Researchers from the Cambridge Centre for Smart Infrastructure and Construction (CSIC) will join a £7.7 million collaborative project set up to drive new standards for safer, greener, more cost-effective UK infrastructure.
The team at CSIC will be contributing their unique combination of expertise in data-centric engineering and foundational statistical machine learning in delivering efficient PBSHM algorithms.Professor Mark Girolami
Funded by the Engineering and Physical Sciences Research Council (EPSRC), the ROSEHIPS (Revolutionising Operational Safety and Economy for High-value Infrastructure using Population-based SHM) project will aim to solve the infrastructure asset management problem in the UK for maintaining our buildings and structures, such as bridges and transport networks, via transformative new research to automate health monitoring.
Instead of expensive scheduled inspections, diagnoses can be provided economically by permanently-installed sensors, collecting structural data continuously and interpreting it via computer algorithms. Using Population Based Structural Health Monitoring (PBSHM), the project will develop machine learning, sensing and Digital Twin technology for automated inference of health for structures in operation now, and drive new standards for safer, greener structures in future.
Led by researchers at the University of Sheffield, the project involves the University of Cambridge, Queen’s University Belfast and the University of Exeter, combining sensor development, machine learning and civil engineering expertise. Key industry partners include Northern Ireland Department for Infrastructure, Translink, Arqiva, Cellnex (UK) and Siemens Gamesa. The team at CSIC will contribute expertise in data-centric engineering and foundational statistical machine learning in delivering efficient PBSHM algorithms.
Healthy infrastructure is critical to ensuring the continued functionality and growth of UK society and the economy. Unfortunately, monitoring and maintaining our buildings and transport network is expensive; in the UK, a backlog of maintenance works, identified in 2019, will cost £6.7bn.
Considering bridges, inspection is usually carried out visually by human experts. Resources are stretched, so inspections cannot be carried out as often as desired, repairs aren’t made quickly and opportunities are missed to make cost effective decisions on maintenance and improvement. In a few extreme cases structural failure can result in fatalities.
The offshore wind (OW) sector is another area for concern. OW has driven down energy costs and increased power output, pioneering a global change to clean energy. The UK leads globally in OW energy, providing almost one third of the UK's annual electricity demand and helping meet the UK’s net-zero-by-2050 target. The drive for turbines in deeper water demands new ways of asset management, controlling and limiting operation/maintenance lifetime costs. As turbines increase in numbers, size, and capacity, these issues become even more important.
Co-investigator Professor Mark Girolami is an Academic Director for CSIC and the Sir Kirby Laing Professor of Civil Engineering at Cambridge, where he also holds the Royal Academy of Engineering Research Chair in Data-Centric Engineering (DCE).
Professor Girolami said: “This research programme is set to make significant advances in the theory, methodology, application, successful deployment and adoption of Population-Based Structural Health Monitoring (PBSHM), in making our critical inter-connected infrastructure safe, resilient and more efficient. This programme will draw on, and build upon, much of the capability and expertise built over the last decade at CSIC. In particular, the team at CSIC will be contributing their unique combination of expertise in data-centric engineering and foundational statistical machine learning in delivering efficient PBSHM algorithms.”
Professor Keith Worden, from the University of Sheffield’s Department of Mechanical Engineering, said: “Population-Based Structural Health Monitoring (PBSHM) is a game-changing idea, emerging in the UK very recently. It has the potential to overcome current technological barriers and transform our ability to automatically infer the condition of a structure, or a network of structures, from sensor data.
“This programme brings together the perfect team, mixing complementary skills in machine learning and advanced data analysis with expertise in new sensor systems and insight into complex infrastructure systems.”
The work will be underpinned by experiments using facilities such as the Structural Dynamics Laboratory for Verification and Validation (LVV) at the University of Sheffield to monitor the dynamic response and ‘health’ of structures, such as traffic loading, a full scale or near full scale.
 Source material: Brown (D.) (Jan. 7, 2019) “Cost of bridge maintenance backlog is £6.7bn”. (Accessed 02/15/2020).
Adapted from a University of Sheffield press release.