Evaluation of Energy and Lighting in Schools Considering Solar Protections DOI

Cristián Muñoz-Viveros,

Alexis Pérez-Fargallo, Carlos Rubio-Bellido

et al.

Published: Jan. 1, 2023

The implementation of the solar protections laid out in regulations and certification systems decreases cooling demands, although it has an uncontrolled even unforeseen effect on daylighting. Achieving a balance between both requirements is challenge for facade design, energy behavior, lighting performance since restricting radiation contributions daylight's contribution. This research aims to define methodology that allows, early design stage, evaluation protection solutions consider optimal daylight using annual dynamic indicators while maintaining adequate energy-saving levels. For this purpose, consumption have been considered as primary indicators, namely Spatial autonomy (sDA), Annual access (ASE), useful illuminance (UDI) with variations Modified Solar Factor (MSF). Thermal light assessments were made modeling two types protection. case study school classroom located city Talca, central Chile, considering window-to-wall ratios (WWR) 40%, 50%, 60%. premise's thermal behavior obtained sDA UDI results allowed making approximation solutions, however, ASE values all cases, classified unsuitable use. analysis suggests better limit are by organizing WWR instead MSF each solution identifies. compared options at reaching recommended levels savings 70% or more, It concluded achieve minimum acceptable daylighting levels, consumption, necessary relevant indicators.

Language: Английский

A predictive model for daylight performance based on multimodal generative adversarial networks at the early design stage DOI
X Li, Ye Yuan, Gang Liu

et al.

Energy and Buildings, Journal Year: 2024, Volume and Issue: 305, P. 113876 - 113876

Published: Jan. 3, 2024

Language: Английский

Citations

17
AI for conceptual architecture: Reflections on designing with text-to-text, text-to-image, and image-to-image generators DOI Creative Commons
Anca-Simona Horvath, Panagiota Pouliou

Frontiers of Architectural Research, Journal Year: 2024, Volume and Issue: 13(3), P. 593 - 612

Published: April 3, 2024

In this paper we present a research-through-design study where employed text-to-text, text-to-image, and image-to-image generative tools for conceptual architecture project the eVolo skyscraper competition. We trained these algorithms on dataset that collected curated, consisting of texts about images architecture. describe our design process, final proposal, reflect usefulness such early-stage design, discuss implications future research practice. By analysing results from training text-to-text generators could establish specific brief informed concept. The generator gave an overview shape grammars previous submissions. All were intriguing can assist creativity in way, useful gaining insight into historical architectural data, helped brief, provoked new ideas. reflecting argue use language when employing takes role three layers intertwined work: discourse, programming languages, annotations. map unfolds how came together as contribution to making machine learning more explainable creatives.

Language: Английский

Citations

10
Integrating Pix2Pix and computational fluid dynamics for enhanced indoor airflow prediction: A case study with wing-walls DOI Creative Commons
You-Jeong Kim, Manal Anis,

Yun Kyu Yi

et al.

Journal of Building Engineering, Journal Year: 2024, Volume and Issue: 91, P. 109517 - 109517

Published: May 6, 2024

Computational Fluid Dynamics (CFD) is often used for analyzing natural ventilation but limited in early design stages due to its high computational demands and the need detailed inputs. To overcome such limitations of CFD simulation, this paper proposes a method using conditional Generative Adversarial Network (cGAN) based image-to-image translation (Pix2Pix) predict indoor airflow condition. Compared other traditional machine learning models that averaged values like air velocity, Pix2Pix can contour plot given building floor plan image, which provides more intuitive feedback designers. The proposed was tested understand movement caused by wing-walls attached windows. model trained 1,153 pairs images, incorporating variations window widths, wing-wall depth, angle, wind speed, direction. It achieved prediction accuracy 94% produced results less than second. Moreover, showed relatively better performance with changes windows properties rather properties. This indicates serve as an efficient proxy conventional simulations, helping designers optimize designs at stage without complex

Language: Английский

Citations

4
Highly Generalized Surrogate Models for Indoor Glare Performance Based on Multimodal Deep Learning Networks at the Early Design Stage DOI
X Li, Gang Liu, Ye Yuan

et al.

Building and Environment, Journal Year: 2025, Volume and Issue: unknown, P. 112706 - 112706

Published: Feb. 1, 2025

Language: Английский

Citations

0
Optimal design strategy of traditional courtyard based on performance and data-driven method—A case study of Yanshen ancient town, China DOI Creative Commons
Zhixin Xu, Xin Zheng, Xiangfeng Li

et al.

Frontiers of Architectural Research, Journal Year: 2025, Volume and Issue: unknown

Published: Feb. 1, 2025

Language: Английский

Citations

0
Application of machine learning and genetic algorithms in environmental performance assessment and optimization of traditional Huizhou houses in China DOI Creative Commons
Zhixin Xu, Xiangfeng Li,

Chenhao Duan

et al.

Frontiers of Architectural Research, Journal Year: 2025, Volume and Issue: unknown

Published: March 1, 2025

Language: Английский

Citations

0
Architectural space design methods using data algorithms DOI Creative Commons
Jingyang Liu,

Yifan Zhang,

Sen Zhao

et al.

AIP Advances, Journal Year: 2025, Volume and Issue: 15(4)

Published: April 1, 2025

Currently, various industries around the world are advocating innovation, and design of architectural spaces is no exception. However, innovation traditional space methods not enough. In view problems methods, such as weak quantification, logic, low level science technology, this paper used particle swarm optimization algorithm in data to study methods. This introduced principles design, studied some existing problems, make innovations Experts scholars were invited score verify superiority for design. The residents’ satisfaction rate with building method using was more than 91.65%, average 20 residents 93.2%. At same time, experts who scored 8.34 points. Innovative requires Only by applying right approach can ideal effect be achieved quickly possible ensure quality

Language: Английский

Citations

0
Generative AI in architectural design: Application, data, and evaluation methods DOI
Suhyung Jang, Hyunsung Roh, Ghang Lee

et al.

Automation in Construction, Journal Year: 2025, Volume and Issue: 174, P. 106174 - 106174

Published: April 4, 2025

Language: Английский

Citations

0
Research on the Application of CGAN in the Design of Historic Building Facades in Urban Renewal—Taking Fujian Putian Historic Districts as an Example DOI Creative Commons
Hongpan Lin, Linsheng Huang, Yile Chen

et al.

Buildings, Journal Year: 2023, Volume and Issue: 13(6), P. 1478 - 1478

Published: June 7, 2023

In recent years, artificial intelligence technology has widely influenced the design field, introducing new ideas to efficiently and systematically solve urban renewal problems. The purpose of this study is create a stylized generation for building facade decoration in historic districts, which will aid control district style form. goal use technical advantages conditional generative adversarial network (CGAN) image transfer method independently designing specific by interpreting data historical facades. research paper based on Putian Fujian Province facilitates an experiment acquisition, processing screening, model training, generation, matching target area. found following: (1) CGAN can better identify generate decorative districts. It realize overall or partial scheme facade. (2) terms adaptability, provide reference reconstruction, renovation, renovation projects. Especially districts with obvious styles, visualization effect better. addition, it also certain significance determination building. (3) Lastly, learn internal laws complex form clear attribute. be extended other fields heritage protection enhance practitioners’ environment improve efficiency capability professional design.

Language: Английский

Citations

10
Research on the Application of CGAN in the Design of Historic Building Facades in Urban Renewal—Taking Fujian Putian Historic Districts as an Example DOI Open Access
Hongpan Lin,

Linsheng Huang,

Yile Chen

et al.

Published: May 3, 2023

In recent years, artificial intelligence technology has widely influenced the field of design, bringing new ideas to efficiently and systematically solve urban renewal design problems. The purpose this study is create a stylized generation for building facade decoration in historic districts, which will aid control district style form. goal use technical advantages conditional generative adversarial network (CGAN) image transfer method independently designing specific by interpreting data historical facades. research paper based on Putian Fujian Province, through an experiment acquisition, processing screening, model training, generation, matching target area. found that: (1) CGAN can better identify generate decorative districts. It realize overall or partial scheme facade; (2) terms adaptability, provide reference reconstruction, renovation, renovation projects. Especially districts with obvious styles, visualization effect better. addition, it also certain significance determination building; (3) This learn internal laws complex form so as clear attribute. be extended other fields heritage protection enhance practitioners' environment improve efficiency ability professional design.

Language: Английский

Citations

7