Proportions of the energy dissipated during deformation of particulate materials are converted to heat and sound. The high-frequency (>10kHz) component of this sound energy is called acoustic emission (AE). AE monitoring offers the potential to sense particle-scale interactions that lead to macro-scale responses of granular materials. AE is widely used in many industries for non-destructive testing and evaluation of materials and systems; however, it is seldom used in geotechnical engineering, despite evidence of the benefits, because AE generated by particulate materials is highly complex and difficult to measure and interpret.
The aim of this PhD is to develop analytics for the automated interpretation of AE generated by geotechnical infrastructure assets. The objectives are: (1) to establish feature extraction and/or pattern recognition methodologies to quantify AE parameters; (2) to develop artificial intelligence analytics to convert AE input parameters to asset health statuses; and (3) to assess performance of the analytics using experiments.
Extensive datasets of AE measurements have been produced through series of controlled element (e.g. triaxial, direct-shear) and full-scale physical model (e.g. buried pipelines) tests. This PhD will exploit the existing datasets, and supplement them using new experiments.
The successful candidate will join the ‘Listening to Infrastructure’ research group, which is developing continuous, real-time acoustic emission (AE) monitoring systems that can be distributed across geotechnical infrastructure assets (e.g. buried pipelines, foundations, retaining structures) to sense soil and soil/structure interaction behaviour, and provide early warning that will enable targeted and timely interventions.
Applicants should have, or expect to achieve, at least a 2:1 Honours degree (or equivalent) in a relevant scientific or engineering discipline.
A relevant Master's degree and / or experience in one or more of the following will be an advantage: artificial intelligence, computer science, signal analysis