Layout designs are encountered in a variety of fields. For problems with many design degrees of freedom, efficiency of design methods becomes a major concern. In recent years, machine learning methods such as artificial neural networks have been used increasingly to speed up the design process. A main issue of many such approaches is the need for a large corpus of training data that are generated using high-dimensional simulations. The high computational cost associated with training data generation largely diminishes the efficiency gained by using machine learning methods. In this work, an adaptive artificial neural network-based generative design approach is proposed and developed. This method uses a generative adversarial network to generate design candidates and thus the number of design variables is greatly reduced. To speed up the evaluation of the objective function, a convolutional neural network is constructed as the surrogate model for function evaluation. The inverse design is carried out using the genetic algorithm in conjunction with two neural networks. A novel adaptive learning and optimization strategy is proposed, which allows the design space to be effectively explored for the search for optimal solutions. As such the number of training data needed is greatly reduced. The performance of the proposed design method is demonstrated on two heat source layout design problems. In both problems, optimal designs have been obtained. Compared with several existing approaches, the proposed approach has the best performance in terms of accuracy and efficiency.

翻译：在许多领域都遇到布局设计设计,对于设计自由程度众多的问题,设计方法的效率成为一大问题。近年来,人们越来越多地使用人工神经网络等机器学习方法来加速设计过程。许多这类方法的一个主要问题是需要使用高维模拟生成的大量培训数据。与培训数据生成有关的高计算成本在很大程度上降低了通过使用机器学习方法获得的效率。在这项工作中,提出并开发了适应性人工神经网络的基因化设计方法。这种方法使用基因化对抗网络来产生设计候选人,因此设计变量的数量大大减少。为加速对目标功能的评价,设计进化神经网络作为功能评估的替代模型来构建。反向设计是与两个神经网络一起使用遗传算法进行的。提出了一种新的适应性学习和优化战略,为寻找最佳解决方案有效地探索了设计空间。这种培训数据的数量大大减少了。为了加速对目标功能的评估,拟议的设计方法的性能和最佳热源设计方法在两种最佳设计上都有问题。在两种最佳热源设计方法上进行了比较。