Stages Of Building Design Research Articles

Developing surrogate models for the early-stage design of residential blocks using graph neural networks

Abstract Building simulation based on physical modeling is commonly adopted for performance prediction, but the high time costs hinder its application in the early design stage of buildings. Data-driven surrogate models have been proposed as a means to replicate computationally expensive simulation models. However, existing surrogate models for sustainable residential block design are limited in scope, focusing either on individual buildings or on specific cases within multi-block projects. This study leverages graph neural networks to develop optimal surrogate models incorporating inter-building effects to predict multiple indicators of sustainable performance for residential blocks at a region level. A graph schema is proposed to represent the general geometric features and relations among buildings in residential block design. A regional dataset is generated for model training and testing, using real residential zones in Hong Kong. The surrogate models are developed and evaluated, using two kinds of architectures (individual architectures for specific indicators and an integrative architecture) and three different neural networks (graph attention network (GAT), graph convolutional network, and artificial neural network). The results showed that the surrogate models using the individual architectures and GAT outperform the models using other architectures and neural networks. These surrogate models achieve a high prediction accuracy with CV(RMSE)s of 11.79%, 7.63%, and 8.00% in terms of energy consumption, indoor thermal comfort, and daylighting, respectively, on the regional test set. Moreover, they enable a significant acceleration of the performance evaluation, reducing the calculation time from 6.346 min to 1.565 ms (243,297 times) per case compared to physics-based simulations.

A geometry-based decomposition method for energy prediction in early design stages of residential buildings

PurposeThe purpose of the study is to develop a geometry-based energy estimation method for surrogate and metamodels to be used in the early design phase of buildings.Design/methodology/approachOptimizing building form and design variables in the early stages of the architectural design process, particularly during the conceptual phase, can significantly enhance overall design performance and energy efficiency at minimal cost. This study introduces a novel decomposition method for evaluating building energy performance by simplifying complex building forms into basic geometric shapes.FindingsThe developed method is applied to certain cases of design variation under specified boundary conditions, and the accuracy of heating and cooling energy loads is calculated with simulated energy models of these cases. As a result of the calculation, accuracy rates between 84.30 and 99.98% were founded.Originality/valueThis paper proposes a prediction model with a geometric identification method for an innovative geometry-based surrogate modeling method. This method also provides a way for artificial intelligence-based prediction models used in surrogate models to create a dataset and can be used in the training in future works.

Optimising thermal-daylight performance in tropical open-plan offices: A coupled OTTV and daylight prediction approach

In tropical climates, the thermal performance of air-conditioned commercial building envelopes, particularly offices, is commonly assessed using the Overall Thermal Transfer Value (OTTV). Designing office buildings in these regions requires meticulous attention to achieve the optimum thermal-daylight balance, which often has conflicting characteristics. This study aims to enhance the thermal-daylight performance optimization process for open-plan office building envelopes in tropical climates, with Kuala Lumpur as a specific case study. The methodology involves parametric thermal and daylight simulations, incorporating an extensive global sensitivity analysis (GSA) based on the Monte Carlo method. Next, the most critical design parameters affecting daylight provision are identified and used to develop a prediction formula for daylight provision assessment. Finally, the exploration further examines the impact of dominant parameters on energy consumption across diverse urban densities. The results pinpointed the Shading Coefficient (SC1) and Window-to-Wall Ratio (WWR) as pivotal factors affecting heat gain. At the same time, obstruction angle (Theta), WWR, and Visible Transmittance (Tvis) significantly influence daylight provision. Furthermore, the developed daylight prediction formula consists of a fast method that can be coupled with OTTV to evaluate and optimise the thermal-daylight performance in the early design stage of office buildings. Moreover, the study reveals potential energy savings of up to 8 %, 4.83 %, and 4 % in very low, medium, and very high urban densities, respectively. These insights and the daylight prediction formula provide valuable tools for optimising building envelope thermal-daylight performance during the early stages of architectural design, offering practical guidance for both practitioners and researchers.

Exploring green building certification credit selection: A model based on explainable machine learning

Green buildings represent a promising solution for advancing high-quality development in the building sector to combat climate change. Selecting appropriate credits from the rating system based on the distinct characteristics of buildings is a crucial step in the green building certification process. However, in practice, credit selection is a complex and challenging task, often relying on the personal experience of experts. This study develops a model based on explainable machine learning techniques, aiming to aid architects in selecting suitable credits in the early stages of green building design and explore the impact of various factors on credit selection. A case library of 210 green buildings is established to verify the model's performance. The model demonstrated a notable precision rate of 82.38 % in the selection of regular credits. Leveraging SHapley Additive exPlanations (SHAP) technology, the model uncovers a pattern indicating that buildings sharing specific characteristics tend to exhibit similar performance on particular credits, suggesting an inherent preference or avoidance of these credits. The model developed in this study offers practical strategies for architects in credit selection, reducing the reliance on expert opinions and simplifying the credit selection process. The introduction of explainable machine learning techniques enhances the transparency of model decisions and provides targeted insights for architects and standard setters.

Engineering information format utilisation across building design stages: An exploration of BIM applicability in China

Building Information Modelling (BIM) has been extensively advocated in the construction industry for its potential to improve design efficiency and quality. However, its application continues to encounter considerable resistance from designers because BIM is less efficient than conventional 2D and 3D data formats in some design tasks. Consequently, a flexible approach that integrates BIM into existing workflows, instead of fully replacing traditional data formats, is believed to better enhance BIM application. Given this concern, this study conducts a questionnaire survey among Chinese designers to investigate the engineering information formats used in practice and to assess the potential and applicability of this flexible approach. Analysis of the survey responses using relevance analysis, logistic regression, and multiple correspondence analysis reveals that BIM is more frequently used for coordinating multi-disciplinary data in the later stages of project development than in early design phases. Conversely, conventional 2D and 3D formats are preferred for creating and comparing design alternatives during the concept and developed design stages. A practical application for BIM emerges in the technical design stage of prefabricated construction projects. These results suggest a promising approach for BIM application: allowing the use of conventional data format in the concept and developed design stages, integrating these designs into a shared BIM model in the technical design stage, and maintaining them in the BIM model thereafter. Besides offering an in-depth analysis of engineering information format utilisation, this study offers practical strategies for contractors, policymakers, and BIM developers to extend BIM application and promotion.

Optimal design guidelines for net zero energy residential buildings in cooling-dominated climates: Case study of Ghana

Net zero energy buildings (NZEBs) are regarded as an achievable solution for reducing energy use and carbon emissions in the built environment and addressing climate change. However, the ultimate objective of NZEBs is to enhance the energy performance of buildings by changing how they are designed and constructed. Consequently, identifying cost-effective energy efficiency strategies at the early design stages of buildings has become imperative and often required in several countries. This study describes a systematic analysis approach to optimize the design of residential facilities considering both energy efficiency and renewable energy systems. The design optimization is based on life cycle cost (LCC) analysis, which considers capital and energy costs over the lifecycle of the building. The analysis consistently shows that LCC-based optimal designs significantly reduced the building's annual energy consumption, achieving 34–35% energy-saving across the various climates compared to the baseline case. The most cost-effective energy efficiency measures that proved effective across all the climate zones include north orientation of the building at 180 azimuth degrees, natural ventilation, adequate window-to-wall ratio, minimal façade air leakage (i.e., about 5-7 ACH @50 Pa), and high efficient fans, air conditioning, and dehumidification. The integration of the PV system indicates that the net zero energy (NZE) design for the building is technically feasible and cost-effective across the climate zones considered. The sensitivity analysis further shows that the cost of integrating PV systems is even more cost-effective over a more extended period of the building's lifecycle. The study provides an optimal path for designing NZEBs and offers guidelines to achieve NZE across the building's lifecycle.

Advancing energy efficiency in livestock building: Simplified building energy simulation tool for geometric design of pigsty

Concerns related to food security and animal welfare have led to increasing interest in analyzing the energy demands of heating, ventilation, and air conditioning (HVAC) systems in livestock buildings. However, building energy simulation (BES) model, which facilitates precise HVAC systems energy analysis, is difficult to use for non-experts, and particularly, its usability drops significantly in livestock buildings, which are often constructed without involvement of building engineers. This study, therefore, developed a tool that can analyze the energy demand of pigsties by changing geometric design variables with only several numerical inputs without separate 3D modeling. Pigsty geometric design types were classified by examining pigsty architectural design manual and web portal map search. A simplified tool, utilizing EnergyPlus and MATLAB graphical user interface, was developed to analyze energy demand in pigsties by leveraging simple user inputs for geometric design modeling. This tool simplifies exploring potential energy savings through geometric design changes in the early design stages of livestock buildings. The methodology introduced in this study lays the groundwork for future enhancements, including the integration of various design-phase variables beyond geometric design.

Exploring waste reduction approaches in the architectural design stage of university buildings in the United States

Determining construction and demolition (C&D) waste reduction approaches in the architectural design stage is critical since this waste can be reduced by design decisions. Additionally, adding space and equipment which allow collection, recycling, and storage of solid waste at the usage phase of buildings are important in terms of design decisions. An online survey concerning design decisions of university buildings was conducted among United States (US) higher education institutions. Responses for 74 building projects from 71 universities were collected, analysed descriptively (i.e. percentages), and inferentially (i.e. correlations). Responses in some categories were aggregated to determine the total environment scores of the universities. The highest possible environmental score was determined as 8. While the score of 12 universities was 7, the score of three universities was 0. Of the participants, 85% stated that their University required architect to include specific design features for solid waste management (SWM) in the building; 89% stated that the University asked to use greener materials; 78% stated that the University asked to use longer-lasting building products. A set of recommendations and suggestions were provided to deal with the C&D and solid waste issue arising from university buildings.

Development of a rapid assessment tool for integrating thermal comfort in early design stage of energy-efficient office buildings

Comprehending and predicting energy performance of existing buildings and new constructions is crucial towards decarbonization. Instead of utilizing simulation software, multiple regression models are utilized to predict building energy consumption while ensuring indoor thermal comfort to speed up this process. However, previous predictive models prioritize reducing energy demand, with limited focus on thermal comfort. This study aims to support decision-making during retrofitting and new construction planning though developing a prediction model. An air-conditioned office building served as a reference building for simulation. 21 design parameters were analyzed, including aspects of weather, building envelope, internal loads, ventilation, and temperature settings. Stepwise regression results unveiled the crucial variables in the final model, with 8, 9, 13, and 6 variables remaining for peak cooling load, annual cooling load, overheating hours (WE), and Environmental Quality Index for thermal comfort (EQITC) in the perimeter zones, and 5, 6, 8, and 5 variables for the core zones, respectively. Furthermore, insights into the important variables regarding cooling load and thermal comfort were respectively provided. Weather- and envelope-related variables, such as cooling degree-days, global solar radiation, solar heat gain coefficient (SHGC), and U-value, have the highest impacts on cooling load. For thermal comfort, variables including temperature setpoint, occupant activity level, and factors related to window sunlight transmission performance, such as SHGC, window area ratio, and overhang projection ratio, proved to be influential. Overall, this study provided accurate models for assessing optimal strategies for energy efficiency and thermal comfort during the early design phases, advancing building performance practices.

Modeling and optimization method for building energy performance in the design stage

Building energy consumption is responsible for 30%–40% of the total society's energy consumption. There is great energy-saving potential in the building design stage. Good building designs can substantially reduce energy consumption in the long term. This study introduces a data-driven, modeling and optimization method for building energy performance in the design stage. The method has four steps: building model establishment, dataset generation, surrogate modeling, and optimization. Six potential regression methods and five potential optimization methods are applied and compared in two cases; where the regression models are used to train surrogate models, and the optimization methods are used to find the optimal designs. One case uses a constantly operating AC system and the other case uses an intermittently operating AC system. The results show the same trends in both cases. RFR has the best accuracy in predicting the annual building energy consumption, with RMSE consistently below 0.41 GJ for varying subcases. AdaBoost has the poorest performance among the six regression methods. The results indicate that 2000 to 3500 subcases are enough for the optimization of one case. In the case with a constantly operating AC system, the combination of XGBoost and DE found the best design with minimal annual building energy consumption of 1060 GJ; In the case with an intermittently operating AC system, the combination of GB and PSO found the best design with minimal annual building energy consumption of 565 GJ. The combination of RFR and PSO failed to find the optimal design in a limited time for both cases.

An Estimation of Speech Privacy Class Based on ISO Parameter

This paper examines speech privacy in both residential and commercial spaces. The ASTM E2638 standard defines the Speech Privacy Class (SPC) parameter, which measures speech privacy based on the signal-to-noise ratio at the listener’s position. This paper proposes estimating the SPC value using relevant ISO parameters commonly used in European practice: the apparent sound reduction index in dB (defined by ISO 16283-1, 2 standards) and the equivalent ambient noise level in dBA (defined by the ISO 1996-1 standard). The estimated value of the SPC parameter in this paper is referred to as the Speech Privacy Index (SPI). A diverse range of situations, i.e., rooms, was analyzed in the field. These rooms varied in terms of purpose, organization, dimensions, furnishings, isolation from other spaces, and internal and external environments. The results of the experiments demonstrate a strong correlation between the SPC value estimated according to ISO parameters (the proposed method) and the SPC as defined in the ASTM E standard. This indicates that the proposed method can provide an indicator of the state of speech privacy in buildings. The significance of the proposed calculation method (i.e., the STI parameter) lies in its ability to be applied at the building design stage, as well as after its completion, during routine testing.

Formulation of justifiable wind loading distributions up tall buildings derived from HFFB measurements

For the general case of non-linear and combined sway and twist mode shapes, analysis of HFFB measurements gives rise to serious challenges and various techniques have been developed using significant assumptions. This is because it is not possible to directly obtain the distribution of varying fluctuating wind loads throughout the height of tall buildings. This paper proposes a straightforward HFFB-based wind load/twist distribution approach in the time domain to predict the wind-induced dynamic response of tall buildings. Using this framework, it is possible to overcome the deficiencies of mode shape correction factor approach, and the complexity and impracticality of alternative approaches for tall buildings. Two 1:300 scale rigid models of benchmark tall buildings, IAWE Buildings A and B, have been selected to perform a detailed wind tunnel investigation as subjects to evaluate this proposed HFFB approach study. Building A has complex 3D mode shapes combining sway and twist, whereas the simpler Building B has uncoupled linear mode shapes in sway and twist. The high frequency pressure integration (HFPI) wind tunnel technique was utilised to measure surface pressure information in separate tests to obtain the reference wind loading for validation of the HFFB predictions. Furthermore, a commonly used HFFB mode shape correction factor approach was used to estimate the dynamic wind responses which were compared to those from the proposed approach. From the comparison between the aerodynamic and dynamic wind results from proposed HFFB approach and reference HFPI results, it is found that the proposed HFFB approach can predict the vertical distributions of the wind forces and torque (wind loads) with acceptable accuracy for carrying out the conceptual stage of tall building design.

A predictive model for daylight performance based on multimodal generative adversarial networks at the early design stage

In the early building design stage, machine learning-based surrogate models demonstrate significant advantages in rapidly evaluating design performance compared to conventional simulation software. However, due to network limitations, current models struggle to incorporate comprehensive building information, leading to undesired generalizability in adapting to design variations. This study proposes a multimodal Generative Adversarial Network (GAN)-based surrogate model, representing building features with combined multimodal data of images and vectors. Geometric features on the plan and façade are translated into grayscale maps, indicating the potential for daylight reception from each viewpoint, while material properties and weather features are extracted as vectors, such as reflectance, transmittance, sun position and sky conditions. To satisfy the demands of multimodal inputs, the multimodal feature fusion block, the vector-based feature encoding block, and the feature reinforcement block are introduced. These components aim to promote the deep integration of information from different modalities, balance the influences of features across different dimensional scales, and ensure the integrity of the information. The model's validity was verified on the RPLAN database, predicting illumination distribution at the whole-building hierarchy instead of the single-room hierarchy. The results indicate that the multimodal GAN has a Mean Squared Error of 8.129, a Mean Absolute Percentage Error of 0.135, and a Structural Similarity Index of 0.907 on the test set. Meanwhile, this approach saved 73.03% of computing time compared to simulation methods. Boasting strengths in generalizability, speed, and accuracy, the model provides effective support for daylight organization in the early stage of building design, without being confined by variable design scenarios.

Integration of Ecological and Eco-technological Design on Architecture (Hot, Dry Climatic Environment)

The eco-technological architecture works to improve the efficiency of energy consumption, and the interaction of the building and its systems with the external environment as a living outlet that affects and is affected by the external environment. The research paper aims to devise sustainable ecological design criteria during all stages of sustainable building design by studying the integration between the ecology system and Eco technology on the hot, dry climatic environment and its direct impact on architecture to achieve compatibility and compatibility with the surrounding environment, leading to a more interactive architecture with the environment, an attempt to achieve ecological design features. By analyzing the architectural output resulting from the eco-technological concept, and achieving the highest degrees of comfort in the internal environment with the highest possible performance and the lowest possible cost, it positively affects the comfort of users. Therefore, architectural designers must move towards eco-technological thinking to pay attention to the energy rationalization system and the sustainability of buildings, realizing the importance of analyzing the basic principles of the eco-technological approach to obtain an environmentally compatible interior design, and paying attention to the technological means available to achieve energy efficiency in internal spaces in ways that do not affect the external environment.

A Building Information Modeling-Life Cycle Cost Analysis Integrated Model to Enhance Decisions Related to the Selection of Construction Methods at the Conceptual Design Stage of Buildings

A Building Information Modeling-Life Cycle Cost Analysis Integrated Model to Enhance Decisions Related to the Selection of Construction Methods at the Conceptual Design Stage of Buildings

Predicting whole-life carbon emissions for buildings using different machine learning algorithms: A case study on typical residential properties in Cornwall, UK

Whole-life carbon emissions (WLCE) studies are critical in assessing the environmental impact of buildings and promoting sustainable design practices. However, existing methods for estimating WLCE are time-consuming and data-intensive, limiting their usefulness in the early building design stages. In response to this, this research introduces a novel approach by harnessing various machine learning algorithms to predict WLCE and WLCE intensity (normalised by floor area) for buildings. To evaluate the suitability of machine learning algorithms, we conducted an experiment involving ten algorithms to build the prediction models. These models were trained using data from 150 typical residential properties in Cornwall, UK, along with 28 features obtained from a comprehensive survey, including floor area, heating type, and occupant characteristics. The ten algorithms include Multiple Linear Regression, and non-linear algorithms such as Decision Tree, Random Forest. Performance evaluation metrics, such as coefficient of determination (R2), mean absolute error (MAE), means squared error (MSE), root-mean-square error (RMSE), and elapsed time, were employed. Our research contributes to the field by showcasing the effectiveness of machine learning models in predicting building WLCE. We reveal that all the tested machine learning algorithms have the capability to predict WLCE and WLCE intensity, non-linear models outperform linear ones, and the Random Forest (RF) model demonstrates superior performance in terms of accuracy, stability, and efficiency. This research encourages the integration of life cycle studies into the early design stage, even within tight building design schedules, offering practical guidance to architects and designers. Furthermore, these results also benefit a wide range of stakeholders, not only the architects but also the engineers, policymakers, and life cycle assessment (LCA) researchers, contributing to the advancement of data-driven sustainability approaches within the building sector.

Hypogeomagnetic field in residential and public buildings

Introduction. The impact of geomagnetic field (GMF) on the human body is a proven fact, while an increased, but also a weakened geomagnetic field is the critical factor. The problems of normalization of GMF levels in existing residential and public buildings lead to the need for the use of calculation methods at the design stage of multistorey and high-rise buildings, the development of instrumental control methods at the stage of commissioning. 
 The purpose of the study was to develop and scientifically substantiate methodological approaches to carrying out field measurements of GMF intensity and calculating the GMF attenuation coefficient in residential and public buildings.
 Materials and methods. The current and previously valid regulatory and methodological documents establishing requirements for geomagnetic field intensity measurements were analyzed, as well as protocols of GMF intensity measurement at thirty commissioned facilities completed in 2018–2022.
 Results. Issues arising during the measurements of GMF intensity and assessing hypogeomagnetic conditions in residential and public buildings are identified. The minimum required amount of work, control points of measurements, requirements to measuring instruments (MI), as well as to the processing and registration of the obtained measurement results are proposed.
 Limitations. The results of the study can be used only for measuring the GMF intensity and assessing hypogeomagnetic conditions in the premises of residential and public buildings, and are not applied to measurements in the workplace.
 Conclusion. The proposed methodological approaches will make it possible to carry out measurements of the geomagnetic field intensity, process and document the obtained results, as well as assess hypogeomagnetic conditions in residential and public buildings for compliance with current hygienic standards.

Comprehensive application system of BIM technology in MULTIBAY project

With the rapid development of urbanization, the number of super high-rise buildings with increased building volume and scale is gradually increasing. At present, there are still problems such as inconsistent engineering information transmission and low efficiency of collaborative management among various participants in the construction of international super high-rise buildings. Because of this, based on engineering practice, using the advantages of BIM technology such as visualization, simulation, and collaboration, this article explores the application process of BIM technology in the design stage of super high-rise buildings, such as multi-disciplinary detailed design and drawing collision inspection, as well as in the construction stage, such as visual technical disclosure and scheme selection. It also constructs a BIM whole process management system, enabling BIM technology to better participate in the whole process of project construction, improving the level of project information technology, and providing engineering reference for the application of BIM technology in similar super high-rise buildings.

Wall and air conditioner combination for the best energy and economic performance: Methodology demonstration for high-rise residential buildings

Enhancing energy efficiency of any system with affordable measures is always a ‘win-win’ option, specifically for systems consuming large amount of energy. With increasing population and economic growth, rapid urbanization is inevitable, more so in developing countries. Due to higher population density and scarcity of available land, high-rise residential and commercial buildings are now increasing in big cities. Building energy efficiency has eventually emerged as a critical issue for such high-rise buildings. Space cooling consumes a huge amount of energy for high-rise buildings in tropical countries. Selection of masonry materials for exterior walls with matching air conditioners should be optimized for the best energy efficiency vis-à-vis least cost for high-rise buildings. Such a study to determine the optimized solution is reported using data of ten typical high-rise residential buildings in the warm-humid climate of Kolkata, India. The methodology followed is an integrated iterative process involving whole building energy simulation to determine the optimum performance out of different possible combinations of building walls (i.e., passive measure) and selection of corresponding air conditioners (i.e., active measure) for simultaneous best energy efficiency and minimum costing. Results show that the combination of autoclaved aerated concrete block wall and 5-star split air conditioner emerges as the optimum, being 37.53% more energy efficient and 24.27% more cost effective than the typically practiced baseline option. The required 29.47% higher capital investment is well compensated for lower annual expenditure for operational energy when fifteen years’ cash flow is considered. The study shows an integrated methodology for deciding the optimum combination of passive and active measures for the possible best energy performance at a minimum cost at the early design stage of high-rise buildings.

Investigation of heating energy performance gap (EPG) in design and operation stages of residential buildings

The Energy Performance Gap (EPG) in buildings is a recognized phenomenon. However, its definition and underlying factors are extensive, necessitating a thorough investigation of the quantitative impact of each factor contributing to the EPG. In this research, a calibration-based approach is employed to identify and measure the contribution of these factors. Questionnaires, measurements, analyses, and calibrations are conducted on the energy performance of four residential units of an apartment block building in Iran as a case study. Subsequently, the impact rates of three key causes of the EPG, namely heating system efficiency, weather data in an EnergyPlus Weather (EPW) format file, and occupant behavior, are determined. By incorporating these causes into the model calibration process, the disparities between the design and operation stages are decreased. The study highlights the significance and quantifiable effects of accurate and measured boiler efficiency, utilizing a genuine EPW file rather than a convenient EPW file e.g., airport stations, and adopting precise and adaptable assumptions for occupant behavior modeling in bridging the EPG between the design and operation stages. There are a number of factors that impact the design stage gap, including boiler efficiency, occupant behavior, and a corrected EPW file, which contribute 43.9%, 26%, and 6.6%, respectively.