top of page

Surrogate PHFGMC Micromechanical Models for Multiscale Analysis: AI-Enhanced Low-Velocity Impact Analysis of Composite plates


Hadas Hochster (1), Yevheniia Bernikov(1),  Ido Meshi(1), Shiyao Lin(2), Vipul Ranatunga(3), Anthony M.  Waas(2), Noam N.Y Shemesh(4), and Rami Haj-Ali (1)

affiliates: (1)School of Mechanical Engineering, Tel Aviv University, Tel Aviv, Israel,(2) University of Michigan, Ann Arbor, MI, 48109, (3) Air Force Research Laboratory, Wright Patterson AFB, 45433, USA, (4) IAF Aeronautical Engineering Branch, Tel-Aviv, Israel


Contact:


Abstract:

The parametric high-fidelity generalized method of cells (PHFGMC) is an advanced micromechanical method that can be used for the nonlinear and failure analysis of several composite materials. In order to overcome the prohibitive computational cost of integrating micromechanical models into multiscale structural analyses as constitutive models, a proxy-surrogate modeling approach has been proposed by implementing a reduction modeling approach with deep Artificial Neural Networks (DNNs or ANNs).  To that end, we propose a new artificial neural network (ANN) based micromechanical modeling framework, termed ANN-PHFGMC, for exploring the nonlinear behavior of fiber-reinforced polymeric (FRP) materials.   Pre-simulated mechanical stress–strain responses and behaviors are determined using the PHFGMC to generate a multiaxial training database for the ANN micromodel. Next, the PHFGMC-ANN approach has been employed to investigate the low velocity impact (LVI)  analysis of laminated composite plates. Multiscale LVI analyses are performed for different composite panels with different layups and the results are compared to experimental data to demonstrate the new model's ability to integrate refined nonlinear micromechanical models within a multiscale analysis.


Representative Results:




Paper Publication


Education

2022-present: PhD in mechanical engineeringMechanical Engineering School, Engineering Faculty, Tel Aviv UniversityAdvisor: Professor Rami Haj-Ali

2020-2022: M.Sc. in mechanical engineeringMechanical Engineering School, Engineering Faculty, Tel Aviv UniversityAdvisor: Professor Rami Haj-Ali

2016-2020: Double major degree: B.Sc. in mechanical engineering, B.A humanities unitMechanical Engineering School, Engineering Faculty, Tel Aviv University


Research Experience

Nonlinear and failure analysis of composite materials using PHFGMC micromechanical model.

Low-velocity impact analyses for different composite plates and stiffened panels using PHFGMC-ANNConducting experiments using DIC technique.


References

Hochster H, Bernikov Y, Meshi I, et al. Refined nonlinear micromechanical models using artificial neural networks for multiscale analysis of laminated composites subject to low-velocity impact. International Journal of Solids and Structures 2023; 264: 112123. DOI: https://doi.org/10.1016/j.ijsolstr.2023.112123.

Kommentare


bottom of page