Session: 01-05-01: Applications of Artificial Intelligence/Machine Learning for Aerospace Structures

Paper Number: 135792

135792 - Geometric Intelligence and Design Informatics for Advanced Materials, Structures, and Manufacturing 

Innovative materials discovery and functional device development often involve the inverse design problem: how to achieve desired performance by deriving the optimal design? A fundamental challenge herein is how to abstract the physical systems and represent them heterogeneously at nano-, micro-, and macroscopic scales to conduct further design optimization. In the era of big data, my research goal is to reveal the structures of intelligence of materials in multiscale by leveraging geometry, topology, and machine learning. By creating geometric computational representations, I propose integrating design theory with geometric intelligence to form design informatics, which can be further exploited to accelerate design generation and implement design automation. In this talk, I will introduce our recent work in design informatics, including design representations and design optimization and its applications in advanced materials and structure design, as well as design for additive manufacturing. Firstly, I’ll present the foundations of geometric representations and manifold learning. Secondly, I’ll present recent work on the data-driven inverse design of mechanical metamaterials and shape-morphing materials. Lastly, I’ll present the computational design optimization framework, design for additive manufacturing paradigm, and their applications in aerospace ultralight and high-strength aerospace parts design.

Presenting Author: Jida Huang University of Illinois

Presenting Author Biography: Dr. Jida Huang is an Assistant Professor in the Department of Mechanical and Industrial Engineering at the University of Illinois at Chicago, where he directs the Design Reasoning and Evolution for Advanced Manufacturing (DREAM) lab. DREAM lab focuses on geometric data analytics and design informatics for advanced materials and structures to elucidate materials architecture-process-property relation spanning the nano-, micro-, and macro-scales. DREAM lab develops computational approaches for design and fabrication problems occurring in the entire product lifecycle, from early-stage conceptual design to design modeling, simulation, realization, and final fabrication, with the mission of tackling societal challenges in healthcare, energy, and climate change. Dr. Huang received his Ph.D. in Industrial and Systems Engineering in 2019 from the University at Buffalo, State University of New York, where he received presidential fellowship and Graduate Student Researcher of the Year 2018. He also received the best paper award at IDETC/CIE 2021, hosted by the American Society of Mechanical Engineers. He gratefully acknowledges prior and current support from NSF, NASA, and Illinois Innovation Network.