Topology optimization of 2D structures with nonlinearities using deep learning

2020/02/29 by Diab W. Abueidda, Diab Abueidda, Seid Koric +3
Computer Science · Engineering · Mathematics · #Advanced Multi-Objective Optimization Algorithms #Artificial intelligence #Artificial neural network #Boundary value problem #Composite Structure Analysis and Optimization #Computer science #Convolutional neural network #Engineering #Finite element method #Hyperelastic material #Mathematical optimization #Mathematics #Nonlinear system #Pipeline (software) #Set (abstract data type) #Structural engineering #Topology (electrical circuits) #Topology Optimization in Engineering #Topology optimization #cs.CE #cs.LG

paper · pdf · doi:10.1016/j.compstruc.2020.106283

arxiv created 2020/04/13 · openalex publication_date 2020/05/15 · arxiv updated 2021/02/09 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/05

Abstract

The field of optimal design of linear elastic structures has seen many exciting successes that resulted in new architected materials and structural designs. With the availability of cloud computing, including high-performance computing, machine learning, and simulation, searching for optimal nonlinear structures is now within reach. In this study, we develop convolutional neural network models to predict optimized designs for a given set of boundary conditions, loads, and optimization constraints. We have considered the case of materials with a linear elastic response with and without stress constraint. Also, we have considered the case of materials with a hyperelastic response, where material and geometric nonlinearities are involved. For the nonlinear elastic case, the neo-Hookean model is utilized. For this purpose, we generate datasets composed of the optimized designs paired with the corresponding boundary conditions, loads, and constraints, using a topology optimization framework to train and validate the neural network models. The developed models are capable of accurately predicting the optimized designs without requiring an iterative scheme and with negligible inference computational time. The suggested pipeline can be generalized to other nonlinear mechanics scenarios and design domains.

Citations

• A Practical Guide to Training Restricted Boltzmann Machines
• Adam: A Method for Stochastic Optimization
• The method of moving asymptotes—a new method for structural optimization
• Tangent operators and design sensitivity formulations for transient non‐linear coupled problems with applications to elastoplasticity
• 3D Topology Optimization using Convolutional Neural Networks
• A Novel Topology Optimization Approach using Conditional Deep Learning
• A deep Convolutional Neural Network for topology optimization with strong generalization ability
• Deep long short-term memory networks for nonlinear structural seismic response prediction
• Understanding deep learning requires rethinking generalization
• An energy approach to the solution of partial differential equations in computational mechanics via machine learning: Concepts, implementation and applications