier for innovation in predictive maintenance? 7. What advice would you give to companies considering implementing a predictive maintenance solution? |
* invited