3D Topology Optimization using Convolutional Neural Networks

Abstract

Topology optimization is computationally demanding that requires the assembly and solution to a finite element problem for each material distribution hypothesis. As a complementary alternative to the traditional physics-based topology optimization, we explore a data-driven approach that can quickly generate accurate solutions. To this end, we propose a deep learning approach based on a 3D encoder-decoder Convolutional Neural Network architecture for accelerating 3D topology optimization and to determine the optimal computational strategy for its deployment. Analysis of iteration-wise progress of the Solid Isotropic Material with Penalization process is used as a guideline to study how the earlier steps of the conventional topology optimization can be used as input for our approach to predict the final optimized output structure directly from this input. We conduct a comparative study between multiple strategies for training the neural network and assess the effect of using various input combinations for the CNN to finalize the strategy with the highest accuracy in predictions for practical deployment. For the best performing network, we achieved about 40% reduction in overall computation time while also attaining structural accuracies in the order of 96%.

arXiv commentThe paper is under review in 'Special issue on Computer-Aided Design on Advances in Generative Design', 16 Pages, 7 tables, 8 figures

References in corpus (1)

• Deep learning for determining a near-optimal topological design without any iteration

Cited by in corpus (17)

• Deep Generative Design: Integration of Topology Optimization and Generative Models
• Topology optimization of 2D structures with nonlinearities using deep learning
• Generative Design by Reinforcement Learning: Enhancing the Diversity of Topology Optimization Designs
• Learning to design from humans: Imitating human designers through deep learning
• Algorithmically-Consistent Deep Learning Frameworks for Structural Topology Optimization
• Data-driven topology design using a deep generative model
• Neural reparameterization improves structural optimization
• A mechanistic-based data-driven approach to accelerate structural topology optimization through finite element convolutional neural network (FE-CNN)
• Convolutional Neural Network-based Topology Optimization (CNN-TO) By Estimating Sensitivity of Compliance from Material Distribution
• How machine learning can help the design and analysis of composite materials and structures?
• Scalable Deep-Learning-Accelerated Topology Optimization for Additively Manufactured Materials
• Image-based reconstruction for the impact problems by using DPNNs
• A study on using image based machine learning methods to develop the surrogate models of stamp forming simulations
• DNN-Based Topology Optimisation: Spatial Invariance and Neural Tangent Kernel
• Accelerating gradient-based topology optimization design with dual-model neural networks
• Can CNN Construct Highly Accurate Models Efficiently for High-Dimensional Problems in Complex Product Designs?
• An FEA surrogate model with Boundary Oriented Graph Embedding approach