Optimal design of frame structures with mixed categorical and continuous design variables using the Gumbel-Softmax method

TL;DR

This paper introduces a gradient-based optimization method using Gumbel-Softmax to efficiently handle mixed categorical and continuous variables in large-scale frame structure design, reducing computational cost and improving optimization performance.

Contribution

The paper presents a novel gradient-based optimizer that incorporates Gumbel-Softmax for handling categorical variables in structural optimization, enabling simultaneous optimization of mixed variable types.

Findings

The proposed method outperforms genetic algorithms in computational efficiency.

It effectively handles high-dimensional mixed-variable optimization problems.

Numerical case studies demonstrate the optimizer's advantages in real-world scenarios.

Abstract

In optimizing real-world structures, due to fabrication or budgetary restraints, the design variables may be restricted to a set of standard engineering choices. Such variables, commonly called categorical variables, are discrete and unordered in essence, precluding the utilization of gradient-based optimizers for the problems containing them. In this paper, incorporating the Gumbel-Softmax (GSM) method, we propose a new gradient-based optimizer for handling such variables in the optimal design of large-scale frame structures. The GSM method provides a means to draw differentiable samples from categorical distributions, thereby enabling sensitivity analysis for the variables generated from such distributions. The sensitivity information can greatly reduce the computational cost of traversing high-dimensional and discrete design spaces in comparison to employing gradient-free optimization methods. In addition, since the developed optimizer is gradient-based, it can naturally handle the simultaneous optimization of categorical and continuous design variables. Through three numerical case studies, different aspects of the proposed optimizer are studied and its advantages over population-based optimizers, specifically a genetic algorithm, are demonstrated.