Accelerating gradient-based topology optimization design with dual-model artificial neural networks

Abstract

Topology optimization (TO) is a common technique used in free-form designs. However, conventional TO-based design approaches suffer from high computational cost due to the need for repetitive forward calculations and/or sensitivity analysis, which are typically done using high-dimensional simulations such as Finite Element Analysis (FEA). In this work, neural networks are used as efficient surrogate models for forward and sensitivity calculations in order to greatly accelerate the design process of topology optimization. To improve the accuracy of sensitivity analyses, dual-model neural networks that are trained with both forward and sensitivity data are constructed and are integrated into the Solid Isotropic Material with Penalization (SIMP) method to replace FEA. The performance of the accelerated SIMP method is demonstrated on two benchmark design problems namely minimum compliance design and metamaterial design. The efficiency gained in the problem with size of 64x64 is 137 times in forward calculation and 74 times in sensitivity analysis. In addition, effective data generation methods suitable for TO designs are investigated and developed, which lead to a great saving in training time. In both benchmark design problems, a design accuracy of 95% can be achieved with only around 2000 training data.

A data-driven minimum stiffness prediction method for machining regions of aircraft structural parts

“…White et al [22] established a two-layered neural network model to map the geometrical parameters of microscale metamaterials to the element stiffness matrix. Qian et al [7] improved the above method and built a dual-model neural network to improve the accuracy of topology optimization.…”

“…Traditional stiffness calculation methods mainly include mechanics calculation methods [4], empirical formula methods [5], finite element methods (FEM) [6] and surrogate-based methods [7]. However, due to the structural complexity, these methods are either inaccurate or time consuming, which is far away from the requirements of real manufacturing.…”

An Artificial Intelligence–Assisted Design Method for Topology Optimization without Pre-Optimized Training Data

“…Sosnovik and Oseledets used DL to speed up conventional TO by [24] by using the results from some conventional TO iterations as input for the ANN. Qian and Ye accelerated conventional TO by utilizing surrogate models for forward and sensitivity calculations [25]. These approaches are indirect since some iterations are required.…”

An adaptive artificial neural network-based generative design method for layout designs

“…Such an approach is not only inefficient in problems with many design variables, but also not suitable for problems in which good design solutions lie in an extremely small portion of the design space. How to efficiently generate training data to truly achieve time saving in design problems is an ongoing research topic [7]. In a recent work [8], a machine learning framework was developed for topology optimization, in which a deep neural network (DNN) was used to predict the sensitivity information required to update the design.…”