Abstract
The effective management of aging infrastructure represents a critical concern globally, exerting profound socio-economic influences and occupying a prominent position on the political agenda. The escalating occurrences of catastrophic collapses in recent years underscore the pressing requirement for efficient Structural Health Monitoring (SHM) strategies. These strategies play a pivotal role in aiding decision-making processes related to prioritizing interventions and rehabilitation efforts. Among SHM systems, those utilizing Operational Modal Analysis (OMA) through vibration-based techniques have gained popularity due to their non-destructive nature, comprehensive damage assessment capabilities, and relative ease of automation. Despite their advantages, current OMA methods encounter significant scalability challenges, primarily attributable to extensive computational demands and the necessity for substantial expert involvement. In this context, recent advancements in the field of artificial intelligence (AI) present a promising solution to address these scalability issues, opening the door for the development of next-generation SHM systems. This study introduces an innovative Multitask Learning Deep Neural Network (MTL-DNN) model designed for rapid and automated blind source modal identification of structures. Integrating the concepts of undetermined second-order blind source identification (SOBI) into the architecture of the network, the proposed model can reveal the independent modal components present in the raw response acceleration data with minimum computational burden. The presented results demonstrate the quasi-instantaneous modal identification capabilities of the proposed architecture, enabling the estimation of more components than the number of sensors.
Published Version (
Free)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call