Structural Health Monitoring for Smart Infrastructure

Said is currently focused on structural health monitoring of bridges using vision-based techniques. Because this is a robust and cost-effective solution for characterizing the load and structural response of bridges. Earlier, he worked as a post-doctoral research scholar in the Earthquake Engineering Research Centre, University of Iceland. There, his research has mainly focused on the prediction and safety of structures under multiple hazards. His future focus will be to establish a team that will contribute to usage of artificial intelligence for structural health monitoring, vibration control of structures, assessment of onshore and offshore structures, structural dynamics, earthquake, and wind engineering.

Prateek received his Ph.D. in structural health monitoring (SHM) of underground structures from the Department of Civil Engineering at the Indian Institute of Technology (IIT) Delhi, India. He did his M.Tech. in Geotechnical engineering from Delhi Technological University and B.Tech. in Civil engineering. He is involved in the research and development of sensor technologies and systems for performing structural health monitoring of civil structures. Here at the University of Twente, as a postdoctoral fellow, he is reviewing SHM technologies for wet infrastructure such as navigation locks, canals, quay walls, and dikes.

Maria joined the SHM4SI group as a PhD candidate to work on structural health and condition monitoring of bridges. In particular, her research work focuses on a hybrid approach (data-driven and physics-based) to characterize the bridge response under operational and environmental variations. Her past work experience as a Structural Engineer was in the industry on new design-build projects and on seismic/ structural assessments of existing buildings in Europe and overseas.

Mohsen is currently studying his EngD on designing a monitoring system for the condition assessment of the Beatrix lock complex. His design project is under the supervision of Professor André Dorée and Dr. Roland Kromanis in the department of civil engineering and management and in cooperation with Heijmans company. With a background in structural engineering, his expertise is in the field of image processing. Thus, vision-based monitoring is right up his alley. Prior to joining the SHM4SI group, Mohsen worked as a site manager on industrial structure retrofit projects at the Mobarakeh steel plant.

The aim of this project is to develop a cost-effective and sustainable approach to Bridge Integrity Management (BrIM) by integrating advanced digital technologies as decision-support tools throughout the bridge lifecycle.

Across Europe, many bridges have been in service for more than 50 years and now show significant signs of deterioration. In addition, they are often operating under conditions that differ substantially from their original design assumptions, with climate change accelerating the deterioration process. To address these challenges, BRIDGITISE brings together 24 academic and industrial partners in a multidisciplinary consortium, structured into 16 PhD research projects organized into three clusters: development and validation of digital technologies for bridge data collection; application of Artificial Intelligence (AI) and Internet of Things (IoT) technologies for processing and sharing bridge integrity information; and implementation of digital decision-support tools for lifecycle bridge management. The consortium covers the full digital BrIM value chain, including distributed sensors, drones, crowdsensing, satellite radar, digital twins, IoT, and AI-based analytics. Continuous monitoring data, combined with intelligent processing, will enable timely detection of deterioration, accurate prediction of structural performance, and optimization of maintenance interventions, ultimately setting a new standard for bridge lifecycle management, enhancing safety, extending service life, and reducing maintenance costs while training a new generation of researchers to lead Europe’s infrastructure digital transformation.

For more details on BRIDGITISE project: Click Here

The aim of this project is to design a sensor system for monitoring the long-term performance of the lock complex, by assessing the bed protection condition near the lock structure excited by the propeller wash of the large vessels. 

The Princess Beatrix Lock complex, located in Utrecht, the Netherlands, with three chambers, is a very busy ship transportation node in Dutch inland waterways. The Heijmans construction company, as a client of this project, is responsible for the maintenance of the lock for 27 years. Nevertheless, they are not the determiner of the chambers for ships to pass through the lock. Thus, they need to be aware of the influence of different ships’ passage with different behaviors to improve or modify the current operational guideline. Therefore, The impacts on the approach bed need to be monitored after every ship passage. To do this, using a monitoring system is developed to continuously scan the bed morphology of the canal to analyze the different behavior of passing ships.

The aim of this project is to develop an integrated measurement interpretation approach, which produces accurate predictions of bridge response resulting from applied loads (e.g., temperature, traffic, and wind).

To address the issue of effective monitoring, a data-driven approach is developed to characterise the bridge response based on combining the effect of environmental, static, and dynamic loading conditions under continuous monitoring data of at least one year. The methodology involves site data collection using a wired sensor system, analysis, and interpretation of collected data, and characterization of bridge response through time. Bayesian processes are employed to characterize traffic-induced response knowing the properties of vehicles and bridge response. The regression-based thermal response prediction methodology characterizes bridge thermal response. Bridge conditions then are assessed by analyzing the difference between predicted and measured response. This process detects any anomaly or possible defects or damages if present. The data collection is based on real full-scale footbridges that are used on a daily basis with a series of several contact sensors installed such as accelerometers, strain gauges, inclinometers, and temperature sensors.