In an urban context that needs to be constantly adapted to global crises, population movements, climate change and economic crises, designers and engineers strive to configure solutions that respond to multiple criteria. Within this framework, the concept of generative design is gaining more and more ground in the construction field, allowing rapid design space exploration, optimization and decision making for complex design problems. This thesis implements an experiment in a common design problem such as optimizing the topology of shell structures for structural performance, using an Artificial Intelligence Framework. To implement this experiment a novel dataset consisting of various mesh tessellations is created. The next step is to design a generative workflow that combines unsupervised and supervised learning along with a Gradient Descent Algorithm for pattern generation, structural performance estimation and optimization. A Variational Autoencoder is trained to generate new mesh tessellations and a Surrogate Model is used to predict the structural performance of the decoded designs. Finally, a Gradient Descent Algorithm searches the latent space of the Variational Autoencoder for optimum solutions. The results show that the proposed Artificial Intelligence workflow is able to generate novel and structurally better performing solutions that those existing in the training dataset. The findings of this thesis indicate that Artificial Intelligence can be successfully integrated into the concept of Generative Design to optimize shell structures.

This thesis is part of a larger ongoing research project at the TU Delft regarding structural glass as a novel construction material. Here, the focus is directed towards the casting of glass to create complex free-form geometries. Thus far, only smaller components have been created, but a multitude of previous student work explored how the current limitations in the fabrication process could be overcome by using topology optimization to design larger cast glass components. This thesis continues this research by integrating the limitations and remarks concluded from previous work to further explore the potential of designing large cast glass components using topology optimization. This thesis intends to contribute to the existing research by creating a tool for the design of 3D optimized cast glass components, which can take into consideration the structural properties of glass as well as manufacturing, annealing and specific design criteria. The tool is created in Matlab, using the SIMP optimization method with 8-noded hexahedral finite elements for the structural model. From the literature review it was concluded that the SIMP methodology is best suited the requirements of this project. For the structural model, 8-noded hexahedral elements were selected. Two algorithms were developed: one with a compliance based objective and a second with a volume based objective. The algorithm’s performance was tested on different domains. To facilitate comparison with existing literature, the algorithm was initially calibrated with a domain width of one element, effectively creating a two-dimensional optimization. Subsequently, its performance was assessed through the application of a small three-dimensional problem. Finally, the algorithm is used to design a case study involving the structural slab of a small pedestrian bridge located inside the British Museum. The results validate the benefits of the 3D algorithm. The geometries optimized in three dimensions have a higher structural stiffness and offer more spatial insight. Moreover, the volume optimizations results in a larger material reduction than those achieved in two-dimensional optimizations. For this reason, the volume-optimized component was selected for post-processing and implementation in the final design.

Climate change and extreme heat are critical issues which have been faced all over the world. Consequently, designers strive to monitor and assess the performance of facades by developing environmental assessments at the early design stages, since design changes do not require many resources. Rapid urban expansion in many parts of the world is leading to increased exposure to extreme natural hazards, exacerbated by climate change. It is essential to come up with strategies for mitigating the vulnerability of the built environment. The concept of thermal resilience and adaptation to climate change have gained ground and international attention in the Architecture, Engineering and Construction (AEC) industry. Resilience is a multi-facet property which defines the vulnerability of the built environment. Although the qualitative assessment of resilience value, the quantification of urban resilience is not yet representative enough and there is a lack of calculating the resilience in the built environment. However, designers are called to develop building and planning proposals with taking into consideration the thermal resilience of buildings against extreme hazards. This thesis aims to fill the gap between the qualitative and quantitative evaluation of thermal resilience in buildings by considering the operational building performance and the thermal performance of the building envelope in case of extreme heat waves. Towards this direction, the most influential parameters of thermal resilience are identified by implementing a sensitivity analysis process, in the first part. Secondly, a quantification method is presented and the thermal resilience performance for buildings in Amsterdam is calculated. Last, this thesis attempts to develop a computational workflow in order to assist designers and engineers in defining the thermal resilience index from the early design stage. Defining a less computational cost and time-consuming workflow is also a goal. Due to time limitations, the multi-facet aspect of resilience and the difficulty of quantification of its indicators, this research focuses on the ex-ante evaluation of the building envelope by identifying its vulnerability to extreme heat waves.

This thesis continues the investigation in the direction of exploring the potential regarding the use of Topology Optimization techniques for the design of cast glass structures. Previous theses in TU Delft have underlined the large potential for the design of these megaliths, but at the same time they have also underlined the strong limitations that derive from the use of commercial software as the tool for it. The limitations are directly related to the brittle nature of glass which results in significantly different behavior regarding its maximum tensile and compressive allowable limits. This renders fundamental to be able to evaluate both of these criteria during the optimization process. If this is not possible, as it was the case in the previous theses, a secondary (post-processing) phase should be integrated in the process in order to alleviate the peak stresses that may occur in the structure. This increases significantly the time and effort needed for the design and, therefore, it was underlined as an issue to be tackled in further exploration. This thesis aspires to address this problem with the creation of a customized optimization tool that takes all the structural constraints into consideration and, additionally, integrates the criteria specifically related to the glass manufacturing process, such as the overall annealing time needed. The tool is created in Matlab with the use of Finite Element Method equations in order to develop the structural model. The results of the structural analysis were validated through comparison with results obtained through ANSYS. The literature review covers a wide scope of topics. Firstly, the glass properties and the casting process are investigated in order to properly indicate the criteria and constraints that arise in every phase. The second part refers to topology optimization. A comparative review of the different algorithmic methodologies is realized and SIMP is selected as the most appropriate for the project. Additionally, the different categories of formulation for the optimization problem – stress, compliance and volume based – are discussed in order to select the appropriate objective and constraints. At the same time, a review of the previous theses is realized in order to indicate which method was used in every case and how the constraints were integrated in the process every time. In the end two different algorithms are developed based on two different problem formulations; one with compliance objective and a second one with volume objective. The aim is to investigate if the volume objective optimization can be a robust alternative to the classical compliance approach leading to more lightweight structures which at the same time fulfill the criteria regarding their feasibility to be manufactured. Firstly, the performance of the algorithm in relation to each objective and constraint individually is evaluated though application in a smaller scale benchmark problem. The results showed that all the setups work and, therefore, they can be used for the final design experiments. However, it also indicated that some constraints, such as stress, cannot be applied individually but they always have to be combined with another constraint that guides the optimization in order to lead in a reasonable result. Afterwards, a combination of objective and constraints for each of the two aforementioned formulations – compliance and volume - is tested and applied in the case study example which refers to a slab that serves as a small pedestrian bridge inside the British Museum. The results validate the estimation that a volume-based problem formulation can offer a robust result which resembles the result obtained from the traditional compliance-based formulation. Moreover, the result in the volume-based case is clearer and sharper and for this reason it was selected in the end for implementation in the final design. The formulation is then used in combination with different glass types, boundary conditions and design domain in order to conclude to the final shape of the slab.

The study of energy consumption across various building clusters offers a path to discerning intricate patterns and establishing energy efficiency metrics. However, these analyses have mostly been limited to small, controlled settings, leaving a vast potential for broader application in energy efficiency management and classification untapped. This research leverages machine learning models to determine gas consumption patterns and energy efficiency characteristics of buildings in real-life settings, based on a range of parameters including insulation properties and year of construction. The developed system was applied to a comprehensive dataset comprising eight distinct clusters of buildings, with a total of nearly 10,000 hourly gas consumption. To supplement the analysis, additional data was gathered concerning the building features. The findings indicate that the average gas consumption varies significantly across clusters, with dependencies shown for the age of the building, insulation characteristics, and building orientation The developed framework proved to be suitable for gaining insights into average gas consumption and usage patterns at a building level, non-intrusively and on a large scale. The additional data provided comparative insights between different building groups. The developed system can be easily expanded for other building characteristics and could be used to drive tailored feedback on energy efficiency improvements within buildings. This research paves the way for a more comprehensive approach to building energy efficiency, one that goes beyond the traditional parameters to include a broader set of variables such as building usage, occupant behavior,and heating system efficiency

This thesis explores the application of topology optimization for large-scale glass structures in architecture, addressing the limitations of traditional casting methods and exploring the potential of 3D printed glass. Previous research emphasized the importance of manufacturing methods, but highlighted the lack of transparency in topology optimized cast glass. This study uses 3D printing to overcome these challenges, focusing on the unique properties and manufacturing techniques of 3D printed glass, including the limitations of its brittle nature and different tensile and compressive strengths. An extensive literature review provides a foundation for glass properties, manufacturing techniques and the principles of topology optimization. The research advances the use of SIMP methodology and adapts it to 3D printed glass constraints such as overhang, path continuity and nozzle size. Therefore, it incorporates an adapted layer-to-layer overhang filter and addresses the island eect and path control using advanced computing techniques. The implementation of these methodologies is described in detail, with specific adjustments to the overhang angles and connection strategies for island structures. Testing within a predefined design domain evaluates the limitations and capabilities of the proposed solutions, culminating in the selection and 3D printing of a feasible design. The results validate the approach and highlight the need for further research, especially regarding the anisotropy of glass layers. This research is concluded with a discussion of the broader academic implications and future research opportunities, supported by additional insights and findings presented in the appendix. This work demonstrates significant advances in structural glass architecture and paves the way for innovative applications of 3D printed glass.

As the consumer electricity prices rise, European policymakers are increasingly focused on decarbonizing the power grid, which requires homeowners and local administrators to adopt renewable energy sources amidst a complex set of often conflicting objectives and constraints. This paper introduces an innovative application of deep reinforcement learning (DRL) for long-term strategic planning of rooftop photovoltaic systems and battery energy storage within the residential sector, aiming to balance environmental and financial objectives considering the ever-evolving system condition and uncertainties inherent in the market. The problem is modeled as a Markov Decision Process (MDP), facilitating sequential decision-making across 25 annual steps. The DRL environment incorporates a comprehensive set of variables identified through extensive literature review and market analysis. To account for their long-term dynamics, scenarios were simulated using appropriate stochastic and propabilistic processes for agent's training. A policy-based DRL agent is evaluated, exploring various residential and technological scenarios, including three single-family houses, different PV models and various optimisation scopes. Moreover, a deployment workflow and a user interface are developed to support real-world decision-making applications. Furthermore, a separate DRL model is crafted to simulate battery management system's charging and discharging protocol. The findings suggest that deep reinforcement learning offers a promising solution for addressing this complex problem. It offers enhanced flexibility in decision-making and helps mitigate investment risks.

As the consumer electricity prices rise, European policymakers are increasingly focused on decarbonizing the power grid, which requires homeowners and local administrators to adopt renewable energy sources amidst a complex set of often conflicting objectives and constraints. This paper introduces an innovative application of deep reinforcement learning (DRL) for long-term strategic planning of rooftop photovoltaic systems and battery energy storage within the residential sector, aiming to balance environmental and financial objectives considering the ever-evolving system condition and uncertainties inherent in the market. The problem is modeled as a Markov Decision Process (MDP), facilitating sequential decision-making across 25 annual steps. The DRL environment incorporates a comprehensive set of variables identified through extensive literature review and market analysis. To account for their long-term dynamics, scenarios were simulated using appropriate stochastic and propabilistic processes for agent's training. A policy-based DRL agent is evaluated, exploring various residential and technological scenarios, including three single-family houses, different PV models and various optimisation scopes. Moreover, a deployment workflow and a user interface are developed to support real-world decision-making applications. Furthermore, a separate DRL model is crafted to simulate battery management system's charging and discharging protocol. The findings suggest that deep reinforcement learning offers a promising solution for addressing this complex problem. It offers enhanced flexibility in decision-making and helps mitigate investment risks.

Across the world, countries are facing housing shortages and the Netherlands is no different. The increasing demand for new housing exceeds the growth rate of the architecture, engineering, and construction industry. Current solutions remain small in scale and therefore unsustainable. Multi-family housing is the optimal typology to address the housing shortage but the industry cannot design and build these projects fast enough. Automation can help. In 2016, Kevin Kelly[2016] reframed the conversation about automation, by stating "our most important mechanical inventions are not machines that do what humans do better, but machines that can do things we can't do at all." Humans cannot address the housing crisis alone, but automation through the application of deep learning models can bring well-designed spaces to everyone. Since the introduction of computers, architects have looked for ways to automate menial tasks. Some researchers even imagine a future where the machine becomes a partner to architects and designers, contributing to the design process. This ambition requires that the algorithms train themselves. Innovations in the field of deep learning have made this possible by allowing algorithms to train themselves through the use of artificial neural networks. When it comes to applying deep learning to generative design tasks, however, there is little research. The studies that have been done generate geometry that is small in size (64 x 64 x 64 voxels) and focuses on objects like chairs, not on buildings. 3D generative adversarial networks show promise for generating building geometry. By automating design, it is possible to apply expert knowledge on good design to all projects so everyone has access to well-designed buildings. This research aims to develop the architecture for a generative adversarial network that produces feasible building geometry. An important first step was identifying and pre-processing a data set that could be used for this purpose. The data set is released with the publication of this thesis so it can be used for further research. Through this thesis, the Improved 3D Wasserstein Generative Adversarial Network architecture has also been developed and documented. The research found that using a combination of Wasserstein loss with gradient penalty, Leaky ReLU activation functions in the generator and the critic, and the RMS Prop optimizer results in an architecture with stable training and outputs that are similar in size, shape, and proportion to the training data with minimal noise in the output. Performance of 3D Wasserstein generative adversarial networks with these hyperparameters was improved even further when using ten layers and a larger number of channels. The experiments concluded that generative adversarial networks can be used to generate building geometry and can be an area of continued research to improve generative design tools and support the automation of architectural design.

In the last decades, climate change is causing our environment to change rapidly, unprecedented in recent history. Civil engineering structures are dependent on the deteriorating environment they are situated in. Changes can cause an increase in loading due to, for example, extreme weather events or alter the structure’s resistance by, for instance, accelerated corrosion or an increase in the number of frost days. However, planning for such events depends significantly on the state of climate change, which is not considered in the sequential decision-making optimization for inspecting and maintaining our infrastructures. Sequential decision-making optimization refers to the process of finding an optimal sequence of actions to be performed to keep the structure safe. Optimality often refers to the plan with the lowest costs. Traditional inspection and maintenance plans seek a solution by applying heuristic-decision rules on, for instance, time- or condition constraints and fail to find an optimal solution. During the last decade, a new method called Deep Reinforcement Learning (DRL) has been applied and proven to find an optimal strategy to beat traditional approaches. Especially the ability of DRL to find an optimal solution for partially observable environments makes it a perfect candidate for the problem at hand. This thesis has developed a framework that incorporates partial observability over possible climate scenarios in the decision-making of engineering structures’ inspection and maintenance planning. The framework explains the steps required to translate a physical system towards a Partially Observable Markov Decision Process (POMDP), as the mathematical framework needed to seek an optimal se- quence of inspection and maintenance actions for. Then, it is explained how the POMDP can be used to find an optimal policy with a DRL algorithm, which includes benchmarking and testing the policy. A belief state has been incorporated over the climate scenarios to simulate the partial observability of the climate. Updating over the scenarios is provided by Bayesian Inference, using a climate parameter, such as temperature. The framework has been applied to a case study in the second part of the thesis. The case study con- figures a stochastic deterioration process for different climate scenarios. An optimal policy has been found by applying Proximal Policy Optimization (PPO) with a decentralized policy for the various com- ponents. Two well-established heuristic-based maintenance policies, time-based maintenance (TBM) and condition-based maintenance (CBM) have been configured as benchmarks for the framework. The framework is compared against the benchmarks using lifecycle costs and safety as metrics. The policy provided by the framework has outperformed both benchmarks in terms of costs while maintaining the same safety. The policy beat TBM with 5% and CBM with 1% in terms of lifecycle costs. Another important distinction is that the benchmarks are optimized for the climate scenarios, while the frame- work finds this distinction without prior knowledge. It is therefore concluded that the framework can find an optimal policy under the uncertainties related to climate change. The case study, however, does not fully capture the complexity of engineering structures that the framework can catch. It is therefore recommended to use the framework for a more complex structure in the future.

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. In this direction, smart and adaptive life-cycle inspection and maintenance planning are of paramount importance to reduce costs, increase structural reliability, and minimize resource-intensive interventions. Deep reinforcement learning provides a novel approach to strategize these decisions for systems subject to uncertainties and deterioration. The goal of this project is to determine optimal life-cycle inspection and maintenance policies for road networks. Road maintenance and inspection planning is a complex task, involving a multitude of different objectives, such as the minimization of lifecycle cost and CO2 emissions (both from the maintenance works and vehicle emissions). However, current literature has underestimated the importance of optimizing for multiple objectives, and doesn’t consider the environmental impact during planning. In the current project, we aim to optimize the maintenance and inspection schedule with respect to minimizing the maintenance costs, carbon emissions and vehicle owners costs at the same time. To achieve that, a multi-objective road network environment will be modelled and multiple multi-objective Deep Reinforcement learning approaches will be applied and compared to traditional life-cycle management policies.

Early design choices in building shape and fenestration significantly influ- ence the yearly daylight performance of office buildings. Annual daylight performance must be analyzed at the conceptual design stage to support building form and fenestration design decisions. However, the simulation modeling and daylight calculations necessary for the annual daylight fore- cast are extraordinarily time-consuming, which negatively influences its early design viability. Machine learning-based methods that experimentally learn from simulation-derived data have been implemented to decrease the time of daylight simulations. We concentrate on the visual comfort of working en- vironments. This particular sort of area demands more visual comfort than others. Four machine-learning methods are compared concerning their appli- cability in spatial daylight autonomy, annual sunlight exposure, and spatially disturbing glare. This research proposes a machine learning-based modeling strategy for predicting yearly daylight performance early in the design stage. The developed prediction model results for the sDA(Spatial Daylight Auton- omy), ASE (Annual Sunlight exposure), and sDG(Spatial Disturbing Glare) settings. After comparing the models for each output the best chosen model attained R2 scores of 0.85, 0.65, and 0.26 and MAE scores of 3.33, 22.5, and 22.16, respectively.

An issue of utmost significance constitutes the maintenance of engineering systems exposed to corrosive environments, e.g. coastal and marine environments, highly acidic environments, etc. The most beneficial sequence of maintenance decisions, i.e. the one that corresponds to the minimum maintenance cost, can be sought as the solution to an optimization problem. Owing to the high complexity of this sequential decision optimization problem, traditional methods such as thresholdbased approaches, fail to arrive at an optimal strategy, while at the same time the commonly used offline knowledge about the environment can not capture efficiently the stochastic way in which an engineering system deteriorates. Over the last few years, Deep Reinforcement Learning (DRL) has been proven a promising tool to tackle such problems, being often limited though by the dimensionality curse and the implications caused by large state and action spaces, an issue which leads to simplifications like their discretization. Bayesian principles and model updating are the most widely used tools to model accurately systems with high uncertainty, by incorporating data acquired through monitoring devices and thus improving the knowledge about the stochastic system. This research proposes an integrated framework that aims to determine an optimal sequence of maintenance decisions over the lifespan of deteriorating engineering systems, combining the aforementioned core concepts of Deep Reinforcement Learning (DRL) and Bayesian Model Updating (BMU). More specifically, it investigates different Deep Reinforcement Learning (DRL) algorithms, namely Double Deep Q-Network (DDQN), Advantage Actor Critic (A2C), and Proximal Policy Optimization (PPO), while the updating of the uncertain parameters is performed through sampling, i.e. No-U-Turn Sampler (NUTS). All these tools will be first applied to elementary problems for the sake of verification and validation, while the culmination of this research is the application of the framework on a more realistic and complicated, multi-component structure. The obtained results are compared with benchmark performances to properly showcase the efficiency and the weaknesses of the tool.

Energy use, CO2 emissions, and waste production are all significant causes of environmental issues. The building sector is a major contributor to these problems, specifically the manufacturing of (structural) steel elements. Application of reuse and/or remanufacturing, as done in a circular economy, will reduce these effects. Therefore, these techniques must to be taken into account while designing buildings and structures. However, as actors in the construction industry recognize barriers, such as time delays in the early phases of the design process, these tactics are not yet commonly used. Nonetheless, reusing structural steel components is still favoured by structural engineers, particularly when the aforementioned obstacles can be removed. This is feasible with the use of computational tools. In this thesis, an AI based deep generative design framework is developed to optimize a 3D spatial truss structure for structural performance, material use and similarity to a defined stock of reusable materials. This workflow consist of a labelled dataset of geometries and performance indicators, a variational autoencoder (VAE), a predictive surrogate model and optimization through gradient descent. The aim of this study is to gain insight into the extent to which such a workflow can be applied in early-stage architectural and structural design exploration, especially with regards to making circular design & reuse more feasible. The case study in this thesis is a spatial truss structure supporting a flat roof. It was found that a surrogate model can be successfully trained to predict the performance of a geometry. For this, various input data representations can be used, including adjacency matrices and edge-vertex matrices. Through training of a VAE, a latent space from which meshes could be generated was successfully constructed. The VAE was able to accurately reconstruct a significant part of the geometry dataset. Through gradient descent, novel meshes were generated. Predicted performance of these meshes was increased. After assessing performance with simulations and calculations, increases in performance often remained. The largest performance increase found was 74.2%. Minor editing of meshes based on user insight demonstrated further increase in mesh performance.