The project aims to develop next-generation structural health monitoring practices for pedestrian bridges. Through the integration of data from biometric sensors and advanced structural sensors like cameras, strain gauges, and gyroscopes via data fusion, the project will establish a robust framework for assessing structural integrity and enhancing overall safety standards. The research focuses on pioneering a next-generation monitoring system that incorporates data fusion, digital twins, the Internet of Things, and artificial intelligence. Furthermore, the project aims to develop a monitoring system for crowd management, contributing to enhanced safety measures.

Approach:

The project is structured around three key phases, initially focusing on two laboratory bridges, and subsequently transitioning to a real-world bridge. In the initial phase, data is collected from experimental structures and crowds of varying characteristics within controlled laboratory environments. In the next phase, the collected data forms the basis for developing a real-time monitoring system that continuously updates through the integration of digital twin technology and artificial intelligence. The third phase extends the research to a real-world bridge, facilitating the refinement of the monitoring system's adaptability to real-life settings with external influences and diverse structural conditions.

Student involvement:

The research student will actively participate in the laboratory testing and subsequent data analysis within this research project. This involves both the design and set-up of the laboratory SHM system, as well as the execution of experiments. In addition, the student will make contributions to the data analysis by employing cutting-edge data analysis techniques and AI/ML methods. The student will gain knowledge and experience in various areas, including experimental testing, AI, data science, data analysis, coding, and SHM sensor technology.

School

Civil and Environmental Engineering

Research Area

Structural health monitoring | Data science | Digital twins | Internet of things | Bridge monitoring | Crowd safety

Our research environment is a dynamic and collaborative setting that encourages innovation and interdisciplinary collaboration. We have state-of-the-art laboratories equipped with cutting-edge sensor technologies, data analysis tools, and simulation software. Our team consists of experienced researchers in civil engineering and data science.

The fundamental objectives of this project revolve around developing effective methods for bridge monitoring to identify potential structural damage. Additionally, the project aims to develop capabilities for detecting crowd activities that influence the bridge's responses. By addressing both aspects, the goal is to establish a comprehensive monitoring system that enhances the safety and resilience of bridges, ensuring timely response mechanisms to both structural issues and crowd dynamics.

 

The practical implications of this project extend to the proposal of a novel safety approach for bridges, with potential applications in crowd control management. The insights gained from this project contribute to the formulation of a practical and innovative safety strategy that can be implemented across various structures hosting crowds, including stadiums, bridges, and other gathering spaces. The project's outcomes are intended to offer tangible solutions that go beyond theoretical considerations, providing a basis for the development and application of effective safety measures in real-world scenarios involving diverse structures and crowd dynamics.