Asset Health Digital twins for energy infrastructure

Summary

Energy infrastructure assets underpin modern economies, yet their serviceability and safety are frequently compromised by deterioration processes such as cracking, spalling, efflorescence, corrosion, and biological growth.

These defects increase maintenance costs and shorten service life, posing significant challenges for infrastructure asset management. While large-scale infrastructure owners increasingly adopt sensor-based monitoring systems, the majority of routine inspection in practice still relies on manual visual surveys, sometimes supplemented by non-destructive testing.

Such methods are well documented as subjective, labour-intensive, and inconsistent. Furthermore, traditional computer-vision methods have been explored for automating inspection, but their performance has proven inconsistent under real field conditions.

The advent of deep learning substantially advanced this field by introducing Convolutional Neural Networks (CNNs) that automatically extract multi-scale features and spatial context from images, greatly improving robustness and accuracy. Architectures such as U-Net, with its encoder–decoder structure, have achieved wide adoption for crack segmentation tasks.

These developments demonstrate the potential of deep learning to replace manual inspection with automated, data-driven approaches, yet significant challenges persist in benchmarking models systematically, validating them on both curated and field datasets, and extending their application to multi-defect detection where several deterioration types coexist.

This research aims to evaluate the effectiveness of deep-learning-based computer-vision models for structural health monitoring of the energy infrastructure assets, with particular emphasis on crack segmentation and multi-defect analysis.

The study advances the digital transformation of Structural Health Monitoring (SHM) in construction practice. The potential contribution is a unified benchmarking framework that provides practitioners with evidence-based guidance on the performance trade-offs between detection speed, segmentation accuracy, and field robustness.

The potential results include an automated image analysis that reduces reliance on subjective manual assessment, shorten inspection cycles, and generates structured spatial defect data to support maintenance prioritisation. In doing so, the study provides a practical foundation for deploying AI-enabled inspection in asset management, with demonstrated implications for site safety, operational efficiency, and carbon reduction.

Essential criteria

Applicants should hold, or expect to obtain, a First or Upper Second Class Honours Degree in a subject relevant to the proposed area of study.

We may also consider applications from those who hold equivalent qualifications, for example, a Lower Second Class Honours Degree plus a Master’s Degree with Distinction.

In exceptional circumstances, the University may consider a portfolio of evidence from applicants who have appropriate professional experience which is equivalent to the learning outcomes of an Honours degree in lieu of academic qualifications.

• Research proposal of no more than 2000 words detailing aims, objectives, milestones and methodology of the project

Equal Opportunities

The University is an equal opportunities employer and welcomes applicants from all sections of the community, particularly from those with disabilities.

Appointment will be made on merit.

Funding and eligibility

This project is funded by:

• Department for the Economy (DfE)
• Vice Chancellor's Research Scholarship (VCRS)

PhD Scholarships are available for this project and will cover:

• Tuition fees.
• A maintenance allowance of approximately £22,000 (exact rate is to be confirmed) per annum for three years, subject to satisfactory academic performance.
• A Research Training Support Grant (RTSG) of approximately £900 per annum.

To be eligible for these scholarships applicants must: be a UK or Irish national; or have pre-settled or settled status; or have indefinite leave to remain or enter.

Applicants should also meet the residency criteria which requires that they have lived in the EEA, Switzerland, the UK or Gibraltar for at least the three years preceding the start date of the research degree programme i.e. September 2027.

Applicants who already hold a doctoral degree or who have been registered on a programme of research leading to the award of a doctoral degree on a full-time basis for more than one year, or part-time equivalent, funded from any source, including self-financing students, are NOT eligible to apply for an award.

Students in full-time employment are not eligible for an award.

Due consideration should be given to financing your studies.

Part-time PhD scholarships may be available at a 0.5 pro rata rate of the full-time scholarship, which would require a six-year registration period.

The University will award a successful candidate one of the following scholarships for the project, depending on the funding available at the time an admissions offer is made:

1. Department for the Economy (DfE) PhD Scholarships
2. Vice Chancellor’s Research Scholarships (VCRS)

Please note that the Terms and Conditions for scholarships are subject to change for 2027/28.