CycleGAN for Undamaged-to-Damaged Domain Translation for Structural Health Monitoring and Damage Detection

The accelerated advancements in the data science field in the last few decades has benefitted many other fields including Structural Health Monitoring (SHM). Particularly, the employment of Artificial Intelligence (AI) such as Machine Learning (ML) and Deep Learning (DL) methods towards vibration-based damage diagnostics of civil structures have seen a great interest due to their nature of supreme performance in learning from data. Along with diagnostics, damage prognostics also hold a vital prominence, such as estimating the remaining useful life of civil structures. Currently used AI-based data-driven methods for damage diagnostics and prognostics are centered on historical data of the structures and require a substantial amount of data to directly form the prediction models. Although some of these methods are generative-based models, after learning the distribution of the data, they are used to perform ML or DL tasks such as classification, regression, clustering, etc. In this study, a variant of Generative Adversarial Networks (GAN), Cycle-Consistent Wasserstein Deep Convolutional GAN with Gradient Penalty (CycleWDCGAN-GP) model is used to answer some of the most important questions in SHM: "How does the dynamic signature of a structure transition from undamaged to damaged conditions?" and "What is the nature of such transition?". The outcomes of this study demonstrate that the proposed model can accurately generate the possible future responses of a structure for potential future damaged conditions. In other words, with the proposed methodology, the stakeholders will be able to understand the damaged condition of structures while the structures are still in healthy (undamaged) conditions. This tool will enable them to be more proactive in overseeing the life cycle performance of structures as well as assist in remaining useful life predictions.