Learning Interpretable Reduced-order Models for Jumping Quadrupeds

This work introduces a novel methodology for the development of interpretable reduced-order dynamic models specifically tailored for jumping quadruped robots. Leveraging Symbolic Regression combined with autoencoder neural networks, the framework autonomously derives symbolic equations from data and fundamental physics principles capturing the...

GNNs and Beam Dynamics: Investigation into the application of Graph Neural Networks to predict the dynamic behaviour of lattice beams

In the past decade, the application of Neural Networks (NNs) has received increasing interest due to the growth in computing power. In the field of computational mechanics, this has led to numerous publications presenting surrogate models to assist or replace conventional simulation methods. A subset of these networks, referred to as Graph...

Dynamic Modelling of A Rolling Piston Compressor Including A Packed-Bed Drying System

To produce an alternative fuel like Methanol from scratch, on a miniature scale- the reactants CO2 and H2O are sourced locally. Zero Emission Fuels B.V. (ZEF) does this by collecting carbon dioxide from the air, via carbon capture techniques and compressing it to high pressure of 55bars. As a consequence of humidity inside the captured CO2,...

Model-Driven Objective Functions in MPC using Economic Engineering Systems Theory: With an Application to Supply-Chain Scheduling at Shell

This thesis introduces a theory for model-driven objective functions in Model Predictive Control (MPC) algorithms. For scheduling supply chains, such model-driven objective functions allow the MPC algorithm to make optimal scheduling decisions by anticipating future changes in product flow and transfer price dynamics. Including such dynamics...

Dynamic Modelling of a Solid Oxide Fuel Cell System: Integration of 1-D SOFC Dynamic Model with the Balance of Plant components

The constant pressure on the maritime sector to reduce Greenhouse Gas (GHG) emissions has led the shipping industry to search for alternatives, such as zero-emissions propulsion systems, which would allow meeting the 2050 target imposed by International Maritime Organization (IMO) regulation. Fuel cells have demonstrated to substantially...

Closed loop wet scrubber system for maritime application: Dynamic modelling and system integration

The maritime sector is important for the facilitation and growth of global trade. Currently, about 90% of the goods are transported by ships and as a result, the number of ships has risen, increasing the emissions related to shipping. Pollution caused by exhaust gas, especially the sulphur oxide emission, from marine diesel engines has become a...

Sitting Up System: A novel concept for large integrated offshore wind turbine installation

It is expected by the EWEA that in the North Sea only the wind energy capacity will increase to 45 GW. In 2015 the capacity was only 5.2 GW. Offshore contractors should be capable of installing lots of turbines and just that is a problem. As turbines increase in size installation vessels need significant upgrades. Therefore, most contractors...

Dynamic model and preliminary design of a small-scale renewable methanol system

Zero Emission Fuels B.V. develops a standalone System that produces renewable methanol from air and sunlight. In this thesis the steady-state model of this System is replaced with a Simulation Tool that can predict its behaviour for every minute of a year. The goal is to verify how technical design parameters influence methanol production and to...

Selective Catalytic Reduction for Marine Applications: Dynamic Modelling and System Integration

Environmental regulations are continuously raising the bar towards more advanced diesel engine designs ca- pable of minimizing the emissions of polluting substances. The recent IMO Tier III legislation, entered into force in 2016, is forcing the engine manufacturers to meet a NOx reduction of more than 70% from Tier II for all the ships sailing...