Abstract

Port structures face the constant threat of deterioration due to exposure to dynamic and seismic forces, as well as harsh environmental condition prevalent in a maritime setting. These challenges lead to induced stress concentrations within the structures, resulting in potential catastrophic failures. Despite significant effort, expenses, and time consumption associated with traditional structural health monitoring systems (SHM), regular inspections remain the norm. This study introduces innovative methods to replace traditional approaches, leveraging Artificial Neural Networks (ANNs) as surrogates for real-time finite element (FE) modelling. The goal is to develop FE-based real-time digital twins for port structure by using sensor data, visualizing structural behaviour, and enabling a comprehensive monitoring of its structural response. An ANN model is trained using a validated FE model of the structure, generating immediate deformations based on sensor readings. By implementing this approach, stress variations are efficiently obtained and visualized throughout the structure. Unlike traditional methods that follow an inverse approach in estimating the entire structural response based on sensor values, the ANNs demonstrate high efficiency in addressing ill-conditioning issues inherent in such processes. This integrated methodology showcases the effectiveness of ANNs in providing real-time insights into the structural response of port infrastructure, offering a viable addition to the conventional SHM practices. The trained ANN model generates results in a high accuracy where the testing error is in the order of 10−5 and it generates data within 15 milli seconds demonstrating the near real-time conditions. The development of digital twins, facilitated by ANNs, demonstrates a promising solution for continuous monitoring, predictive maintenance, and risk mitigation in the face of dynamic operational and environmental challenges. The study contributes to the advancement of smart infrastructure by harnessing the capabilities of artificial intelligence and digital twin technology.

Full Text
Paper version not known

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

Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.