PSI - Issue 71

Available online at www.sciencedirect.com

ScienceDirect

Procedia Structural Integrity 71 (2025) 469–476

Keywords: Crystal plasticity; Microstructure; Machine Learning; ConvLSTM 1. Introduction The last few decades have seen a remarkable growth in the development of new alloy systems for advanced applications. However, new material development requires significant time and cost, which can be reduced by the use of high-resolution models. Several such models and computational methods have been developed to predict the properties of various metallic systems, and Crystal Plasticity Finite Element Method (CPFEM) is one of those high potential technique. CPFEM method efficiently calculates the micro-structural properties incorporating the effects of phenomena such as grain boundary strengthening, dislocation density etc. shown by Evers et al. (2004) and Li et al. Abstract Over the past century, a lot of research has been done to form innovative materials that can cater to serve different purposes in industries such as aerospace, automotive, marine etc. However, metals still hold a major part of the products developed in these industries and hence, it is important to study the behavior of metals both macroscopically as well as microscopically. Finite Element Method using Crystal Plasticity constitutive model (CPFEM) is one of the popular methods that enables investigating the material behavior at micro level accurately but is computationally expensive. Recent studies suggest that ML (Machine learning) techniques can significantly reduce the computational time when ensembled with methodologies that evaluate the behavior of materials (e.g., phase-field methods, CPFEM, Peridynamics). This paper highlights the ability of ML based full-field simulations of polycrystalline alloys to reduce computational time of CPFEM simulations. A convolution-based LSTM (ConvLSTM) model is used and trained using few time steps of full-field response from CPFEM simulations. © 2025 The Authors. Published by ELSEVIER B.V. This is an open access article under the CC BY-NC-ND license (https://creativecommons.org/licenses/by-nc-nd/4.0) Peer-review under responsibility of SICE 2024 organizers 5 th International Structural Integrity Conference & Exhibition (SICE 2024) Machine Learning to Accelerate Full-Field Crystal Plasticity Simulations A Shivnag Sharma a, ∗ , Owais Ahmad b , Somnath Bhowmick b , Pritam Chakraborty a a Dept. Of Aerospace Engineering, IIT Kanpur, Kanpur, UP, India (208016) b Dept. Of Materials Science and Engineering, IIT Kanpur, Kanpur, UP, India (208016)

_____________

* Corresponding author. Tel.: +91-7879551125.

E-mail address: shivnag22@iitk.ac.in

2452-3216 © 2025 The Authors. Published by ELSEVIER B.V. This is an open access article under the CC BY-NC-ND license (https://creativecommons.org/licenses/by-nc-nd/4.0) Peer-review under responsibility of SICE 2024 organizers 10.1016/j.prostr.2025.08.063