A novel generative reverse net assisted evolution algorithm for expensive-computational optimizations

TL;DR

This paper introduces a new optimization algorithm that combines generative deep learning with evolutionary strategies to efficiently solve complex, computationally expensive design problems, demonstrated on composite material and sheet-forming cases.

Contribution

The study presents a novel Generative Reverse Net assisted Evolution Algorithm (GRN-EA) that leverages deep learning for surrogate modeling in expensive optimization tasks.

Findings

Successfully optimized a Variable-Stiffness composite hole-plate.

Effectively handled complex sheet-forming optimization.

Demonstrated reduced computational costs in practical problems.

Abstract

Simulation-based optimization is a useful method for practical design problems. However, it is difficult for complicated problems due to expensive-computational costs. A popular way to overcome this issue is to use a surrogate model to save the cost. Nevertheless, limited design parameters those are input to traditional surrogate models can difficultly represent the whole design problem, which might result in unexpected errors. In this study, physical cloud images from simulations are employed and attempted to construct the surrogate model. Simultaneously, based on the strong pattern recognition and generation abilities of deep learning models, a novel Generative Reverse Net assisted Evolution Algorithm (GRN-EA) is proposed for expensive-design problems. In this study, a numerical example of a Variable-Stiffness (VS) composite hole-plate is employed to obtain the optimal distribution of the curved fiber. Moreover, to evaluate the performance of GRN-EA in practical engineering problems, a more complex sheet-forming case is optimized. According to the two problems, some expensive-simulations can be well handled in this study.