CEEM Seminar | Jessica Zhang | Carnegie Mellon University
From neurological disorders to additive manufacturing: integrating isogeometric analysis with deep learning and digital twins
Coupling physics-based simulation and data-driven modeling have demonstrated great power in predicting complex systems. This talk focuses on integrating an advanced finite element method, isogeometric analysis (IGA), with deep learning and digital twins to address challenging problems of neurological disorders and additive manufacturing (AM). First, we introduce a novel phase field model coupled with tubulin and synaptogenesis concentration to simulate intricate neurite outgrowth and disorders. By integrating IGA and convolutional neural networks, we conduct thorough investigations into the functional role of various parameters affecting the neurodevelopmental disorder with comparison to experimental results. Second, to investigate intracellular transport induced neurodegenerative disorders, we develop a PDE-constrained optimization model to simulate traffic jams induced by microtubule reduction and swirl. We also build a novel IGA-based physics-informed graph neural network to quickly predict normal and abnormal transport phenomena in complex neuron geometries, and recently, a graph-autoencoder-based latent dynamics surrogate model to further improve the prediction efficiency. In the area of AM, our research focuses on a machine learning framework for inverse design and manufacturing of self-assembling fiber-reinforced composites in 4D printing, IGA-based topology optimization for AM of heat exchangers, as well as data-driven residual deformation prediction and lattice support structure design in the laser powder bed fusion (LPBF) AM process. Our efforts aim to predict stress-induced build failures using dynamic neural surrogates, where reduced order modeling is a key technique to efficiently simulate underlying physics. The talk will conclude with an extension to other applications including two recently started projects.
Jessica Zhang
Jessica Zhang is the George Tallman Ladd and Florence Barrett Ladd Professor of Mechanical Engineering at Carnegie Mellon University (CMU) with a courtesy appointment in Biomedical Engineering and Civil & Environmental Engineering. She received her B.Eng. in Automotive Engineering, and M.Eng. in Engineering Mechanics from Tsinghua University, China; and M.Eng. in Aerospace Engineering and Engineering Mechanics and Ph.D. in Computational Engineering and Sciences from Oden Institute, The University of Texas at Austin. Her research interests include computational geometry, isogeometric analysis, finite element method, data-driven simulation, image processing, with a strong focus on their applications in computational biomedicine and engineering. Zhang has co-authored over 260 publications in peer-reviewed journals and conference proceedings and received several Best Paper Awards. She published a book entitled “Geometric Modeling and Mesh Generation from Scanned Images” with CRC Press, Taylor & Francis Group. Zhang’s recent major awards include ASME Van C. Mow Medal, AWM-SIAM Sonia Kovalevsky Lecture Award, and Simons Visiting Professorship from Mathematisches Forschungsinstitut Oberwolfach of Germany. She is a Fellow of ASME, SIAM, IAMBE, AIMBE, IACM, USACM, SMA, IMR and ELATES at Drexel. She also received the prestigious US Presidential Early Career Award for Scientists and Engineers, NSF CAREER Award, Office of Naval Research Young Investigator Award, and USACM Gallagher Young Investigator Award. Zhang’s recent leadership roles in her research societies include President of USACM, Chair of ASME AMD-CONCAM, Chair of SIAM Activity Group of Geometric Design, Chair of IAMBE Membership Committee, and Chair of AIMBE College of Fellows. She is the Editor-in-Chief of Engineering with Computers.