Skip to content


Title: Micromechanical Analysis of Materials with Complex Microstructures: Automated Modeling and Deep Learning Algorithms


A integrated computational framework relying on virtual microstructure reconstruction, parallel mesh generation, and deep learning algorithms will be presented for predicting/simulating the multiscale failure response of materials. A NURBS-based virtual reconstruction algorithm is developed for synthesizing heterogenous material microstructures by packing arbitrary shaped inclusions, morphologies of which are extracted from imaging data such as micro-computed tomography images. A genetic algorithm (GA) based optimization phase is then utilized to replicate target statistical microstructural descriptors such as the volume fraction, spatial arrangement, and orientations of embedded inclusions. We also introduce a new AI-based approach relying on Deep Convolutional Degenerative Adversarial Networks (DCGAN) for the virtual reconstruction of complex biomaterial microstructures. Conforming finite element (FE) meshes are generated using a non-iterative meshing algorithm, coined Conforming to Interface Structured Adaptive Mesh Refinement (CISAMR), which transforms an initial structured mesh into a high-quality conforming mesh. CISAMR can handle problems with highly intricate geometries, including material interfaces with sharp edges/corners, as well as mixed-mode fracture problems involving crack merging. We show the application of this integrated reconstruction-meshing framework, together with deep learning algorithm, for predicting the failure response and fatigue life of a variety of materials systems, including particulate composites, fiber-reinforced composites, and biomaterials. Moreover, we show how these  algorithms can be used in the realm of computational biomechanics for creating digital twins of human vertebra and predicting the risk of vertebral compression fracture  in cancer patients with spinal metastasis.


Soheil Soghrati is an Associate professor of Mechanical and Aerospace Engineering at The Ohio State University. He earned his PhD in Structural Engineering with Minor in Computational Science in Engineering from the University of Illinois at Urbana-Champaign, during which he held a graduate research assistantship at the Beckman Institute for Advanced Science and Technology. Soghrati joined the Department of Mechanical and Aerospace Engineering at OSU in June 2013 with a joint appointment in the Department of Materials Science and Engineering. He is also one of the steering board faculty members in the Simulation Innovation and Modeling Center (SIMCenter) at OSU. 

Soghrati’s research interests lay in the area of computational solid mechanics with especial focus on the development and implementation of advanced finite element and AI algorithms for the automated modeling of problems with complex and/or evolving morphologies. He has established the Automated Computational Mechanics Laboratory (ACML) at OSU. Some of the problems investigated in Soghrati's research group include cancer engineering, microstructure reconstruction and mesh generation algorithms, deep learning algorithms and their applications in computational mechanics, simulating localized corrosion and corrosion-assisted failure of metals, digital manufacturing, studying the multiscale failure response of composites, computational biomechanics, and computational design of Lithium-ion battery electrodes. Current projects in ACML are supported by the National Science Foundation, Air Force Office of Scientific Research, Department of Defense, Honda R&D Americas, Ford, and OSU’s Center for Cancer Engineering.

You can also stream this seminar via Zoom

Thursday, November 10, 2022 at 4:05pm to 5:20pm

John D. Tickle Engineering Building, 405
851 Neyland Dr, Knoxville, TN 37996

Event Type

Lectures & Presentations




Current Students, Faculty & Staff


CEE Seminar, CEE Fall 2022

Civil and Environmental Engineering
Contact Name

Timothy Truster

Contact Email

Google Calendar iCal Outlook

Recent Activity