Published on Fri Jul 27 2018

One-Shot Generation of Near-Optimal Topology through Theory-Driven Machine Learning

Ruijin Cang, Hope Yao, Yi Ren

We introduce a theory-driven mechanism for learning a neural network model that performs generative topology design in one shot given a problem setting. The proposed mechanism can lead to machines that quickly response to new design requirements based on its knowledge accumulated through past experiences.

0
0
0
Abstract

We introduce a theory-driven mechanism for learning a neural network model that performs generative topology design in one shot given a problem setting, circumventing the conventional iterative process that computational design tasks usually entail. The proposed mechanism can lead to machines that quickly response to new design requirements based on its knowledge accumulated through past experiences of design generation. Achieving such a mechanism through supervised learning would require an impractically large amount of problem-solution pairs for training, due to the known limitation of deep neural networks in knowledge generalization. To this end, we introduce an interaction between a student (the neural network) and a teacher (the optimality conditions underlying topology optimization): The student learns from existing data and is tested on unseen problems. Deviation of the student's solutions from the optimality conditions is quantified, and used for choosing new data points to learn from. We call this learning mechanism "theory-driven", as it explicitly uses domain-specific theories to guide the learning, thus distinguishing itself from purely data-driven supervised learning. We show through a compliance minimization problem that the proposed learning mechanism leads to topology generation with near-optimal structural compliance, much improved from standard supervised learning under the same computational budget.

Thu Feb 11 2021
Artificial Intelligence
Real-Time Topology Optimization in 3D via Deep Transfer Learning
The literature on topology optimization has exploded over the last two decades. We introduce a transfer learning method based on a convolutional neural network. The method is multiple orders of magnitude more efficient than the established gradient-based methods, such as SIMP.
0
0
0
Tue Feb 04 2020
Machine Learning
Self-Directed Online Machine Learning for Topology Optimization
Topology optimization by optimally distributing materials in a given domain requires gradient-free optimizers to solve highly complicated problems. With hundreds of design variables or more involved, solving such problems would require millions of Finite Element Method (FEM) calculations whose computational cost is huge and impractical.
0
0
0
Mon Jul 19 2021
Machine Learning
Robust Topology Optimization Using Variational Autoencoders
Topology Optimization is the process of finding the optimal arrangement of materials within a design domain. Robust topology optimization (RTO) incorporates the effect of input uncertainties and produces a design with the best average performance. It is computationally expensive to carry out RTO using finite grotesqueelement and Monte Carlo sampling.
0
0
0
Thu Mar 05 2020
Artificial Intelligence
TopologyGAN: Topology Optimization Using Generative Adversarial Networks Based on Physical Fields Over the Initial Domain
0
0
0
Wed Jul 14 2021
Machine Learning
Conservative Objective Models for Effective Offline Model-Based Optimization
In this paper, we aim to solve data-driven model-based optimization (MBO) problems. The goal is to find a design that maximizes an unknown objective function. We propose conservative objective models (COMs) to overcome distributional shift.
5
54
216
Mon Apr 05 2021
Neural Networks
Fast Design Space Exploration of Nonlinear Systems: Part II
0
0
0