Sensor and Data Analytics Systems for Structural Health Monitoring in Smart Infrastructure

Lead Research Organisation: Queen's University of Belfast
Department Name: Electronics Electrical Eng and Comp Sci


There is considerable interest in employing Structural Health Monitoring (SHM) to evaluate the condition of engineering structures and is particularly relevant for infrastructure in smart cities and new transportation systems. SHM has been used within Mechanical Engineering applications for some decades now but is increasingly being looked at within Civil Infrastructure for widespread implementation. However, there exist largely 2 challenges to wide-scale adoption of SHM in this domain; (i) data collection and (ii) data interpretation and analysis.

To identify what information can be garnered from measurements, much of the research to date has focused on data interpretation and this work is ongoing. However, for practical implementation there is an urgent need for sensing solutions that can (a) collect the necessary data on structures that may have no power or communications and (b) be sufficiently low cost to make large scale data collection financially practicable. In the case of many bridges, for example, this is a particular problem as these structures provide vital transport interconnections particularly in the countryside; therefore, providing low-cost, practical solutions that can monitor performance on a continual basis is vital.

This project aims to tackle these challenges from a multidisciplinary perspective (bridging both Information and Communication technologies and Engineering themes, and in particular bringing together sensors and instrumentation, artificial intelligence, microelectronics design and structural engineering.) and to this end several areas for innovation have been identified with the outputs of these providing enabling technologies for low-cost, long-term SHM real-world implementations;

- Carrying out research into new approaches to monitoring utilising new sensing paradigms through both simulation and practical experiments

- Developing new data compression algorithms and strategies to tackle the challenges of embedded sensor's (low power, low communications capacities, low compute resources)

- Creating solutions incorporating embedded artificial intelligence and edge computing to reduce data backhaul capacity requirements through the decentralisation of analytics computation


10 25 50

Studentship Projects

Project Reference Relationship Related To Start End Student Name
EP/N509541/1 30/09/2016 29/09/2021
2275989 Studentship EP/N509541/1 30/09/2019 30/07/2023 Alan James Ferguson
EP/R513118/1 30/09/2018 29/09/2023
2275989 Studentship EP/R513118/1 30/09/2019 30/07/2023 Alan James Ferguson