Predictive performance enhancement via domain-adaptive designable data augmentation and virtual data-based optimization

In this study, we present a methodology for deriving an optimal performance design in a new domain using a designable generative adversarial network (DGAN) structure based on domain-adaptive designable data augmentation (DADDA). In a generative adversarial network (GAN), two neural networks—the generator and discriminator—compete to learn virtual data that are difficult to distinguish from real data. The DGAN can estimate the corresponding design variables along with the generated virtual data by adding an inverse generator to the GAN structure. Designable data augmentation is possible by using a DGAN for unknown design variables in the virtual data created by the GAN. The advantage of a DGAN is that it is adaptable to both single and multiple design domains. In this study, we develop a DADDA method using a domain-adaptive DGAN. DADDA is a source/target domain-adaptive method that maximizes the design performance in a new target domain from the beginning based on an already optimized source domain that has accumulated a large amount of data. The methodology is verified using one mathematical example and two engineering analysis examples. First, the design is derived by increasing the goal performance step by step. The engineering analysis examples confirm that the design can be improved by up to 12.6%. In addition, we propose a method for deriving the maximum performance enhancement limit according to a virtual data-based optimization, without analyzing the goal performance individually, by grafting it with a genetic algorithm.