Hasil untuk "Details in building design and construction. Including walls, roofs"

Aya M.F. El-Bahrawy

Perforated solar screens (PSSs) have been widely used as an outer skin for the fully glazed façades of office buildings for their environmental and aesthetic benefits. However, PSS have several parameters that can affect their efficiency, including perforation percentage, thickness, material properties, and others. Controlling and balancing the influence of these parameters is critical for optimizing the quality of the indoor environment while meeting the required demands and needs. This paper investigates the impact of balancing the effect of four design parameters—matrix, perforation percentage, thickness, and separation distance—on promoting the daylighting and glare performance of south façades in office buildings in a hot, dry climate. The analyses were performed with Honeybee and Ladybug plugins through Grasshopper interface in Rhinoceros 3D software on a base case (without PSS), four independently optimized solutions for each parameter, and a balanced solution at three times per four days around the year. Genetic algorithms and the Python component in Grasshopper were utilized to identify the optimal balanced solutions. The results showed a noticeable reduction in the overlit areas in the balanced solutions by 21-61% compared to the base case, outperforming independent parameter optimizations by up to 36%. Additionally, the balanced solutions effectively eliminated glare across all analyzed periods and provided more effective solutions in terms of visual access and material sustainability. These findings suggest that balancing the influence of multiple design parameters is more effective than optimizing individual parameters, providing better control over daylight efficiency and glare reduction.

Mohammad Hassan Abedini, Hanieh Gholami, Hamed Sangin

Addressing the challenges of global warming and rising energy demands, this study explores fixed shading systems as passive and sustainable solutions to improve energy efficiency, thermal comfort, and daylight performance in office buildings. Conducted in the hot desert climate of Qom, the research employs advanced simulation tools, including Rhino 8 integrated with Grasshopper, Honeybee, and Ladybug, to model and evaluate shading strategies. A multi-objective optimization (MOO) approach was applied to enhance four key metrics: Thermal Comfort Percent (TCP), Energy Use Intensity (EUI), Annual Sunlight Exposure (ASE), and Spatial Daylight Autonomy (sDA). Optimization and visualization were carried out using Colibri and Design Explorer to identify shading configurations that effectively balance energy savings, thermal comfort, and daylighting. The results highlight substantial improvements achieved through optimized shading designs. Fixed exterior shading systems reduced EUI by up to 14.95% for overhangs, with side fins, light shelves, and H-louvers achieving reductions of 7.28%, 13.45%, and 6.04%, respectively. ASE was effectively mitigated, with side fins and H-louvers achieving reductions of 36.25% and 9.38%. Optimal daylighting performance was observed, as sDA reached 100% for H-louvers, side fins, overhangs, and light shelves, and 98.25% for egg-crates and V-louvers. Regarding TCP, egg-crates exhibited the highest performance at 74.18%, followed by H-louvers at 70.21%. These findings demonstrate that integrating tailored shading systems into office buildings not only enhances occupant comfort and reduces energy consumption but also supports sustainable building practices, offering practical solutions for environmentally conscious architectural design.

Peilin Li, Jun Yin, Jing Zhong et al.

In the context of the digital development of architecture, the automatic segmentation of walls and windows is a key step in improving the efficiency of building information models and computer-aided design. This study proposes an automatic segmentation model for building facade walls and windows based on multimodal semantic guidance, called Segment Any Architectural Facades (SAAF). First, SAAF has a multimodal semantic collaborative feature extraction mechanism. By combining natural language processing technology, it can fuse the semantic information in text descriptions with image features, enhancing the semantic understanding of building facade components. Second, we developed an end-to-end training framework that enables the model to autonomously learn the mapping relationship from text descriptions to image segmentation, reducing the influence of manual intervention on the segmentation results and improving the automation and robustness of the model. Finally, we conducted extensive experiments on multiple facade datasets. The segmentation results of SAAF outperformed existing methods in the mIoU metric, indicating that the SAAF model can maintain high-precision segmentation ability when faced with diverse datasets. Our model has made certain progress in improving the accuracy and generalization ability of the wall and window segmentation task. It is expected to provide a reference for the development of architectural computer vision technology and also explore new ideas and technical paths for the application of multimodal learning in the architectural field.

Simon Adamov, Joel Oskarsson, Leif Denby et al.

Machine learning is revolutionizing global weather forecasting, with models that efficiently produce highly accurate forecasts. Apart from global forecasting there is also a large value in high-resolution regional weather forecasts, focusing on accurate simulations of the atmosphere for a limited area. Initial attempts have been made to use machine learning for such limited area scenarios, but these experiments do not consider realistic forecasting settings and do not investigate the many design choices involved. We present a framework for building kilometer-scale machine learning limited area models with boundary conditions imposed through a flexible boundary forcing method. This enables boundary conditions defined either from reanalysis or operational forecast data. Our approach employs specialized graph constructions with rectangular and triangular meshes, along with multi-step rollout training strategies to improve temporal consistency. We perform systematic evaluation of different design choices, including the boundary width, graph construction and boundary forcing integration. Models are evaluated across both a Danish and a Swiss domain, two regions that exhibit different orographical characteristics. Verification is performed against both gridded analysis data and in-situ observations, including a case study for the storm Ciara in February 2020. Both models achieve skillful predictions across a wide range of variables, with our Swiss model outperforming the numerical weather prediction baseline for key surface variables. With their substantially lower computational cost, our findings demonstrate great potential for machine learning limited area models in the future of regional weather forecasting.

Hongjian Zhou, Pingchuan Ma, Jiaqi Gu

Photonic Integrated Circuits (PICs) offer tremendous advantages in bandwidth, parallelism, and energy efficiency, making them essential for emerging applications in artificial intelligence (AI), high-performance computing (HPC), sensing, and communications. However, the design of modern PICs, which now integrate hundreds to thousands of components, remains largely manual, resulting in inefficiency, poor scalability, and susceptibility to errors. To address these challenges, we propose PoLaRIS, a comprehensive Intelligent Electronic-Photonic Design Automation (EPDA) framework that spans both device-level synthesis and system-level physical layout. PoLaRIS combines a robust, fabrication-aware inverse design engine with a routing-informed placement and curvy-aware detailed router, enabling the automated generation of design rule violation (DRV)-free and performance-optimized layouts. By unifying physics-driven optimization with machine learning and domain-specific algorithms, PoLaRIS significantly accelerates PIC development, lowers design barriers, and lays the groundwork for scalable photonic system design automation.

Christian Ghiaus

Building Performance Simulation (BPS) uses advanced computational and data science methods. Reproducibility, the ability to obtain the same results by using the same data and methods, is essential in BPS research to ensure the reliability and validity of scientific results. The benefits of reproducible research include enhanced scientific integrity, faster scientific advancements, and valuable educational resources. Despite its importance, reproducibility in BPS is often overlooked due to technical complexities, insufficient documentation, and cultural barriers such as the lack of incentives for sharing code and data. This paper encourages the reproducibility of articles on computational science and proposes to recognize reproductible code and data, with persistent Digital Object Identifier (DOI), as peer-reviewed archival publications. Practical workflows for achieving reproducibility in BPS are presented for the use of MATLAB and Python.

Emre Girgin, Arda Taha Candan, Coşkun Anıl Zaman

The fields of autonomous systems and robotics are receiving considerable attention in civil applications such as construction, logistics, and firefighting. Nevertheless, the widespread adoption of these technologies is hindered by the necessity for robust processing units to run AI models. Edge-AI solutions offer considerable promise, enabling low-power, cost-effective robotics that can automate civil services, improve safety, and enhance sustainability. This paper presents a novel Edge-AI-enabled drone-based surveillance system for autonomous multi-robot operations at construction sites. Our system integrates a lightweight MCU-based object detection model within a custom-built UAV platform and a 5G-enabled multi-agent coordination infrastructure. We specifically target the real-time obstacle detection and dynamic path planning problem in construction environments, providing a comprehensive dataset specifically created for MCU-based edge applications. Field experiments demonstrate practical viability and identify optimal operational parameters, highlighting our approach's scalability and computational efficiency advantages compared to existing UAV solutions. The present and future roles of autonomous vehicles on construction sites are also discussed, as well as the effectiveness of edge-AI solutions. We share our dataset publicly at github.com/egirgin/storaige-b950

Tachaya Sangkakool, Zulfiqar Ali Jumani

This research examines the natural and artificial lighting performance comparison in an architecture classroom at a university in southern Thailand and gives principles for enhancing lighting design. The sample for the study was classroom spaces. The efficacy of natural and artificial lighting was studied using static and dynamic models, and data were obtained using a 4 in 1 multi-function environmental meter at various times of the day. The current study adopted the IESNA (Illuminating Engineering Society of North America) and CIBSE (Chartered Institution of Building Services Engineers) lighting standards for the performance comparison analysis. The results showed that the natural light in the classrooms did not satisfy the standards for lighting levels. In contrast, the artificial lighting was more effective but raised some issues with uniformity and glare. The study offers recommendations for improving lighting effectiveness, maximizing natural light, reducing energy consumption, improving the uniformity of artificial illumination, addressing issues with various classroom lighting designs, and creating more comfortable and realistic learning environments.

Nurefşan Sönmez, Arzu Cılasun Kunduracı, Cemre Çubukçuoğlu

Enhancing daylighting in heritage buildings is a complex challenge that requires a delicate balance between preserving architectural integrity and improving visual comfort. This paper investigates enhancing daylight in heritage buildings, balancing preservation and visual comfort. It focuses on a 1905 heritage building undergoing reconstruction, addressing insufficient daylight on the ground floor and glare on the first floor. The study investigated novel design solutions by using simulation and optimization approaches. A multi-objective optimization algorithm, called JDEMO Algorithm (a multi-objective self-adaptive differential evolution algorithm), was utilized to obtain Pareto optimal results, and integrated with performative simulations using ClimateStudio (CS) plug-in for Grasshopper. Strategies include altering skylight glazing materials, surface materials, and using Tubular Daylight Guidance Systems (TDGS). Results show TDGS with larger diameters improve Useful Daylight Illuminance (UDI) and reduce Spatial Disturbing Glare (sDG). Material selection impacts daylight distribution, emphasizing the importance of skylight glazing materials. While specific to one case, this research has wider implications for heritage preservation and daylighting. By innovating sustainable design, it contributes to preserving heritage buildings while enhancing visual comfort.

Ilyass Abouelaziz, Youssef Mourchid

This paper presents a framework to address the challenges involved in building point cloud cleaning, plane detection, and semantic segmentation, with the ultimate goal of enhancing building modeling. We focus in the cleaning stage on removing outliers from the acquired point cloud data by employing an adaptive threshold technique based on z-score measure. Following the cleaning process, we perform plane detection using the robust RANSAC paradigm. The goal is to carry out multiple plane segmentations, and to classify segments into distinct categories, such as floors, ceilings, and walls. The resulting segments can generate accurate and detailed point clouds representing the building's architectural elements. Moreover, we address the problem of semantic segmentation, which plays a vital role in the identification and classification of different components within the building, such as walls, windows, doors, roofs, and objects. Inspired by the PointNet architecture, we propose a deep learning architecture for efficient semantic segmentation in buildings. The results demonstrate the effectiveness of the proposed framework in handling building modeling tasks, paving the way for improved accuracy and efficiency in the field of building modelization.

Fayrouz H. F. Hassan, Khaled A. Y. Ali, Salwa A. M. Ahmed

Biomimicry inspired architects to solve complex design problems and develop adaptive solutions for enhancing the environmental quality. Fields of inspiration include energy efficiency, natural ventilation, daylighting, and structural stability. In this paper, 144 biomimicry-inspired building skin alternatives have been developed to improve daylighting performance in office buildings in Assiut City, Egypt; 72 alternatives are of 0.5 m frame depth, and other 72 alternatives are of 1.0 m frame depth. Two levels of biomimicry; namely, the organism level (snakeskin) and the behavior level (plants tropism), have been adopted. Alternatives have been developed to be simulated ClimateStudio plug-in for Rhino in accordance with the international rating system leadership in energy and environmental design (LEED v4.1). The evaluation criteria are spatial Daylight Autonomy (sDA), Annual Sunlight Exposure (ASE), Annual Average Lux (AAl), and Spatial Distributing Glare (sDG). An evaluation point system has been developed to evaluate alternatives using Analytical Hierarchy Process (AHP) based on the feedback of 14 faculty of architecture members. Nine building skin alternatives developed succeeded to achieve notable improvement (from 16.69% to 33.73%) compared to the base cases. In general, the 1.0 m frame-depth alternatives achieved better results in improving daylighting performance than the 0.5 m frame-depth alternatives. The most effective parameter in improving daylighting performance was the rotation angle of the skin unit used, to be followed by the distance between the skin and the building façade, the solid-to-void ratio of the skin, the number of units constituting the skin system, and the horizontal bending distance of the skin unit, respectively.

Seyedeh Azadeh Aghajanzadeh, Seyed Morteza Hosseini, Mojtaba Lorzangeneh et al.

Excessive heat in the high-rise urban fabric has contributed to pedestrian and occupants' discomfort. Establishing wind circulation in space with an environmentally compatible and optimal configuration is necessary to improve comfort in this region. The study benefits from field measurements and experimental validation of CFD simulation to investigate the effective parameters that affect wind speed. The master plan has proposed decentralized and limited high-rise construction to prevent the horizontal growth of Babolsar city. Meanwhile, the demand for high-rise buildings is high in the city. Therefore, altitude density (height factor) is considered as a constant factor. The buildings' orientation and enclosure based on the passages' width have opposite reactions in the direction of the prevailing wind. The correlation between the orientation and the enclosure with the wind speed are the values of 0.504 and 0.2226 respectively, which have the highest correlation among other parameters. The changes have been made in the building orientation factor in the dominant wind direction by creating permeability as well as creating low enclosure in the paths and empty spaces perpendicular to the dominant wind (W’= 3W, E’ = 0.33E). These strategies have finally improved wind velocity and created wind circulation in urban block spaces. Finally, according to the data analysis for Climate compatible in humid areas and the optimal behavior of wind flow for proper urban ventilation, an improved layout for future developments will be presented.

Hanifa Izzati, Harry Kurniawan

The De Tjolomadoe Museum was originally a sugar factory which later underwent a revitalization after being neglected for 20 years by carrying out the concept of adaptive reuse. After the revitalization was completed, the building was reopened as a museum along with various other supporting functions. The widespread use of social media such as Instagram among the public, the De Tjolomadoe Museum also uses Instagram as a medium to interact and attract the attention of the wider community to visit this museum. As a result, many people are interested in visiting and documenting it through photos which are then uploaded to social media and uploaded by tagging the official Instagram account @detjolomadoe_official. This study aims to find the effect of photo composition on the architecture of the De Tjolomadoe Museum by uploading the Instagram photo tag @detjolomadoe_official. This research focuses on the exterior of the museum through photos tagged on the Instagram account @detjolomadoe_official. Photos are taken via screenshots which are then processed by classifying them based on the composition used. The research is continued with analysis and discussion in accordance with related theories. The discussion starts with photo composition preferences, layers in photos, and building elements that appear in photos. The photos obtained were able to strengthen the character of the De Tjolomadoe Museum into a monumental building because of its compositional arrangement.

Birra Firmansyah, Suko Istijanto

The museum is one of the places where these stories from the past are brought together in dioramas and their collections, so that these stories live on and can be interpreted in depth and detail by future generations. The museum itself is a place of discovery of relics of the past, where people can explore and travel through history, remembering the past in their hearts and minds. The Bojonegoro region has a history that is important enough to be remembered by the Bojonegoro people themselves. Therefor Bojonegoro needs the Museum to become a facility for protecting historical items to always remind the struggle of the Bojonegoro region itself and can become a means of recreation and edutourism for the Bojonegoro region.

Venny, Tessa Eka Darmayanti

The fast growing population of Indonesia in this 4.0 industry revolution influence the large demand of housing and without realizing caused negative impacts to the environment. The usage of eco-friendly materials is one of few aspect of sustainable architecture which is deemed important and could contribute in halting global warming. This research aims to get insights regarding the implementation of the  green architecture concept in Citraland Gama City Medan residence, and its impact on the environment. With qualitative research method, this research is expected to broaden knowledge and push architechs in Indonesia to contribute in developing housing based on green technology with the use of eco-friendly materials. The demand of gree housing is answered by Citraland Gama City Medan of PT. Ciputra. From the research one of the houses in the area is using local, recycled, prefabricated materials that could cut down cost and reduce material that has the potential to become waste so that it can positively impact the global warming issue, also having good impact on social and environment

Yingjie Li, Mingju Liu, Alan Mishchenko et al.

The complexity of modern hardware designs necessitates advanced methodologies for optimizing and analyzing modern digital systems. In recent times, machine learning (ML) methodologies have emerged as potent instruments for assessing design quality-of-results at the Register-Transfer Level (RTL) or Boolean level, aiming to expedite design exploration of advanced RTL configurations. In this presentation, we introduce an innovative open-source framework that translates RTL designs into graph representation foundations, which can be seamlessly integrated with the PyTorch Geometric graph learning platform. Furthermore, the Verilog-to-PyG (V2PYG) framework is compatible with the open-source Electronic Design Automation (EDA) toolchain OpenROAD, facilitating the collection of labeled datasets in an utterly open-source manner. Additionally, we will present novel RTL data augmentation methods (incorporated in our framework) that enable functional equivalent design augmentation for the construction of an extensive graph-based RTL design database. Lastly, we will showcase several using cases of V2PYG with detailed scripting examples. V2PYG can be found at \url{https://yu-maryland.github.io/Verilog-to-PyG/}.

Rebekah Rousi

This article connects the concepts and phenomena of Design AI, AI in creative industries and AIs capacity for creativity. It links Design AI to UX design and UX designer discourse. Its vagueness and the prominence of UX designers as speakers and writers in the spectacle of cultural AI discourse. The article then, draws comparisons between the Theatre of the Absurd and the UX designer performances of design AI. It additionally sheds light on ToA and the human condition in terms of existentialism, present within the practice of engaging in design that intends to link human experience to technological system logic. This is a theoretical article that utilises examples from UX events published on Youtube, as well as UX designer blogs, in order to illustrate the mechanics of the ToA present within contemporary AI and UX designer discourse.

Peidong Jia, Chenxuan Li, Yuhui Yuan et al.

Graphic design, which has been evolving since the 15th century, plays a crucial role in advertising. The creation of high-quality designs demands design-oriented planning, reasoning, and layer-wise generation. Unlike the recent CanvaGPT, which integrates GPT-4 with existing design templates to build a custom GPT, this paper introduces the COLE system - a hierarchical generation framework designed to comprehensively address these challenges. This COLE system can transform a vague intention prompt into a high-quality multi-layered graphic design, while also supporting flexible editing based on user input. Examples of such input might include directives like ``design a poster for Hisaishi's concert.'' The key insight is to dissect the complex task of text-to-design generation into a hierarchy of simpler sub-tasks, each addressed by specialized models working collaboratively. The results from these models are then consolidated to produce a cohesive final output. Our hierarchical task decomposition can streamline the complex process and significantly enhance generation reliability. Our COLE system comprises multiple fine-tuned Large Language Models (LLMs), Large Multimodal Models (LMMs), and Diffusion Models (DMs), each specifically tailored for design-aware layer-wise captioning, layout planning, reasoning, and the task of generating images and text. Furthermore, we construct the DESIGNINTENTION benchmark to demonstrate the superiority of our COLE system over existing methods in generating high-quality graphic designs from user intent. Last, we present a Canva-like multi-layered image editing tool to support flexible editing of the generated multi-layered graphic design images. We perceive our COLE system as an important step towards addressing more complex and multi-layered graphic design generation tasks in the future.

Shi Jin, Nana Liu, Yue Yu

We study a new method - called Schrodingerisation introduced in [Jin, Liu, Yu, arXiv: 2212.13969] - for solving general linear partial differential equations with quantum simulation. This method converts linear partial differential equations into a `Schrodingerised' or Hamiltonian system, using a new and simple transformation called the warped phase transformation. Here we provide more in-depth technical discussions and expand on this approach in a more detailed and pedagogical way. We apply this to more examples of partial differential equations, including heat, convection, Fokker-Planck, linear Boltzmann and Black-Scholes equations. This approach can also be extended to Schrodingerise general linear partial differential equations, including the Vlasov-Fokker-Planck equation and the Liouville representation equation for nonlinear ordinary differential equations.

Philipp Rosenthal, Oliver Niggemann

Artificial Intelligence (AI) has significant potential for product design: AI can check technical and non-technical constraints on products, it can support a quick design of new product variants and new AI methods may also support creativity. But currently product design and AI are separate communities fostering different terms and theories. This makes a mapping of AI approaches to product design needs difficult and prevents new solutions. As a solution, this paper first clarifies important terms and concepts for the interdisciplinary domain of AI methods in product design. A key contribution of this paper is a new classification of design problems using the four characteristics decomposability, inter-dependencies, innovation and creativity. Definitions of these concepts are given where they are lacking. Early mappings of these concepts to AI solutions are sketched and verified using design examples. The importance of creativity in product design and a corresponding gap in AI is pointed out for future research.