This project will develop novel bridge inspection and digital twin techniques. Digital twin models are created to represent the state and behavior of structures in a digital format. Computer vision techniques have recently been developed for the structural health monitoring of civil structures, including vibration displacement measurements, crack detection, and vibration characteristic identification. This project will investigate digital twin techniques aided by computer vision-based measurement.
Aim
This project aims to develop computer vision-assisted digital twin models for the structural health monitoring of civil engineering structures. These digital twin models will be used to interpret real-time information from videos and images—using computer vision techniques—into assessments of the structural health and safety of the infrastructure. The proposed technique will support targeted safety and maintenance recommendations for infrastructure monitoring and management.
Objectives
The objective of this project is to integrate novel vision and AI-based techniques into the development of digital twin models for structural health monitoring.
Significance
Digitising infrastructure has numerous significant benefits. For example, data from smart infrastructure can improve understanding of how end-users interact with the built environment, enhance risk diagnosis, and reduce maintenance time. It can also optimise infrastructure performance, support data-driven decision-making for resource allocation, and facilitate whole-of-lifecycle infrastructure asset management.
Ideal Candidate
- Full time enrolment, for both domestic and international students
- Minimum required: Bachelor degree (the first class honours or upper second class honours) in Civil Engineering, Structural Engineering or related fields
- Excellent written and verbal communication skills
- Strong computational, programming, algorithms, and data analysis skills
- Outstanding research skills and relevant experiences
- Applicants with Master degrees by research with technical publications and research experiences in structural dynamics and structural health monitoring, especially on computer vision, machine learning, deep learning, signal processing and data analysis techniques, are preferred.
Additionally, the applicants should meet the eligibility criteria for entry into a PhD program at Curtin University.
This project is open to Domestic applicants only.
Internship
Through this project you will also have an internship opportunity.
Scholarship
This scholarship provides a living stipend of $38,440 per annum, based on full-time studies, up to a maximum of three and a half years.
Applications close: 31st December 2026
Enquires and How to Apply
For enquires about this opportunity contact Professor Jun Li at junli@curtin.edu.au
To formally apply submit an Expression of Interest to Professor Jun Li before the application closing date.