PROGRAMME
DIVISIONS
- All Divisions
- Built Environment and Engineering Design (BE)
- Basic Science (BS)
- Chemical Engineering and Material Science (CM)
- Environment and Energy (EE)
- Electrical/Electronics Engineering & Information Engineering (EI)
- Life Science & Health (LH)
- Mechanical and Aerospace Technology (MA)
- Medical Science & Engineering (ME)
- Marine and Ocean Engineering (MO)
- Nuclear & Fusion Technology (NF)
- Women in Science & Technology (WS)
- Multidisciplinary Research (MR)
Mechanical and Aerospace Technology (MA)
The Mechanical & Aerospace Division brings together European and Korean researchers, engineers, and industry leaders to address how artificial intelligence is reshaping the future of mechanical and aerospace engineering. The division covers a broad spectrum of topics united by a common theme: the integration of AI and data-driven approaches into the design, manufacturing, operation, and lifecycle management of complex engineered systems. Applications span widely, including robotics, space systems, production plants, air/ground/water vehicles, infrastructure, medical systems, and more.
Please explore the diverse and extensive sessions under preparation. Both methodological and application-driven presentations are welcome.
Programme Committee
PROF. LEE, Jaemin (이재민)
University of Leeds
DR. LEE, Juseong (이주성)
Eindhoven University of Technology
| Date / Time | 2026-07-21 09:00 -- 10:30 |
|---|---|
| Room | |
| Conveners / Chairs |
|
| Synopsis | This session explores how the next phase of space activity (high-cadence launch, large constellations, and expanding in-orbit infrastructure) is evolving into a true space mobility ecosystem. The session brings together academia and industry to discuss how AI-empowered technologies enable safer and more efficient operations, unlock new mission concepts, and support sustainable growth by addressing orbital debris and the environmental impacts of launch and reentry.
Topics:
• AI for Space Situational Awareness (SSA) and Space Traffic Management (STM)
• AI-driven component design
• In-orbit servicing and robotics
• In-sapce laboratory / In-space data center
• Lunar habitat
• Space debris mitigation and active debris removal (ADR)
• Environmental impacts of spaceflight caused by launch emissions, atmospheric chemistry, and reentry by-products
• Sustainable propulsion and “green” propellants
• Standards and governance for sustainable space
|
| Speakers |
|
| Date / Time | 2026-07-22 13:30 -- 15:00 |
|---|---|
| Room | |
| Conveners / Chairs |
|
| Synopsis | This session is a MA-led session within the Advanced Mobility in the AI Era series, complementing parallel tracks in BEED and EI. The session broadens “Mobility” beyond autonomous vehicles to include movement technologies across scales, e.g., from AI-optimized components and products (e.g., shoes, wearables, and assistive devices) to robots, vehicles, and intelligent transportation systems. After invited talks, the session transitions to a roundtable designed to interrogate not only what AI enables, but what mobility should ultimately deliver for people.
In a conference oriented toward AI-driven futures, this session intentionally asks a counter-question: when “smart autonomy” becomes the default, what should remain deliberately “manual” or even “unsmart”? The roundtable will potentially challenge automation-first assumptions by focusing on what is worth preserving about driving and choice, e.g. joy, agency, identity, and the freedom to move, and how such values can be expressed as concrete engineering constraints rather than vague ideals. It will also examine how optimization and automation redistribute benefits and burdens across different user groups (drivers, passengers, pedestrians, and communities), and who gets to define the objectives, trade-offs, and acceptable risks in AI-enabled mobility systems. |
| Speakers |
|
| Date / Time | 2026-07-21 13:30 -- 15:00 |
|---|---|
| Room | |
| Conveners / Chairs |
|
| Synopsis | The aeronautics industry is experiencing a significant transformation, driven by the global demand for efficient and sustainable aviation. Traditional aircraft development strategies must evolve rapidly to meet ambitious environmental targets, such as net-zero emissions. Artificial Intelligence (AI) plays a pivotal role in this shift by introducing methodologies that enhance aircraft performance and operational safety. Nevertheless, integrating AI into safety-critical aerospace applications poses distinct engineering and regulatory challenges that require rigorous evaluation and adaptation.
This session aims to explore the expansive integration of AI across all aspects of aeronautical research and development. The objective is to foster cross-disciplinary dialogue on how AI and data-driven modelling can solve complex aerospace engineering problems. We invite researchers, engineers, and industry leaders to present cutting-edge research that demonstrates how AI is accelerating technological advancements and shaping the next generation of flight.
Key topics of interest in this session include, but are not limited to:
• Leveraging AI for the comprehensive conceptual design and system integration of next-generation aircraft configurations.
• Accelerating the development and optimisation of lightweight structures through AI.
• AI-driven material discovery and performance prediction for advanced aerospace applications.
• AI applications in the optimisation and testing of sustainable propulsion systems, including high-density battery packs and hydrogen fuel cells.
• Application of generative design and machine learning algorithms for aerodynamic shape optimisation of diverse aircraft configurations.
• The role of Findability, Accessibility, Interoperability, and Reusability (FAIR) data infrastructures and ontologies in enhancing collaboration and interoperability within aeronautical research. |
| Speakers |
|
| Date / Time | 2026-07-21 15:30 -- 17:00 |
|---|---|
| Room | |
| Conveners / Chairs |
|
| Synopsis | The rapid digitalization and electrification of mechanical and aerospace systems has significantly increased system autonomy, complexity, and interconnectivity. As cars, aircraft, industrial assets, manufacturing lines, and cyber-physical systems become increasingly automated, ensuring their safety, reliability, and quality becomes ever more crucial. This session aims to explore how artificial intelligence (AI) and data-driven approaches can fundamentally reshape asset management, maintenance decision-making, and system assurance in safety-critical domains.
Recent advances in AI-based fault detection, diagnostics, and prognostics have enabled earlier and more accurate identification of anomalies in mechanical systems. Prognostics and Health Management (PHM) frameworks now leverage machine learning, deep learning, and hybrid modeling to estimate Remaining Useful Life (RUL) and predict degradation trajectories. In parallel, maintenance optimization strategies—such as condition-based maintenance, predictive maintenance, and opportunistic maintenance—are increasingly integrated with AI to support economically and operationally optimal decisions. Reliability analysis, safety certification, and risk assessment are also being revisited in light of IoT-sensored components and autonomous systems.
However, applying AI in Safety, Reliability, and Quality engineering presents domain-specific challenges. First, data in safety-critical systems is often highly imbalanced, with rare failure events and limited fault examples. This imbalance challenges conventional training paradigms and demands advanced methods for robust learning under sparse and skewed data distributions. Second, while numerous studies demonstrate machine learning applications at the component level, the integration of AI models across system-, process-, and industry-level architectures remains underexplored. Bridging these levels requires coherent system modeling, digital twins, and hierarchical decision frameworks. Third, Safety, Reliability, and Quality domains require explainability, trustworthiness, and certifiability. Black-box models are insufficient in safety-critical contexts. AI must be developed in conjunction with physics-based knowledge, an understanding of system architecture, and established reliability engineering principles. Physics-informed learning, hybrid modeling, interpretable AI, and uncertainty quantification are therefore essential to ensure that AI-driven decisions are transparent, verifiable, and aligned with safety standards.
This session invites a variety of research that explores, but is not limited to:
• AI-based fault detection, diagnostics, and prognostics
• Prognostics and Health Management (PHM) of mechanical and aerospace systems
• Reliability analysis, safety certification, and risk assessment for AI-enabled systems
• Maintenance optimization under uncertainty
• Novel maintenance concepts (condition-based, predictive, opportunistic maintenance)
• Learning under imbalanced and scarce failure data
• Integration of physics-informed AI and system-level modeling
By bringing together researchers and practitioners from mechanical engineering, aerospace systems, industrial engineering, and AI, this session seeks to advance a unified vision of trustworthy, explainable, and system-integrated AI for the next generation of safe and reliable engineered systems.
|
| Speakers |
|
| Date / Time | 2026-07-21 17:00 -- 2026-07-22 18:30 |
|---|---|
| Room | |
| Conveners / Chairs |
|
| Synopsis | The accelerating transition toward climate neutrality and circular industrial systems requires a fundamental rethinking of how products are designed, manufactured, used, and reintegrated into material cycles. As global supply chains experience mounting pressure from resource scarcity -particularly in critical raw materials essential for batteries, renewable‑energy systems, and advanced electronics- the need for intelligent, resilient, and sustainable lifecycle strategies is becoming a core requirement for industrial competitiveness. The European Union’s Digital Product Passport (DPP), introduced under the Ecodesign for Sustainable Products Regulation (ESPR), reflects this shift by mandating comprehensive transparency regarding material composition, environmental footprint, durability, repairability, and recyclability across the entire product lifecycle.
Artificial intelligence is emerging as a transformative enabler of this transition. AI‑assisted Life Cycle Assessment (LCA) accelerates sustainability evaluations, improves data accuracy, and enables near‑real‑time monitoring of environmental performance. Digital twins -virtual representations of products, factories, and recycling systems- support
continuous simulation and optimization, and are increasingly applied to energy‑ and material‑intensive processes. In battery recycling, for instance, digital‑twin‑enabled process optimization has been shown to enhance recovery rates, reduce emissions, and improve overall resource efficiency, demonstrating how AI‑supported circularity can convert sustainability goals into concrete economic value.
At the center of circular product lifecycle management lies the R‑strategy framework. This includes Refuse, Rethink, Reduce, Reuse, Repair, Refurbish, Remanufacture, Repurpose, Recycle, and Recover, offering a structured pathway for extending product life and keeping materials in circulation. AI strengthens each step of this framework: it supports eco‑design strategies that minimize material demand, predicts component failures to enable earlier repair, identifies candidates for reuse and refurbishment, optimizes remanufacturing operations, and enhances the precision and efficiency of recycling and recovery systems. When combined with digital‑traceability infrastructures such as the DPP, R‑strategies become more actionable, measurable, and economically compelling.
The economic dimension is increasingly a driving force for adoption. Automated LCA pipelines reduce compliance and reporting costs, AI‑enhanced predictive maintenance decreases downtime and extends equipment life, and optimized remanufacturing and recycling processes recover high‑value materials, reducing exposure to volatile global markets. For companies in electronics, mobility, and machinery sectors, AI‑enabled R‑strategies lower lifecycle costs, unlock new service‑based business models, and strengthen resilience against geopolitical disruptions in critical‑materials supply chains. Implementing AI‑driven circularity requires coordinated steps across technological, organizational, and regional boundaries. Industries must establish interoperable data infrastructures aligned with DPP requirements, integrate AI‑enhanced LCA tools into design and engineering workflows, deploy digital twins across manufacturing, remanufacturing, and recycling processes, and use resulting insights to develop new circular business models such as component‑as‑a‑service or closed‑loop recycling partnerships. Close collaboration between European and Korean stakeholders is essential to harmonize standards, share lifecycle data, and co‑develop scalable solutions for resource‑intensive high‑tech sectors.
This session brings together European and Korean experts to explore how AI‑enabled lifecycle management, R‑strategy integration, and digital traceability can jointly address sustainability and resource scarcity. Through case studies and cross‑regional perspectives, the session will highlight scientific advances, industrial applications, regulatory developments, and strategic pathways for building product ecosystems that are low‑carbon, circular, economically viable, and resilient to critical‑materials constraints. |
| Speakers |
|
_20260406140557.jpg)
| Date / Time | 2026-07-22 09:00 -- 10:30 |
|---|---|
| Room | |
| Conveners / Chairs | |
| Synopsis | Numerical simulation has been widely used to solve scientific and engineering problems such as in solid mechanics, fluid dynamics, aeronautics, biomechanics, etc. Its accuracy, efficiency, and applicability are continuously being improved by advancing the computing power and numerical methods such as finite element method (FEM), finite difference method (FDM) and boundary element method (BEM), and so on. Nowadays, very complicated problems have been solved such as crash, fluid-solid interaction, multi-disciplinary problems.
High-tech systems become more and more complex and the need to couple different processes of life cycle (design, manufacturing, recycling) to reduce product cost and to protect the environment. In this challenge, the digital twin is a promising concept for system optimization and behavior prediction, which is a detailed digital representation accurately reflecting existing physical systems. To realize digital twins, the role of numerical simulation is crucial. It needs to be conducted accurately and efficiently by fitting with real-time sensor data in the collaboration of machine learning (ML) and internet of things (IoT) technologies. Therefore, it is clear that advances in numerical simulation are required towards multi-physics-multi-scale simulations, and its significance will increase more and more. Consequently, the digital twins will be the ultimate solution for the life cycle management of complex physical systems, improving sustainability.
In this session, the following topics are expected with applications of
• Multidisciplinary analysis and optimization involving the interaction of different fields, for example, fluid mechanics, solid mechanics, and thermodynamics.
• Advanced analytics, including uncertain quantifications, statistical analysis, machine learning and data mining.
• Conceptual modeling and motional prediction of complex products including aerospace, automotive, biomechanics, and so on.
• Systematic modeling and simulation of the manufacturing process, virtual testing process, vehicle motion in traffic flow, etc.
• Challenges and Limitations of current numerical methods.
From this session, it is expected that the latest status of the numerical simulation method and its application to various applications will be discussed with engineers and scientists working in mechanical and aerospace engineering. Also, sharing application examples to innovative and future products will be welcome. |
| Speakers |
|
| Date / Time | 2026-07-22 13:30 -- 15:00 |
|---|---|
| Room | |
| Conveners / Chairs |
|
| Synopsis | This session focuses on advances in structural design and optimization aimed at enabling new and enhanced functionalities in mechanical and aerospace systems. Modern structures are increasingly expected to deliver tailored responses—mechanical, thermal, acoustic, and multi-physical—while remaining lightweight, manufacturable, and reliable. The session welcomes contributions spanning fundamental methods, computational tools, and application-driven demonstrations across scales, from micro-architected materials to full-scale components.
Topics of interest include (but are not limited to):
• Metamaterials and architected materials: mechanical/acoustic/thermal metamaterials, lattice structures, programmable and multi-stable systems, topology-enabled functionalities
• Smart and adaptive materials/structures: shape memory alloys/polymers, piezoelectric and magneto-active systems, morphing structures, self-sensing and self-actuating designs
• AI-driven and data-informed design: generative design, surrogate modeling, physics-informed ML, inverse design, multi-fidelity and active learning strategies
• Optimization methodologies: topology/shape/sizing optimization, multi-objective and multidisciplinary optimization, design for manufacturability (incl. AM constraints)
• Robust and reliability-based design: robust optimization under uncertainty, sensitivity analysis, probabilistic design, worst-case and risk-aware optimization
• Experimental validation and deployment: digital twins, rapid prototyping, validation of optimized designs, certification-relevant considerations for aerospace applications
Overall, this session aims to connect researchers and practitioners developing the next generation of functional structures—linking theory, computation, and validation—to enable innovative mechanical and aerospace technologies. |
| Speakers |
|
| Date / Time | 2026-07-22 15:30 -- 2026-07-31 17:00 |
|---|---|
| Room | |
| Conveners / Chairs |
|
| Synopsis | The rapid evolution of Artificial Intelligence is moving beyond digital systems into the physical world, giving rise to a new paradigm often referred to as Physical AI. The Physical AI is an intelligence embodied in machines that perceive, reason, and act within real-world environments. Robotics serves as the primary platform for realizing Physical AI, transforming abstract algorithms into AI-powered robotic systems that interact with matter, energy, and human society.
This session aims to explore the foundations, methodologies, and applications of AI-powered Robotics. It will bring together researchers and practitioners from mechanical engineering, robotics, AI, control systems, and applied sciences to discuss how intelligent algorithms and physical systems can be co-designed for optimal performance and resilience.
Key themes may include:
• Embodied intelligence and learning in physical systems
• AI-integrated mechanical design and digital twin technologies
• Adaptive motion planning and real-time control
• Human–robot collaboration and safety in dynamic environments
• Applications in smart manufacturing, energy systems, healthcare, aerospace, and infrastructure
AI-powered robots represents the next frontier of the AI-driven future of science and technology, bridging digital intelligence with societal needs, translating data-driven insights into measurable physical outcomes. This session welcomes researchers and industry experts from Europe and Korea to share insights. Through this session, we foster interdisciplinary dialogue on how AI-powered robotics can redefine engineering, accelerate scientific advancement, and create sustainable technological ecosystems. |
| Speakers |
|
