Description
For civil, mechanical, and aerospace structures to extend operation times and to remain in service, structural health monitoring is vital. Structural health monitoring (SHM) system is a method to examining and monitoring the dynamic state of essential constructions. Because of its versatility in adapting to unfavorable structural changes and enhancing structural dependability and life cycle management, it has been extensively used in many engineering domains, especially in civil bridges. Due to the recent technical developments in sensors, high-speed internet, and cloud computing, data-driven approaches to structural health monitoring are gaining appeal. Since artificial intelligence (AI), especially in SHM, was introduced into civil engineering, this modern and promising methods has attracted significant research attention. In this project, a large dataset of acceleration time series using digital sensors was collected by installing structural health monitoring (SHM) system on Nibelungen Bridge located in Worms, Germany. A meta-data description for Artificial Intelligence (AI) models was defined and used to enable automated access to training AI models for deep transfer learning. The models are stored in a research data management in such a way that they can be versioned and uniquely referenced. This paper focuses on analyzing different classification models using deep learning approach to predict the vehicle movement on the bridge from the raw acceleration data obtained from sensors.
