5 Minute read
The deterioration of large infrastructure systems represents trillions of dollars in public and private domains worldwide. Currently, infrastructure asset managers face numerous challenges to maintain their assets. This includes the inability to predict residual service life of the offshore infrastructure assets as damage accumulation over time (for example, corrosion in marine environment) and identification of the appropriate time of intervention.
Applications for this project are no longer being accepted
In collaboration with the supervisors at KU Leuven, who are experts in ultrasound structural health monitoring and machine learning diagnostics and prognostics respectively, this PhD project will focus on predicting the residual service life of the critical offshore structures through theoretical modelling in conjunction with experiments involving unmanned vehicles (for example, drone and unmanned boat) and advanced non-destructive techniques (for example ultrasound, infrared thermography and IBIS-S radar). By developing innovative models for life-cycle structural performance of offshore structures, the research outcomes from this KU Leuven-UoM project have the potential to enable maintenance and capital works decisions that maximise return on resources allocated, while maintaining the performance of offshore structures.
- Deliver the first novel framework for predicting the impact of extreme environmental and operational conditions on UGW propagation characteristics in complex offshore structures. To accomplish this, a deep understanding of the change of UGW propagation characteristics in the presence of varying conditions such as humidity, pressure, salinity, and temperature is required.
- Deliver the first computational framework for accurately estimating structural damage signatures through a wave and finite element scheme under UGW interrogation. These signatures should be obtained within a few seconds’ time in order to enable training of the subsequent DL methodology.
- Deliver the first set of UGW measurements performed through Unmanned Vehicles on wind and tidal turbine blades operating over and underwater. The laboratory experiments will not only validate the developed wave-based computations, but also will serve to prove of the usefulness of the inversion scheme based on probabilistic deep learning. All these developments will provide the scientific community with a state-of-the-art SHM tool that can be used as a benchmark result for future research.
- Deliver the first probabilistic Deep Learning damage identification framework based on Bayesian neural networks. The framework fed through ultrafast UGW propagation and vibration-based predictions will provide real-time information about the damage signatures within a specified structural component under extreme (offshore) conditions and will rigorously detect and identify damage. Given the stochastic nature of the framework, it will also be able to provide the accompanied confidence intervals for each prediction, supplying complete information towards the optimal maintenance planning process.
The University of Melbourne: Associate Professor Lihai Zhang
KU Leuven: Associate Professor Dimitrios Chronopoulos
*Click on the researcher's name above to learn more about their publication and grant successes.
Who we are looking for
We are seeking a PhD candidate with the following skills:
- Demonstrated experience in the field of mechanical or infrastructure engineering.
- Demonstrated experience with scientific computation.
- Demonstrated ability to work independently and as part of a team.
- Demonstrated time and project management skills.
- Demonstrated ability to write research reports or other publications to a publishable standard (even if not published to date).
- Excellent written and oral communication skills.
- Demonstrated organisational skills, time management and ability to work to priorities.
- Demonstrated problem-solving abilities.
The PhD candidate will benefit from the combined expertise of the project supervisors, and the embedding into two research environments.
Associate Professor Dimitrios Chronopoulos is an expert in ultrasound and vibration-based digital-twin methodologies. These methodologies aim at identifying the health state of a structural system by quantifying and localising damaged areas on the system. His work mainly revolved around modelling ultrasound interaction with defects in complex composite and tessellated (3D printed) structures. A set of simulated signatures are numerically extracted for each assumed damage type. These signatures are then projected on experimental results in order to identify damage. Associate Professor Chronopoulos will provide training elements to No2Failure related to ultrasound modelling in complex structures and Bayesian methodologies for system identification.
Associate Professor Lihai Zhang is an expert in porous media mechanics and engineering reliability. By leading an Infrastructure Asset Protection & Management research group at The University of Melbourne, his research work mainly focuses on the reliability-based life-cycle assessment of built infrastructure, building cladding subject to hailstorm impact, corrosion of concrete in the marine environment, and structural health monitoring using non-destructive field testing methodology and unmanned vehicles (UV). His damage propagation expertise can be coupled as a natural extension to damage identification methodologies of KU Leuven to result in a holistic scheme for estimating the Remaining Useful Life (RUL) for a structural component. Associate Professor Zhang will provide training elements to No2Failure related to Damage initiation and propagation under defined loading envelopes in composite structures and) Acquiring monitoring data through non-permanently attached sensors and through unmanned vehicles (UVs).
This PhD project will be based at the University of Melbourne with a minimum 12-month stay at the KU Leuven.
The candidate will be enrolled in the PhD program at the Department of Infrastructure Engineering at the University of Melbourne and in the PhD program at the Faculty of Engineering Technology at KU Leuven.
Applications for this project are no longer being accepted
First published on 7 February 2022.
Share this article
How to apply
Apply for a joint PhD with the KU Leuven - Melbourne Joint PhD.
Discover what researchers from the KU Leuven - Melbourne Joint PhD are working on right now.
Your study experience
Discover what it's like to be a graduate researcher. Find out about University life, support services, and opportunities for skills development.
Find a supervisor or research project
Discover how to find a supervisor and learn how they can support your graduate research, or search available research projects.