Multi-objective Deep Reinforcement Learning for predictive maintenance of road networks

Operation and maintenance of the built environment have a major effect on socioeconomic stability and sustainability. A significant part of our built world approaches or has well exceeded its designated structural life. As engineers, we need to find efficient ways to extend this life while maintaining acceptable levels of safety and performance....

A surrogate-assisted evolutionary algorithm based on inverse distance weighting: Applied to a multi-objective deformable image registration problem

Solutions to many real-life optimization problems take a long time to evaluate. This limits the number of solutions we can evaluate. When optimizing with an Evolutionary Algorithm (EA) a frequently used approach is to approximate the objective using a surrogate function, replacing the time-consuming real evaluation. This surrogate model is...

Techno-economic analysis of hydrogen fuelling supply chains: System integration of mobility sector and power grid including renewable energy generation

Ambitious decarbonization targets are introduced to combat climate change. According to the European Commission, sector coupling is required to achieve these targets. This includes the inclusion of renewables into sectors that are difficult to decarbonize, but also using resources more efficient, and introducing new clean fuels. Recent research...

Multi-sector Water Allocation: The impact of nonlinear approximation network hyperparameters for multi-objective reservoir control

Automatic Controller Selection on a Humanoid Robot: Using Optimization Techniques

Designing controllers for complex robots is not an easy task. Often, researchers hand-tune controllers for humanoid robots, but this is a time-consuming approach that yields a single controller which cannot generalize well to varied tasks. This thesis presents a method which uses the NSGA-II multi-objective optimization (MOO) algorithm with...

Hierarchical Model Predictive Control in Building Climate Systems for Passive Energy Sources

There is an urgent need for technical innovations in the construction industry to meet the European Parliament’s qualifications for reducing the energy footprint of buildings. This thesis is devoted to conducting research on control strategies that optimally manage passive energy sources, e.g., natural ventilation and solar irradiance, in...

Multi-Objective Trajectory Optimization for a Scaled Vehicle

The introduction of control systems in the automotive industry has significantly increased safety. Improved control over the vehicle dynamics has been shown to contribute to substantial reductions in the number of deaths and serious injuries resulting from road traffic crashes. The introduction of Electronic Stability Control yielded impressive...

Designing a future regional energy system: multi-objective optimization of a regional energy system from a multi-actor perspective

The energy system is undergoing a grand transition. In 2019, the Dutch government presented the national climate accord stating that in 2030, 70% of all energy needs to come from a renewable source. In this accord, strong emphasis is put on a regional approach to the energy transition. Across the country, regions are picking up the gauntlet and...

Decarbonisation of the Dutch Container Glass Industry by 2050: A Model-based Analysis of Technology Options

The Dutch container glass industry is an energy- and capital-intensive industry which accounts for about 350 kt of carbon dioxide (CO2) emissions on an annual basis. The fluctuating energy prices during the past decades as well as the implementation of the European Emission trading scheme (ETS) are pushing towards the deep decarbonisation of...

Co-orbital motion and its application to JAXA's MMX mission

In the framework of JAXA's MMX mission to explore the Martian moon of Phobos, an analysis of the stability of three-dimensional quasi-satellite orbits in the Mars-Phobos circular restricted three-body problem was conducted. For this analysis, notions of co-orbital motion, interpreted as the slow motion of the guiding center of the trajectory...

Investigation of a semi-closed cycle small gas turbine for high altitude UAV propulsion

Current unmanned aerial vehicles (UAVs) are limited in operating altitude and endurance by the maximum attainable performance of small gas turbine engines. While improvements in the cycle thermal efficiency can be obtained through the introduction of heat exchangers, the consequent increase in engine weight partially offsets the benefits gained...

Visual Analytics for Generative Design Exploration: An interactive 3D data envirionment for a computational design system facilitating the performance-driven design process of a nearly Zero-Energy sports hall

Improvement of design performances requires exploration of a larger amount of analyzed design solutions in the early design phase. Computational design systems use parametric modeling, building performance simulations and genetic algorithms to iterate through a large amount of design alternatives, converging towards optimal design solutions....

Multi-objective project portfolio optimization: Application in railway infrastructure networks

Investment projects in railway infrastructure networks are needed to maintain a high condition of the network, maximize the capacity of the network, and to keep the risk low. Railway organizations are aiming to achieve these goals, but also want to minimize the costs of the investments. The desires of stakeholders in railway networks such as the...

Graded Structures: The design of a grid shell that uses gradual densification to enhance the performance of the overall structure

This graduation thesis aimed to find an answer to the following question: 'How to design a grid shell for the canopy of a stadium that uses performance based densification to enhance the performance of the structure?'. De Nieuwe Kuip in Rotterdam is used as a case study to put the findings into practice. In order to answer this question a...

Hybrid Optimization of Low-Thrust Many-Revolution Trajectories with Coasting Arcs and Longitude Targeting for Propellant Minimization

Electric Propulsion (EP) has become one of the most efficient technologies for spacecraft propulsion. In contrast to conventional chemical propulsion, the low thrust force generated by EP thrusters can deliver a momentum transfer to the spacecraft that is up to twenty times greater, for an equivalent propellant expenditure. Despite decades of...