Infrastructure Engineering - Theses
Permanent URI for this collection
Search Results
1 - 4 of 4
-
ItemDevelopment of efficient flood inundation modelling schemes using deep learning( 2022)Flood inundation models are one of the important tools used to manage flood-related risks in engineering practices such as infrastructure design, flooding disaster mitigation, and reservoir operations. Two-dimensional (2D) hydrodynamic models are commonly used in engineering applications because of their ability to provide robust estimates of flood inundation depth and extent at high temporal and spatial resolutions. However, due to the high computational costs, 2D models are not suited to many applications such as real-time ensemble flood inundation forecasting or uncertainty analysis. Therefore, many models have been developed based on simplified hydraulic rules such as considering only the conservation of water mass. These models are generally faster than 2D models but have reduced accuracy, which is a problem in many studies where a fine simulation timestep is needed or flow dynamics are significant. Recently, emulation models have been developed for fast flood inundation modelling using data-driven techniques including artificial neural networks, machine learning classification models, and deep learning. These computationally efficient emulation models are found to have comparable accuracy with 2D models when used to simulate flood inundation water level or depth provided with rainfall or streamflow discharge inputs. However, most emulation models simulate flood water/depth for each grid cell in the modelling domain separately, which would significantly increase the computational costs when applied for large domains. To add to that, these models have been found to have reduced accuracy in data-scarce regions on the floodplain. To improve the performance of emulation models, the objective of this thesis is to develop computationally efficient flood inundation models using deep learning and new spatial representation methods, that can be used for fast flood inundation simulation on floodplains with various characteristics at high spatial and temporal resolutions. The major contributions of this thesis include: (1) the development of an emulator for rapid flood inundation modelling which incorporates a novel spatial reduction and reconstruction (SRR) method as well as long short-term memory (LSTM) deep learning models to efficiently estimate flood inundation depth and extent; (2) the development of a Python program for the SRR method for flood surface representation; (3) the development of a U-Net-based spatial reduction and reconstruction (USRR) method and one-dimensional convolutional neural network (1D-CNN) models to emulate flood inundation on flat and complex floodplains. In addition, an input selection structure is developed and validated in the architecture of the LSTM models to simplify the model development process and to reduce the effort required for real-world applications. Also, a comparison is carried out for the performance of the combined approaches of the SRR method and LSTM models, as well as the USRR method and 1D-CNN models in an application to a flat and complex floodplain. The comparison demonstrates the advantages of using the USRR-1D-CNN emulator for rapid modelling of flood inundation on flat floodplains with complex flow paths, while the SRR-LSTM emulator is more computationally efficient and suitable for application to steep floodplains. The flood inundation modelling schemes developed in this thesis provide fast estimates of flood inundation surfaces without a material loss of accuracy compared to 2D hydrodynamic models, useful for applications such as ensemble real-time flood forecasting and flood risk analysis. They have the potential to deepen our understanding of the impacts of input uncertainty on temporal and spatial patterns of flood inundation, and to facilitate improved flood risk management.
-
ItemSHEAR BEHAVIOUR OF REINFORCED CONCRETE ELEMENTS: AN INSIGHT INTO SHEAR TRANSFER MECHANISMS IN CRACKED CONCRETE( 2022)Despite 70 years of investigations in understanding the shear behaviour of reinforced concrete members, it is again gaining attention among structural engineers as the recently issued Australian concrete design standard, AS 3600-2018, updated its shear provisions and ACI 318-19 unveiled its new one-way shear design equation. The shear behaviour of reinforced concrete elements is governed by several shear transfer mechanisms. Among them, the aggregate interlock is responsible for 50-70% of the ultimate shear transfer of cracked concrete elements. Despite its importance, a finite element model for shear transfer due to aggregate interlock considering realistic crack surfaces was still not developed. The complexity of developing a FE model lies due in the mesoscopic nature of the problem. In this study, a novel finite element approach is presented for evaluating shear transfer in crack concrete using realistic concrete crack surfaces. Concrete mesoscale models and zero-thickness cohesive elements were employed to develop the proposed method. Validation of the proposed FE models were conducted on two different experimental setups namely, small scale test and push-off test. The study comprises the evaluation of the surface roughness index of the cracked concrete surfaces. The proposed FE modeling approach demonstrated excellent performance against the most widely used analytical models and empirical equations for predicting the shear transfer in cracked concrete. Stress transfer in cracked concrete has been investigated since the 1970s, yet the existing code-based expressions for predicting shear transfer in cracked concrete were based on limited experimental data leading to insufficient prediction capabilities. Thus, this study further developed a machine learning-based framework for shear transfer in cracked concrete. The research outcomes present a novel finite element approach that is capable of evaluating stress transfer in cracked concrete and a machine learning-based framework to predict the maximum shear transfer in cracked reinforced concrete. The significance of the outcomes is that it enables to the evaluation of the stress transfer in crack concrete numerically while providing a clear pathway to solve the riddle of shear failures.
-
ItemDesign of novel high volume fly ash composites considering early age properties( 2021)As the environmental problems have attracted more and more attention over the recent years, the cement production in concrete industry has become a global concern. In the concrete construction industry, ordinary Portland cement (OPC), as an important binder in concrete, is identified to be the major cause of energy cost and carbon emissions Thus to reduce the environmental impact caused by the cement production, sustainable concrete with the use of less cement has become a necessity. Supplementary cementitious materials (SCMs) have been developed to be used as admixtures in concrete. Fly ash (FA) which is one of the most commonly used SCMs is a waste material from the combustion of coal in electricity stations. It has a large storage over the world and continues to be produced over time. However, the most significant problem of concrete with FA, especially large amount of FA, is the slow early age strength development. A comprehensive literature review on different properties of FA concrete are first provided including mechanical properties, setting time, heat of hydration, workability, self-compacting concrete, shrinkage and creep, several major durability properties (chloride ingress, sulfate attack, carbonation, alkali-silica reaction) and microstructure. Thus the general properties of FA concrete could be better understood. The hydration and strength properties of FA concrete are further investigated for concrete with the incorporation of FA from different regions. The FA were sourced from both Indonesia and Australia including Gladstone, Port Augusta and Bayswater. It was found that the main difference of the FA in different regions is the particle size distribution and the differences in chemical composition. Higher fineness of FA particles leads to higher hydration rate and strength. The degree of hydration and chemically bound water (WB) is linearly correlated with the compressive strength. To improve the early age strength of the overall high volume fly ash (HVFA) concrete mixes, The HVFA concrete mixes were optimized by improving the aggregate grading, reducing the water to binder (w/b) ratio and adjusting the paste to void volume ratio (Vp/Vv). It was found that the concrete mainly fail in pastes rather than aggregate. Thus, the early age strength of HVFA pastes by the adding of admixtures was especially determined. The admixtures used to improve the compressive strength of HVFA pastes were nano-CSH crystals, calcium formate (CF), and hydrated lime (HL). The underlying mechanism of how theses admixtures work in the pastes was investigated by hydration and microstructural testing approaches. It was found that the adding of single nano-CSH crystals, CF or HL could improve the compressive strength of HVFA pastes due to different mechanisms. However, the addition of combined CF and HL decreased the strength mainly due to cracks and pores caused by rapid hydration. As the adiabatic temperature rise is an important parameter that could significantly affect the properties of concrete, the adiabatic temperature rises of OPC and FA concrete were modelled from the heat of hydration curves. The accuracy of the modelling was successfully improved by the adjustment of hydration parameters. Finally, machine learning (ML), as a statistical tool, was used in this research to predict the compressive strength of HVFA composites with the addition of different admixtures. The accuracy of the model could be further improved by increasing the data sets.
-
ItemImproving building energy efficiency: biomimetic adaptive façade and computational data-driven approach( 2020)The urbanisation and population growth are resulting in a significant increase in energy consumption in buildings, leading to a substantial increase in greenhouse gas (GHG) emissions. During the operation of buildings, a massive amount of GHG emissions are released due to the process of building heating, cooling, and lighting, which accounts for the most significant proportion in building energy consumption. Therefore, energy-efficiency design and operation will play an essential role in reducing GHG emissions in buildings. Facade systems are one of the most critical aspects regarding the efficient management of heating, cooling, and lighting energy in buildings. A facade system is a barrier and exchanger (simultaneously) for temperature, light, and air between the building indoor environment and the outside environment. Therefore, the proper design and operation of the facade can effectively save substantial energy. For decades, engineers and researchers from all over the world have been in search for the intelligent design and operation of the facade systems to improve energy efficiency and sustainability in buildings, and to not compromise a pleasant indoor environment for building occupants. Subsequently, they have found that many natural systems have developed a highly efficient biological structure to adapt to dynamic and extreme environments over millions of years. These natural systems now have become great inspirations for the research community in the quest for building energy efficiency solutions, and the biomimetic adaptive facade (BAF) system is one of those remarkable examples of adopting bioinspiration in buildings. The BAF system is considered as a potential solution to improve the performance of conventional facade systems. The BAF system has an ability to adapt its functions, features, or behaviour for dynamically varying climatic conditions, providing buildings with the operational flexibility to act in response to different climate scenarios. Nonetheless, the practical application of a BAF in buildings remains limited due to the absence of a comprehensive design platform that can facilitate the widespread adoption of BAF systems. Most studies on BAFs remain at a conceptual stage of development, and an effective platform that can effectively assist the design and operation of BAF is still lacking. This thesis proposes and develops a methodology for enhancing building energy efficiency using the design of BAF systems, and thereby supports the transition to next-generation facades. Specifically, the objective of this thesis is to develop, test, and evaluate a computational data-driven optimisation approach in assisting the BAF design. The thesis presents a multidisciplinary approach that combines building energy modelling, metaheuristic optimisation, and data-driven methods. The goal of the proposed approach is to minimise the total energy consumption in buildings, including heating, cooling, and lighting energy, but still maintain the indoor environmental quality in terms of thermal and visual performance. A comprehensive analysis of the proposed computational data-driven optimisation approach is provided in the thesis. In summary, this study has proposed a computational data-driven approach based on building energy simulations, optimisation processes, and machine learning algorithms. The proposed approach is used to assist the design and operation of BAFs for building energy efficiency and analyse the interactions between energy-saving and indoor environmental quality. These significant findings demonstrate the potential of BAFs to enhance the energy efficiency of buildings, and the developed platform can be used as an effective tool to support BAFs in both design and product development.