This paper presents a novel combination of Generative Adversarial Networks (GANs) and Clustering Analysis (CA) for topology optimization. Based on the results from the topology analysis, new data are generated by the GANs and Deep Convolutional GANs (DCGANs). K-means Clustering Analysis is employed to select optimized valid data with the minimum compliance and the discreteness of design variables out of generated data through the GANs and the DCGANs. Finally, a Topology Optimization Validation Curve (TOVC) is successfully developed by collecting the optimized valid data through the entire volume fraction of the structure. The adaptability and the efficiency of the proposed method is verified for topology optimization of the well-known MBB beams.

本文提出了将生成的对抗网络（GAN）和聚类分析（CA）进行拓扑优化的新颖组合。根据拓扑分析的结果，GAN和深度卷积GAN（DCGAN）会生成新数据。K-均值聚类分析用于通过GAN和DCGAN从生成的数据中选择具有最小一致性和设计变量离散性的优化有效数据。最后，通过在结构的整个体积分数中收集优化的有效数据，成功开发了拓扑优化验证曲线（TOVC）。验证了所提出方法的适应性和效率，以用于公知MBB波束的拓扑优化。