Pages
 1
 2
 document

van Leeuwen, Elske (author)Computational Fluid Dynamics (CFD) is the main tool to use in industry and engineering problems including turbulent flows. Turbulence modeling relies on solving the NavierStokes equations. Solving these equations directly takes a lot of time and computational power. More affordable methods solve the Reynolds Averaged NavierStokes (RANS)...master thesis 2022
 document

Hemmes, Jasper (author)When simulating fluids the industry standard is Reynolds averaged NavierStokes (RANS). However, the results for certain flows are inaccurate. The main source of error in popular RANS turbulence models is the Boussinesq approximation, assuming a linear relationship between the Reynolds stress anisotropy and the mean rate of strain. Experiments...master thesis 2022
 document

Zhou, H. (author)Applying deep neural networks (DNNs) for system identification (SYSID) has attracted more andmore attention in recent years. The DNNs, which have universal approximation capabilities for any measurable function, have been successfully implemented in SYSID tasks with typical network structures, e.g., feedforward neural networks and recurrent...doctoral thesis 2022
 document

Liu, D. (author), Virgolin, Marco (author), Alderliesten, T. (author), Bosman, P.A.N. (author)Genetic programming (GP) is one of the best approaches today to discover symbolic regression models. To find models that trade off accuracy and complexity, the nondominated sorting genetic algorithm II (NSGAII) is widely used. Unfortunately, it has been shown that NSGAII can be inefficient: in early generations, lowcomplexity models over...conference paper 2022
 document

Harrison, J. (author), Alderliesten, T. (author), Bosman, P.A.N. (author)Genetic Programming (GP) can make an important contribution to explainable artificial intelligence because it can create symbolic expressions as machine learning models. Nevertheless, to be explainable, the expressions must not become too large. This may, however, limit their potential to be accurate. The reuse of subexpressions has the...conference paper 2022
 document

Kramer, O.J.I. (author)In drinking water treatment plants, multiphase flows are a frequent phenomenon. Examples of such flows are pelletsoftening and filter backwashing where liquidsolid fluidisation is applied. A better grasp of these fluidisation processes is needed to be able to determine optimal hydraulic states. In this research, models were developed, and...doctoral thesis 2021
 document

Kubalik, Jiri (author), Derner, Erik (author), Zegklitz, Jan (author), Babuska, R. (author)Reinforcement learning algorithms can solve dynamic decisionmaking and optimal control problems. With continuousvalued state and input variables, reinforcement learning algorithms must rely on function approximators to represent the value function and policy mappings. Commonly used numerical approximators, such as neural networks or basis...journal article 2021
 document

Kubalík, Jiří (author), Derner, Erik (author), Babuska, R. (author)Virtually all dynamic system control methods benefit from the availability of an accurate mathematical model of the system. This includes also methods like reinforcement learning, which can be vastly sped up and made safer by using a dynamic system model. However, obtaining a sufficient amount of informative data for constructing dynamic...journal article 2021
 document

Derner, Erik (author), Kubalik, Jiri (author), Babuska, R. (author)Continual model learning for nonlinear dynamic systems, such as autonomous robots, presents several challenges. First, it tends to be computationally expensive as the amount of data collected by the robot quickly grows in time. Second, the model accuracy is impaired when data from repetitive motions prevail in the training set and outweigh...journal article 2021
 document

Huijing, Jasper P. (author), Dwight, R.P. (author), Schmelzer, M. (author)In this short note we apply the recently proposed datadriven RANS closure modelling framework of Schmelzer et al.(2020) to fully threedimensional, high Reynolds number flows: namely wallmounted cubes and cuboids at Re=40,000, and a cylinder at Re=140,000. For each flow, a new RANS closure is generated using sparse symbolic regression based...journal article 2021
 document

Lingmont, Hidde (author)The advent of machine learning and the availability of big data brought a novel approach for researchers to discover fundamental laws of motion. Computers allow to quickly find underlying physical laws from experimental data, without having indepth knowledge of the system. Applications are widespread among numerous fields such as physics,...master thesis 2020
 document

Goderie, M.W. (author)Wind turbine wakes cause significant reductions in power production and increased fatigue damage for downwind turbines. Thus, they affect the wind levelized cost of energy. Computational Fluid Dynamics (CFD) can be used to quantify the wake characteristics, whereby Reynoldsaveraged NavierStokes (RANS) has the most potential for industrial...master thesis 2020
 document

Nieuwenhuisen, Kyle (author)Adverse pressure gradients, separation and other forms of nonequilibrium flows are often encountered in flows of interest. In these type of flows, the Boussinesq hypothesis does not hold and often leads to erroneous predictions by eddy viscosity models. In an attempt to capture these nonequilibrium effects, lag parameter models introduce a lag...master thesis 2020
 document

Schmelzer, M. (author), Dwight, R.P. (author), Cinnella, Paola (author)In this work recent advancements are presented in utilising deterministic symbolic regression to infer algebraic models for turbulent stressstrain relation with sparsitypromoting regression techniques. The goal is to build a functional expression from a set of candidate functions in order to represent the target data most accurately....conference paper 2020
 document

Derner, Erik (author), Kubalík, Jiří (author), Ancona, N. (author), Babuska, R. (author)Developing mathematical models of dynamic systems is central to many disciplines of engineering and science. Models facilitate simulations, analysis of the system's behavior, decision making and design of automatic control algorithms. Even inherently modelfree control techniques such as reinforcement learning (RL) have been shown to benefit...journal article 2020
 document

Kubalik, Jiai (author), Derner, Erik (author), Babuska, R. (author)In symbolic regression, the search for analytic models is typically driven purely by the prediction error observed on the training data samples. However, when the data samples do not sufficiently cover the input space, the prediction error does not provide sufficient guidance toward desired models. Standard symbolic regression techniques then...conference paper 2020
 document

Schmelzer, M. (author), Dwight, R.P. (author), Cinnella, Paola (author)A novel deterministic symbolic regression method SpaRTA (Sparse Regression of Turbulent Stress Anisotropy) is introduced to infer algebraic stress models for the closure of RANS equations directly from highfidelity LES or DNS data. The models are written as tensor polynomials and are built from a library of candidate functions. The machine...journal article 2019
 document

Kramer, O.J.I. (author), El Hasadi, Yousef M.F. (author), de Moel, P.J. (author), Baars, Eric T. (author), Padding, J.T. (author), van der Hoek, J.P. (author)For an accurate prediction of the porosity of a liquidsolid homogenous fluidized bed, various empirical prediction models have been developed. Symbolic regression machine learning techniques are suitable for analyzing experimental fluidization data to produce empirical expressions for porosity as a function not only of fluid velocity and...conference paper 2019
 document

Märtens, M. (author)This thesis is a contribution to a deeper understanding of how information propagates and what this process entails. At its very core is the concept of the network: a collection of nodes and links, which describes the structure of the systems under investigation. The network is a mathematical model which allows to focus on a very fundamental...doctoral thesis 2018
 document

Kubalík, Jiří (author), Alibekov, Eduard (author), Babuska, R. (author)Modelbased reinforcement learning (RL) algorithms can be used to derive optimal control laws for nonlinear dynamic systems. With continuousvalued state and input variables, RL algorithms have to rely on function approximators to represent the value function and policy mappings. This paper addresses the problem of finding a smooth policy...journal article 2017
Pages
 1
 2