@misc{10481/98644,
year = {2024},
month = {12},
url = {https://hdl.handle.net/10481/98644},
abstract = {Digital twins (DTs) have revolutionised digitalisation practices across various domains, including the Architecture, Engineering,
Construction and Operations (AECO) sector. However, DTs often face challenges related to data scarcity, especially in AECO,
where tests are costly and di:cult to scale. Historical data in this domain are often limited, unstructured and lack interoperability
standards. Data scarcity directly a;ects the accuracy and reliability of the DT models and their decision-making capabilities. To
address these challenges, classical methods are used to produce synthetic data based on prede<ned statistical distributions, which
are barely scalable to unpredictable scenarios and prone to over<tting. Alternately, this work presents a novel comprehensive
approach that covers every aspect from synthetic data generation to training and testing of these data on the system’s models. /is
strategy not only delivers high-quality data that meets the model’s requirements in terms of diversity, complexity and class
balance, but also provides the diagnostic and prognostic capabilities of the DTof the system through its trained models. State-ofthe-
art techniques including generative adversarial networks (GANs), speci<cally Wasserstein generative adversarial networks
with gradient penalty (WGAN-GP), and convolutional neural networks (CNNs) are employed in this novel pervasive approach,
participating in the same architecture for generative, diagnostic and prognostic purposes. GANs enable data augmentation and
reconstruction, while CNNs excel in spatial pattern recognition tasks. /e proposed framework is demonstrated through an
experimental case study on damage diagnostics and prognostics of a laboratory-scale metallic tower, where synthetic datasets are
generated to supplement limited health monitoring data. /e results showcase the e;ectiveness of the generated data for damage
detection, prognostics and operational decision-making within the DTcontext. /e presented method contributes to overcoming
data scarcity challenges and improving the accuracy of DTmodels in the AECO sector. /e article concludes with discussions on
the application of the results and their implications for decision-making within the DT framework.},
organization = {Project: ENHAnCE ITN (https://www.h2020-enhanceitn.
eu/) from the European Union Horizon 2020 Research and
Innovation Programme under the Marie Sklodowska-Curie
grant agreement No. 859957},
organization = {Grant Nos. PID 2020-
119478GB-I00, PLEC2021-007798 and PID2020-
116644RB-I00 of the Spanish Ministry of Science and Education},
publisher = {Wiley Online Library},
keywords = {convolutional neural network (CNN)},
keywords = {digital twin (DT)},
keywords = {generative adversarial networks (GANs)},
title = {Generative Adversarial Networks for Improved Model Training in the Context of the Digital Twin},
doi = {10.1155/stc/9997872},
author = {Megía Cardeñoso, María and Melero Rus, Francisco Javier and Chiachío Ruano, Manuel and Chiachío Ruano, Juan},
}