The building plan automatic design optimization based on CFD numerical intelligent simulation

Li, Yangluxi; Chen, Lei; Li, Guangyao

doi:10.1177/1420326x221134981

Cited by 3 publications

(2 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Studies have been carried out on energetic optimization-calculation range from those on passive design to those on radiant cooling; however, they do not optimize the geometry from a design perspective. [43][44][45][46] This study was aimed at extending the TEAM-TComBE method reported by Yamamoto et al 37 to develop a set of guidelines for use in the thermal design process of buildings. This study compared the results of accuracy verification and computational-load reduction to accumulate fundamental knowledge for a basic design using the TEAM-TComBE method.…”

Section: Introductionmentioning

confidence: 99%

Guidelines for implementing advanced thermal analysis methods in building design

Yamamoto

Taniguchi²

2023

Indoor and Built Environment

View full text Add to dashboard Cite

Although the thermal environment of buildings with thermally complex building envelopes can be predicted, comprehensive guidelines are not available for designers to implement the thermal-environment analysis. Therefore, this study examines the application scope of advanced thermal-analysis methods from the designers’ perspective. The results of the simple model were consistent with the experimental values, with an error of approximately 0.5°C. The analytically determined convective heat-transfer-coefficient values were within 0.3–0.5°W・m2K, and the difference in the predicted values between the results of the simplified and detailed models was minor. The convective heat transfer coefficient calculated using the reference temperature defined at the dimensionless distance y+ was more accurate than that was obtained using the general energy simulation incorporating the boundary-layer theory. Although the simplified advection rate had a maximum error of approximately 150 m3/h, it was considered acceptable. The differences amongst the zones were less than 0.59°C, which is considered minor. The results obtained by using summer advection were sufficiently accurate. Furthermore, the dew-point temperature was used to evaluate the risk of dew condensation. Specifically, the results indicated that the introduction of outside air increased the risk of condensation on the floor.

show abstract

Section: Introductionmentioning

confidence: 99%

Guidelines for implementing advanced thermal analysis methods in building design

Yamamoto

Taniguchi²

2023

Indoor and Built Environment

View full text Add to dashboard Cite

show abstract

“…RL. RL is a novel branch of ML that utilizes a closed-loop feedback control framework [21,54,38]. It represents a novel approach to automatically discovering the optimal control strategy [45,69].…”

mentioning

confidence: 99%

Deep reinforcement learning for the heat transfer control of pulsating impinging jets

Salavatidezfouli,

Zadeh,

Stabile

et al. 2023

ACSE

View full text Add to dashboard Cite

This research study explored the applicability of deep reinforcement learning (DRL) for thermal control based on computational fluid dynamics. To accomplish that, the forced convection on a hot plate prone to a pulsating cooling jet with variable velocity has been investigated. We begin with evaluating the efficiency and viability of a vanilla deep Q-network (DQN) method for thermal control. Subsequently, a comprehensive comparison between different variants of DRL was conducted. Soft double and duel DQN achieved better thermal control performance among all the variants due to their efficient learning and action prioritization capabilities. Results demonstrated that the soft double DQN outperformed the hard double DQN. Moreover, soft double and duel can maintain the temperature in the desired threshold for more than 98% of the control cycle. These findings demonstrated the promising potential of DRL in effectively addressing thermal control systems.

show abstract

Optimization of thermal and light in underground atrium commercial spaces: a case study in Xuzhou, China

Nie,

Ji,

Liu

et al. 2023

International Journal of Low-Carbon Technologies

View full text Add to dashboard Cite

This paper studies the shape design strategy of underground atriums in cold regions based on climate adaptability. From the perspective of climate adaptability, by controlling the shape design parameters of the atrium, and taking the light and thermal performance of the underground atrium as the optimization goal, the light and heat performance simulation and multi-objective optimization are constructed. Method, analyzing the effect relationship of various shape parameters on the light and heat environment and exploring the shape scheme of the underground atrium suitable for cold regions. And it is hoped that architects can take into account the quality of the light and heat environment of the underground atrium in architectural design and use space adjustment to improve the awareness of the quality of the light and heat environment of the underground atrium. The simulation results show that the annual PMV thermal comfort time percentage is 20.47%, the heat radiation difference RAD in summer and winter is 21.17 kw∙w/m2, and the average percentage of natural lighting is 67.41%.

show abstract

The building plan automatic design optimization based on CFD numerical intelligent simulation

Cited by 3 publications

References 37 publications

Guidelines for implementing advanced thermal analysis methods in building design

Guidelines for implementing advanced thermal analysis methods in building design

Deep reinforcement learning for the heat transfer control of pulsating impinging jets

Optimization of thermal and light in underground atrium commercial spaces: a case study in Xuzhou, China

Contact Info

Product

Resources

About