Funding
EPSRC Doctoral Training Partnership Studentship offering the award of fees, together with a tax-free maintenance grant of £19,237 per year for 3.5 years. An additional top up of £3,000 per year for 3.5 years is also available to previous graduates of the University of Leeds.
Lead Supervisor’s full name & email address
Professor Vasilis Sarhosis v.sarhosis@leeds.ac.uk
Co-supervisor name(s)
Professor David Connolly d.connolly@leeds.ac.uk
Professor Anthony Cohn a.g.cohn@leeds.ac.uk
Project summary
Recently, with the increasing global demand for mass transportation and freight, the maintenance of existing transport infrastructure has become important. Therefore, it is essential that railway infrastructure is reliable, cost-efficient, and provides a sustainable transportation mode. However, most of our existing railway infrastructure is ageing and requires continuous monitoring to keep them in service, which requires significant cost. Moreover, these structures are subjected to heavier axle loads, faster train speeds, and greater frequencies of trains, which have resulted in rapid deterioration over time. Apart from that, factors such as extreme variations in temperature, heavy rainfall and increased frequency of flood events due to climate change have introduced increased uncertainty in the long-term performance of such infrastructure assets. Hence, efficient and reliable infrastructure inspection and monitoring are needed to ensure these systems run smoothly at a reasonable cost.
This PhD aims to develop a framework for digital twinning (DT) of railway bridges and provide informed decisions for their repair and maintenance schemes. DT can be imagined here as a digital representation of a physical asset (i.e., a railway bridge) which serves as a ‘living’ digital simulation model and is enabled by the abundance of data (e.g., operational data acquired from the bridge) and advanced data processing and interpretation routines.
The proposed aim will be achieved using the following objectives:
* Development of three dimensional as is geometry of a bridge using photogrammetry and deep learning for defect detection, e.g., cracks;
* Development of a visualisation suite of data from sensors based on building information modelling;
* Development of a physics-based approach for assessing the structural behaviour of masonry arch bridges using high fidelity models;
* Development of real time statistical model for sensor data analysis;
* Development of data centric engineering approach through the construction of a framework for digital twinning for bridges.
* Please state your entry requirements plus any necessary or desired background
First or Upper Second Class UK Bachelor (Honours) or equivalent in a computer science, civil engineering or related background
Subject Area
Civil & Structural Engineering, Computer Science & IT, AI & Machine Learning
#J-18808-Ljbffr