Prof. Juan J. Alonso
Juan J. Alonso is the Vance D. and Arlene C. Coffman Professor and the James and Anna Marie Spilker Chair of the Aeronautics and Astronautics Department at Stanford University. Prof. Alonso is also the founder and director of the Aerospace Design Laboratory (ADL) where he specializes in the development of high-fidelity computational analysis and design methodologies to enable the creation of realizable and efficient aerospace systems. He is the author of over 300 technical publications on the topics of computational aircraft and spacecraft design, multi-disciplinary optimization, fundamental numerical methods, and high-performance parallel computing. During the period spanning 2006-09, Prof. Alonso was the Director of the NASA Fundamental Aeronautics Program in Washington, DC. In that position he was responsible for the entire portfolio of aerospace vehicle and vehicle technology research for the agency in the subsonic rotary wing, subsonic fixed wing, supersonic, and hypersonic regimes, with particular emphasis on the energy and fuel efficiency of the aviation enterprise and its environmental impact. Prof. Alonso is also the CTO and Co-founder of Luminary.ai, a startup company focused on leveraging GPU computing to revolutionize simulation-based analysis and design of engineered products through the use of Physics AI models.
Prof. Alonso is the recipient of several AIAA Best Paper Awards, the NASA Exceptional Public Service Medal, the NASA ARMD Associate Administrator Award, and the AIAA Stanford Chapter Professor of the Year award. Prof. Alonso has served in the NASA Advisory Council, the Secretary of Transportation’s Future of Aviation Advisory Committee, the FAA Administrator’s Management Advisory Council, and as an Independent Expert in the ICAO/CAEP fuel burn, noise, and emissions technology goals evaluation. Prof. Alonso and the ADL are responsible for initiating the development of the open-source SU2 analysis and design environment, intended for use by the worldwide community to advance the state-of-the-art in numerical optimization of problems governed by fluid flows. Prof. Alonso earned his Ph.D. in Mechanical and Aerospace Engineering at Princeton University and his B.S. degree at the Massachusetts Institute of Technology.
Day 1: Wednesday, September 9th | 09:00 – 09:45
Room: Opus
Title: Physics-informed AI/ML Models for Turbomachinery Design Including Experimental Data Assimilation
Speaker: Prof. Juan Alonso (Stanford University, USA)
Abstract:
The last two years have witnessed a surge in the acceleration in our ability to generate, curate, and use data for large-scale training of modern physics-AI surrogates. Additionally, physics-AI architectures are rapidly improving in their ability to accurately represent complex, industrially relevant geometries and associated physics. Extrapolating into the future, we must ask ourselves the question: “What does this mean for the future of aerospace engineering, including power and propulsion systems?” In this presentation, I will describe the evolving landscape of artificial intelligence and machine learning methods (AI/ML) as they relate to various applications in aerospace engineering, including design space exploration, optimization, uncertainty quantification, and data assimilation for digital twins. As key components of the successful use of AI/ML, we focus on the importance of accurate and mesh-independent predictions, the ability for these methods to quantify their own uncertainties so that they are able to, adaptively improve where needed, and the data assimilation capabilities (simulation + experiments + operations) to improve on the predictive abilities of these methods. I draw from recent examples in various applications, like SHIFT-CCA, a physics-AI model for external aerodynamics (including the flowpath for the propulsion system) for the U.S. Air Force’s Collaborative Combat Aircraft, and SHIFT-Pump, a model for the design optimization of compressors. Additional focus is placed on developing not just models, but an entire platform infrastructure that can automate and manage the entire lifecycle of data generation, data curation, model training, and model deployment at scale, including agentic features to decrease cycle time and enhance productivity.
Day 1: Wednesday, September 9th | 14:00 – 15:30
Room: Opus
Title: The AI/ML Ecosystem for Engineering Analysis, Design, and Control
Moderator: Prof. Juan Alonso (Stanford University, USA)
Panelists:
Ass. Prof. Michael Bauerheim (ISAE-Supaero, France), Prof. Xiaomo Jiang (Dalian University of Technology, China), Ass. Prof. Ricardo Vinuesa (University of Michigan, USA)
Abstract:
As data availability (from simulation, test, and operations) becomes more widely available, AI/ML-based methods for the analysis, design, and control of aerospace systems, including power and propulsion systems, are becoming more pervasive. But the pace of development is frenetic and the landscape of physics-informed and agentic AI/ML is changing more rapidly than we can keep up with. In this panel we tackle both the current state and 1-2-year predictions for the capability, accuracy, and cost for such methods. What are the most logical applications in engineering in the near term? What transformational capabilities do we expect in the next 5 years? What are the key bottlenecks to make this technology work in realistic industrial environments?
Prof. Juan J. Alonso
Stanford University,
USA
