Topology Optimization under Uncertainty using a Stochastic Gradient-based Approach

TL;DR

This paper introduces a stochastic gradient-based approach for topology optimization under uncertainty, significantly reducing computational costs by approximating objectives and gradients with fewer adjoint solves, enabling efficient large-scale structural design optimization.

Contribution

It proposes a novel stochastic approximation method integrated with gradient-based algorithms, including SGD and GCMMA, to improve computational efficiency in TOuU with high uncertainty.

Findings

The approach reduces the number of adjoint solves per iteration.

It maintains accuracy with only a small increase in total computational cost.

The method is effective with both SIMP and level set-based structural optimization.

Abstract

Topology optimization under uncertainty (TOuU) often defines objectives and constraints by statistical moments of geometric and physical quantities of interest. Most traditional TOuU methods use gradient-based optimization algorithms and rely on accurate estimates of the statistical moments and their gradients, e.g., via adjoint calculations. When the number of uncertain inputs is large or the quantities of interest exhibit large variability, a large number of adjoint (and/or forward) solves may be required to ensure the accuracy of these gradients. The optimization procedure itself often requires a large number of iterations, which may render TOuU computationally expensive, if not infeasible. To tackle this difficulty, we here propose an optimization approach that generates a stochastic approximation of the objective, constraints, and their gradients via a small number of adjoint (and/or forward) solves, per iteration. A statistically independent (stochastic) approximation of these quantities is generated at each optimization iteration. The total cost of this approach is only a small factor larger than that of the corresponding deterministic TO problem. We incorporate the stochastic approximation of objective, constraints and their design sensitivities into two classes of optimization algorithms. First, we investigate the stochastic gradient descent (SGD) method and a number of its variants, which have been successfully applied to large-scale optimization problems for machine learning. Second, we study the use of the proposed stochastic approximation approach within conventional nonlinear programming methods, focusing on the Globally Convergent Method of Moving Asymptotes (GCMMA). The performance of these algorithms is investigated with structural design optimization problems utilizing a Solid Isotropic Material with Penalization (SIMP), as well as an explicit level set method.