Image-Based Multiresolution Topology Optimization Using Deep Disjunctive Normal Shape Model

We present a machine learning framework for predicting the optimized structural topology designs using multiresolution data. Our approach primarily uses optimized designs from inexpensive coarse mesh finite element simulations for model training and generates high resolution images associated with simulation parameters that are not previously used. Our cost-efficient approach enables the designers to effectively search through possible candidate designs in situations where the design requirements rapidly change. The underlying neural network framework is based on a deep disjunctive normal shape model (DDNSM) which learns the mapping between the simulation parameters and segments of multi resolution images. Using this image-based analysis we provide a practical algorithm which enhances the predictability of the learning machine by determining a limited number of important parametric samples (i.e. samples of the simulation parameters) on which the high resolution training data is generated. We demonstrate our approach on benchmark compliance minimization problems including the 3D topology optimization where we show that the high-fidelity designs from the learning machine are close to optimal designs and can be used as effective initial guesses for the large-scale optimization problem. (C) 2020 Elsevier Ltd. All rights reserved.

Automated summary

The study introduces a machine learning framework for predicting optimized structural topology designs using multiresolution data. By analyzing images and mapping simulation parameters to images through neural networks, the predictability of the learning machine is enhanced. The approach demonstrates significant results in topology optimization problems.