ORCID Profile
0000-0003-0415-4798
Current Organisation
University of Melbourne
Does something not look right? The information on this page has been harvested from data sources that may not be up to date. We continue to work with information providers to improve coverage and quality. To report an issue, use the Feedback Form.
In Research Link Australia (RLA), "Research Topics" refer to ANZSRC FOR and SEO codes. These topics are either sourced from ANZSRC FOR and SEO codes listed in researchers' related grants or generated by a large language model (LLM) based on their publications.
Structural engineering | Civil engineering | Civil Engineering | Construction materials | Structural Engineering | Construction Materials |
Hydrogen Storage | Construction Materials Performance and Processes not elsewhere classified
Publisher: American Society of Civil Engineers (ASCE)
Date: 03-2020
Publisher: Wiley
Date: 16-11-2018
DOI: 10.1111/MICE.12422
Publisher: SAGE Publications
Date: 28-02-2022
DOI: 10.1177/14759217211068859
Abstract: Cracks in concrete structures are one of the most important indicators of structural damage, and it is a necessity to detect and measure cracks for ensuring safety and integrity of concrete structures. The widely practised approach in inspecting the structures is by performing visual inspections followed by manual estimation of crack widths. This approach is not only time-consuming, laborious, and time-intensive but also prone to subjective errors and inefficient. To address these issues, we propose a novel deep learning framework for detecting cracks and then estimating crack widths in concrete surface images. Our framework handles both small- and large-sized images and provides a prediction of crack width at locations specified by the user. The proposed framework uses Attention Recurrent Residual U-Net (Attention R2U-Net) with Random Forest regressor to predict crack width with the mean prediction error of ±0.31 mm for crack widths varying from 0 to 8.95 mm and produces the lowest absolute maximum error of 1.3 mm. Our model has a coefficient of determination ( R 2 ) of 0.91, showing a non-linear mapping function with low prediction errors. We compare our model with a combination of four other segmentation models and regression models. Our proposed model has superior performance compared to other models, and one can easily adopt our framework to a variety of Structural Health Monitoring applications using Internet of Things sensors.
Publisher: Elsevier BV
Date: 11-2017
Publisher: Elsevier BV
Date: 11-2018
Publisher: Elsevier BV
Date: 02-2019
Publisher: Elsevier BV
Date: 11-2015
Publisher: SAGE Publications
Date: 11-2021
Abstract: With the growing number of aging infrastructure across the world, there is a high demand for a more effective inspection method to assess its conditions. Routine assessment of structural conditions is a necessity to ensure the safety and operation of critical infrastructure. However, the current practice to detect structural damages, such as cracks, depends on human visual observation methods, which are prone to efficiency, cost, and safety concerns. In this article, we present an automated detection method, which is based on convolutional neural network models and a non-overlapping window-based approach, to detect crack/non-crack conditions of concrete structures from images. To this end, we construct a data set of crack/non-crack concrete structures, comprising 32,704 training patches, 2074 validation patches, and 6032 test patches. We evaluate the performance of our approach using 15 state-of-the-art convolutional neural network models in terms of number of parameters required to train the models, area under the curve, and inference time. Our approach provides over 95% accuracy and over 87% precision in detecting the cracks for most of the convolutional neural network models. We also show that our approach outperforms existing models in literature in terms of accuracy and inference time. The best performance in terms of area under the curve was achieved by visual geometry group-16 model (area under the curve = 0.9805) and best inference time was provided by AlexNet (0.32 s per image in size of 256 × 256 × 3). Our evaluation shows that deeper convolutional neural network models have higher detection accuracies however, they also require more parameters and have higher inference time. We believe that this study would act as a benchmark for real-time, automated crack detection for condition assessment of infrastructure.
Publisher: Elsevier BV
Date: 10-2019
Publisher: Elsevier BV
Date: 12-2015
Publisher: Elsevier BV
Date: 02-2017
Publisher: Elsevier BV
Date: 05-2016
Publisher: Thomas Telford Ltd.
Date: 02-2020
Abstract: Lightweight concrete foam is mainly used as a filling for sandwich panels for insulation of buildings. Surfactants are chemical admixtures that play an important role in stabilising the air pores in fresh concrete foam before stiffening. This study investigates the effects of surfactants on the microstructure and pore characteristics of concrete foam analysed by X-ray microtomography. The formation of larger pores due to poor stability of bubbles in the concrete foam is directly related to a substantial reduction of compressive strength. Anionic (negatively charged) surfactants produce a stable aqueous foam. However, in the presence of cement particles, the majority of anionic surfactants adsorb on positively charged sites of cement particles. As the result of considerable migration of surfactants from the air–liquid interface of bubbles, the concrete foam is destabilised. Therefore, a surfactant that can generate a stable foam (with water only) may not be able to generate a stable concrete foam. A combination of an anionic and a non-ionic (neutral) surfactant reduced the maximum pore diameter from 1·84 mm to 1·49 mm and increased strength by 25% compared to the concrete foam stabilised by anionic surfactants alone.
Publisher: Elsevier BV
Date: 2020
Publisher: MDPI AG
Date: 29-04-2023
DOI: 10.3390/BUILDINGS13051186
Abstract: The wood industry faces the dual requirements of improving the quality of timber products and minimising waste during the manufacturing process. The finger joint, which is an end-to-end joining method for timber boards, is one of the most important aspects of engineering wood products. This study presents a numerical and optimisation investigation of the effects of finger-joint design parameters on the flexural behaviour of finger-jointed timber beams. A numerical model based on advanced three-dimensional finite element analysis was developed to model the behaviour of finger-jointed beams. Using the validated finite element (FE) model and automated parameterisation, a parametric study was conducted to assess the impact of each design parameter of the finger joint, including finger length, tip thickness, and the number of finger joints. The results indicate that the number of fingers and finger length significantly influence the maximum load capacity, while the tip thickness has a marginal effect on performance. This study identifies a design threshold of five fingers and a 14 mm finger length for achieving efficient, high-performance finger-joint designs. In addition, the multi-objective modified firefly algorithm (MOMFA) was proposed to maximise the finger joint resistance while simultaneously minimising the material waste. The optimisation shows that there will be a significant amount of wood waste when using traditional single-objective optimisation that only focuses on structural performance. In contrast, the proposed method achieves comparable load capacity while significantly reducing waste (up to 53.31%) during the joining process. The automated finite element modelling framework and holistic optimisation developed in this study can be used to design and optimise engineering wood products for construction applications.
Publisher: Elsevier BV
Date: 09-2017
Publisher: Informa UK Limited
Date: 05-2014
Publisher: Elsevier BV
Date: 08-2018
Publisher: Elsevier BV
Date: 11-2022
Publisher: Elsevier BV
Date: 2017
Publisher: Elsevier BV
Date: 05-2023
Publisher: Elsevier BV
Date: 2023
Publisher: Elsevier BV
Date: 11-2022
Start Date: 2024
End Date: 12-2026
Amount: $439,847.00
Funder: Australian Research Council
View Funded ActivityStart Date: 2023
End Date: 12-2025
Amount: $545,173.00
Funder: Australian Research Council
View Funded ActivityStart Date: 10-2022
End Date: 10-2025
Amount: $485,000.00
Funder: Australian Research Council
View Funded Activity