Global ETD Search
Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.
Results
Showing 1 to 18 of 18 for “"Surrogate modelling"”.
-
Aerodynamics and multi-fidelity surrogate modelling of an inverted wing with vortex generators in ground effect
… 2) computational study and 3) multi-fidelity surrogate modelling. <br/><br/>An experimental testing is performed in a wind tunnel equipped with a moving belt rig, studying time-averaged and unsteady aerodynamic characteristics. The experimental work performed shows that a use of vortex …
-
Approximation algorithms for rapid evaluation and optimization of architectural and civil structures
… of approximation algorithms, sometimes called surrogate modelling, in the early-stage design of structures. The use of approximation models to evaluate design performance scores rapidly could lead to a more in-depth exploration of a design space and its trade-offs and also aid in reducing the …
-
Predictive haemodynamics of the human carotid artery
… of the human carotid bifurcation. A Bayesian surrogate modelling technique is proposed and discrete locations in the CAD model are taken as random parameters to form inputs for the surrogate model. A metric, maximal wall shear stress (MWSS) is used as an output for constructing the surrogate …
-
Proper orthogonal decomposition & kriging strategies for design
The proliferation of surrogate modelling techniques have facilitated the application of expensive, high fidelity simulations within design optimisation. Taking considerably fewer function evaluations than direct global optimisation techniques, such as genetic algorithms, surrogate models attempt to …
-
Open-Source tools for practical heat integration and utility system evaluation
… strategy, and (2) a machine learning-based surrogate modelling approach for predicting utility system performance under new heat recovery or plant configurations. Together these contributions allow engineers to investigate multiple heat recovery options and accurately evaluate the …
-
Modelling on-domestic buildings energy performance using machine learning methods, a case study of the UK
… to high time-complexity of energy simulations. Surrogate modelling seems a promising alternative for simulation software, developing accurate energy prediction models requires an understanding of the building physics and a vision on the use of data-driven models. This study evaluated the …
-
Surrogate Model Assisted Nested Simulation with Applications to Variable Annuity Portfolio Valuation and Hedging
… In this thesis, we incorporate the idea of surrogate modelling to the nested simulation algorithm such that all of the input dimensions are reduced. The surrogate models act as proxies to approximate the input/output relationships. Since only a few input points are needed in order to …
-
Multi-Hazard Modelling of Dual Row Retaining Walls
… A combination of centrifuge and numerical modelling was utilised to investigate the problem. Studying the mechanics of the walls in dry sand from the soil stresses to the system displacements revealed the complex nature of the soil structure interaction. Increased wall flexibility can allow …
-
Simulation-based Design with Polynomial Ridge Approximations
… polynomial ridge approximations to construct surrogate models. These models enable rapid evaluations and facilitate a deeper, physically-intuitive understanding of the quantities of interest. For modelling smoothly varying functions, the use of orthogonal polynomials has seen considerable …
-
Machine Learning Force Fields for Modelling Reactions at Complex Interfaces
Computational modelling at the atomic scale has traditionally been constrained by a stark trade-off between accuracy and computational cost. Recently, machine learning (ML) architectures have been trained on highly accurate quantum mechanical calculations to sidestep this …
-
Incorporating sensor measurements using data assimilation and machine learning to improve the accuracy of thermal finite element models
… computational cost associated with such models, surrogate models are constructed. The construction of surrogate models involves a dimensionality reduction step in the form of proper orthogonal decomposition (POD), as well as a prediction step that involves the training of a data-driven model to …
-
Adaptive swarm optimisation assisted surrogate model for pipeline leak detection and characterisation.
… optic, pressure point analysis and numerical modelling, have been proposed during the last decades. One major issue of these methods is distinguishing the leak signal without giving false alarms. Considering that the data obtained by these traditional methods are digital in nature, the machine …
-
Statistical Surrogate Models for Robust Design Optimisation in Reduced Dimension
… and uncertain. This complexity is managed using surrogates to approximate the computational model underlying the black-box function. The system input variables may consist of immutable variables such as PDE source terms and design variables that can be varied to optimise the system. Traditional …
-
On the Evaluation of Common Design Metrics for the Optimization of Non-Axisymmetric Endwall Contours for a 1-stage Turbine Rotor
… with these meshes, the implementation of a surrogate modelling procedure in which part of this computational cost is offset by mathematical modelling, was necessary. Altogether, a total of 8 endwall designs were produced - 6 using a single metric each as the basis of their objective …
-
Seismic experimental analyses and surrogate models of multi-component systems in special-risk industrial facilities
… steel frame structure and the most recent surrogate-based UQ forward analysis advancements. Specifically, the framework is applied to a real-world application consisting of seismic shake table tests of a representative industrial multi-storey frame structure equipped with complex process …
-
Stochastic Ground Motion Models for Uncertainty Quantification in Earthquake Engineering
… forward UQ, the thesis also investigates using surrogate models as substitutes for computationally intensive models in UQEE. Specifically, active-learning-based surrogate models are explored for forward UQ analysis, with a focus on computing full distribution functions. A comprehensive study is …
-
Development of a process modelling methodology and condition monitoring platform for air-cooled condensers
… ambient conditions. This study focuses on modelling a utility-scale ACC system at steady-state conditions applying a 1-D network modelling approach and using a component-level discretization approach. This approach allowed for each cell to be modelled individually, accounting for steam duct …
-
Data-Driven Approaches in Water Pipe Condition Assessment and Failure Prediction
… techniques, numerical methods, and physical modelling to improve failure prediction and support proactive asset management. A key contribution of this work is the development of methods to address the common issue of class imbalance in pipe failure datasets. A semi-supervised clustering …