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...

Preventive-corrective contingency control of distribution power grids using convolutional neural networks

To achieve the goals on greenhouse gas emissions, the energy supply and demand is in transition. Distribution power grids therefore are increasingly reaching their capacity limits due to electrification and the vast increase of distributed energy resource (DER) connection requests with large peak power output. Increasing physical grid capacity...

A Framework for Optimal Sensor Placement to Support Structural Health Monitoring

Offshore or drydock inspection performed by trained surveyors is required within the integrity management of an in-service marine structure to ensure safety and fitness for purpose. However, these physical inspection activities can lead to a considerable increase in lifecycle cost and significant downtime, and they can impose hazards for the...

Design of robust terminal procedures: By optimization of arrival and departure trajectories

With the growth of the air traffic movements and the population of people living around airports, the number of awakenings due to aircraft noise has increased. ICAO has defined four research fields to reduce noise and one of them is implementation of noise abatement operational procedures. This includes different trajectory optimization methods,...

Precision Constrained Optimization by Exponential Ranking

Demonstrative results of a probabilistic constraint handling approach that is exclusively using evolutionary computation are presented. In contrast to other works involving the same probabilistic considerations, in this study local search has been omitted, in order to assess the necessity of this deterministic local search procedure in...

Further Note on the Probabilistic Constraint Handling

A robust probabilistic constraint handling approach in the framework of joint evolutionary-classical optimization has been presented earlier. In this work, the<br/>theoretical foundations of the method are presented in detail. The method is known as bi-objective method, where the conventional penalty function approach is implemented. The present...

A Generative Approach towards Performance-Based Design

Due to a growing number of regulations and standards, building performance becomes equally important as traditional design drivers. Therefore, it is necessary to quickly explore design alternatives that meet these performance requirements. To support this complex design task, a rule-based design system is proposed that is founded on a shape...

Design Tools for Integrative Planning

The performance of an architectural object is highly difficult to both define and measure in its complexity since it is integrating a constantly increasing amount of information, from concrete measurable characteristics to the subjective perception of individual users. The question arising though is how to predict the performance of a building...

The New Allotment: Optimizing Urban Agriculture with Evolutionary Algorithms

An update of the current allotment system in Den Haag on Scheveningen boulevard as a place where both tourist and residents can come to enjoy and learn about fresh produce and sustainable systems. This is an example of using the local conditions (sand) to develop a theme, growing in sand and sand art. The solution uses a powerful multi-objective...

Mathematical explorations in urban and regional design

A generic approach to a rout guidance strategy

The thesis presents a generic methodology able to generate optimal controlled dynamic prescriptive route guidance to be disseminated by means of variable message signs (VMS). The methodology is generic in the sense it can be used on any network topology, with any number of VMS's, for different scenario's (e.g. recurrent congestion or accidents),...