Towards Sustainable Architecture: 3D Convolutional Neural Networks for Computational Fluid Dynamics Simulation and Reverse DesignWorkflow

Musil, J.; Knir, Jakub; Vitsas, Athanasios; Gallou, Irene

doi:10.48550/arxiv.1912.02125

Cited by 3 publications

(4 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…cGANs have been trained on low-resolution scans of hand-drafted plan drawings to generate new plan drawings (Challiou 2017; Kvochick 2018). Other contemporary research has explored the image-to-image translation to shortcut CFD simulation (Galanos et al 2019;Mokhtar et al 2020;Musil et al 2019), using a 2D ground-fl oor plan input to represent building boundaries. However, in cases such as these, the limits of 2D representation enforce a radically simplifi ed representation of architectural form, so that it can be encoded into a one-dimensional representational space.…”

Section: Methods Representationmentioning

confidence: 99%

Encoded Images

Rossi,

Nicholas

2020

Proceedings of the 40th Annual Conference of the Association of Computer Aided Design in Architecture (ACADIA)

View full text Add to dashboard Cite

show abstract

Section: Methods Representationmentioning

confidence: 99%

Encoded Images

Rossi,

Nicholas

2020

Proceedings of the 40th Annual Conference of the Association of Computer Aided Design in Architecture (ACADIA)

View full text Add to dashboard Cite

show abstract

“…The emerging convolutional neural networks and generative adversarial networks in the field of computer vision provide some solutions. For example, Musil proposed the ResNet for approximating real-time prediction of three-dimensional steady-state conditions to predict the wind speed distribution around building structures within a wind field range of 256 m × 128 m × 64 m, under specific wind speed conditions [14]. Mokhtar trained a conditional generative adversarial network approach using 2800 cases as a surrogate model, which can predict the pedestrian wind environment of different building forms in seconds [9].…”

Section: Development Combined With Machine Learningmentioning

confidence: 99%

“…Artificial neural network [19] investigating the relationship between CO 2 concentration and environmental parameters 79.3% 2760 [12] investigating the relationship between plan shapes, surface pressure distribution, and the air change per hour. MAE = 21.3% MAPE = 43.1% 600 [13,20] investigating the relationship between inlet vent speed and distribution of velocities within a specific room R2 = 0.97 Sampling from 5 cases Convolutional neural network [14] investigating the distribution of wind speeds within a specific wind field no quantitative expression 3325 [21] no quantitative expression 8800 [2] Relative error = 1.76% Physics-informed neural networks [17] the multi-physics with initial and boundary conditions known no quantitative expression 6000…”

Section: Sample Sizementioning

confidence: 99%

A Convolutional Neural Network for Steady-State Flow Approximation Trained on a Small Sample Size

Zhong,

Xu,

Feng

et al. 2023

Atmosphere

View full text Add to dashboard Cite

The wind microclimate plays an important role in architectural design, and computational fluid dynamics is a method commonly used for analyzing the issue. However, due to its high technical difficulty and time-consuming nature, it limits the interaction and exploration between designers and environment performance analyses. To address the issue, scholars have proposed a series of approximation models based on machine learning that have partially improved computational efficiency. However, these methods face challenges in terms of balancing applicability, prediction accuracy, and sample size. In this paper, we propose a method based on the classic Vggnet deep convolutional neural network as the backbone to construct an approximate model for predicting steady-state flow fields in urban areas. The method is trained on a small amount of sample data and can be extended to calculate the wind environment performance. Furthermore, we investigated the differences between geometric representation methods, such as the Boolean network representation and signed distance function, as well as different structure models, such as Vgg-CFD-11, Vgg-CFD-13, Vgg-CFD-16, and Vgg-CFD-19. The results indicate that the model can be trained using a small amount of sample data, and all models generally possess the ability to predict the wind environment. The best performance on the validation set and test set was achieved with an RMSE (Root Mean Square Error) of 0.7966 m/s and 2.2345 m/s, respectively, and an R-Squared score of 0.9776 and 0.8455. Finally, we embedded the best-performing model into an architect-friendly urban comprehensive analysis platform, URBAN NEURAL-CFD.

show abstract

“…This approach enables virtual visualization of processes inside the equipment and provides the ability to perform quick what-if analyses, explore operational space, provide information to troubleshoot equipment, and detect or ameliorate anomalies. 9 Warey et al 10 applied three ML algorithms (linear regression with stochastic gradient descent, random forests [RFs] and artificial neural network [ANN]) to CFD data from an automotive heating, ventilation, and air-conditioning system to predict thermal comfort to occupants over a range of operating and environmental conditions. Mosavi et al 11 combined ML and CFD to simulate the fluid structure and interaction between phases in a cylindrical bubble column wherein the ability to learn complex relationships according to the pattern data was demonstrated.…”

Section: Introductionmentioning

confidence: 99%

Prediction of melter cold‐cap topology from plenum temperatures with computational fluid dynamics and machine learning

Abboud

Guillen

Christensen

2022

Int J Ceramic Engine & Sci

View full text Add to dashboard Cite

A computational fluid dynamics (CFD) model of a pilot‐scale waste‐glass melter was used to generate input data for several different machine‐learning models to predict the cold‐cap coverage from plenum temperatures. This methodology could serve as useful to provide nonvisual feedback for operational control. The machine‐learning models tested include an artificial neural network (ANN), a convolutional neural network (CNN), a random forest (RF) algorithm, and a support vector machine (SVM) method. CFD simulations with randomized cold‐cap coverage were run to generate plenum‐temperature distributions. The topology of the cold cap was predicted with each method using an input layer of selected temperature locations. The ANN was used to predict the cold‐cap coverage percentage with an accuracy of 1.2%. The accuracy of the various machine‐learning algorithms was dependent on the filter resolution employed. When using a low resolution (16‐cm filter), the CNN and ANN methods produced the best accuracy, with errors of 6.98% and 6.58%, respectively. At finer levels of resolution (4‐cm filter), the RF method produced the best accuracy, with an error of 8.12%. The ANN and SVM methods required less computational time to train than either the CNN or RF methods.

show abstract

Towards Sustainable Architecture: 3D Convolutional Neural Networks for Computational Fluid Dynamics Simulation and Reverse DesignWorkflow

Cited by 3 publications

References 0 publications

Encoded Images

Encoded Images

A Convolutional Neural Network for Steady-State Flow Approximation Trained on a Small Sample Size

Prediction of melter cold‐cap topology from plenum temperatures with computational fluid dynamics and machine learning

Contact Info

Product

Resources

About