Cumincad : CUMINCAD Papers : Search Results

CumInCAD is a Cumulative Index about publications in Computer Aided Architectural Design
supported by the sibling associations ACADIA, CAADRIA, eCAADe, SIGraDi, ASCAAD and CAAD futures

PDF papers
References

Hits 1 to 2 of 2

Reformat results as: short short into frame detailed detailed into frame

_id	ecaaderis2023_11
id	ecaaderis2023_11
authors	Sepúlveda, Abel, Eslamirad, Nasim, Seyed Salehi, Seyed Shahabaldin, Thalfeldt, Martin and De Luca, Francesco
year	2023
title	Machine Learning-based Optimization Design Workflow based on Obstruction Angles for Building Facades
source	De Luca, F, Lykouras, I and Wurzer, G (eds.), Proceedings of the 9th eCAADe Regional International Symposium, TalTech, 15 - 16 June 2023, pp. 15–24
summary	This paper proposes a ML-based optimization design workflow based on obstruction angles for the optimization of building facades (i.e. g-value and window width). The optimization output consists of the optimal clustering of windows in order to ensure a desired level of daylight provision according to method 2 defined in the EN17307:2018 (i.e. based on Spatial Daylight Autonomy: sDA) and to not exceed a maximum level of specific cooling capacity (SCC). The independent variables or design parameters of the parametric model are: room orientation/dimensions, window dimensions, and obstruction angle (??). The ML prediction models were trained and tested with reliable simulation results using validate softwares. The total number of room combinations is 61440 for sDA and SCC simulations. The development of reliable (90% of right predictions) ML predictive models based on decision tree technique were calibrated. The optimal clustering of windows was done first by floors and secondly by the designer’s need to homogenize the external facade with similar glazing properties and window sizes, having impact on the annual heating consumption. The proposed method help designers to make accurate and faster design decisions during early design stages and renovation plans.
keywords	optimization, daylight, thermal comfort, cooling capacity, machine-learning predictive model, office buildings, cold climates
series	eCAADe
email
last changed	2024/02/05 14:28

_id	ecaade2023_10
id	ecaade2023_10
authors	Sepúlveda, Abel, Eslamirad, Nasim and De Luca, Francesco
year	2023
title	Machine Learning Approach versus Prediction Formulas to Design Healthy Dwellings in a Cold Climate
source	Dokonal, W, Hirschberg, U and Wurzer, G (eds.), Digital Design Reconsidered - Proceedings of the 41st Conference on Education and Research in Computer Aided Architectural Design in Europe (eCAADe 2023) - Volume 2, Graz, 20-22 September 2023, pp. 359–368
doi	https://doi.org/10.52842/conf.ecaade.2023.2.359
summary	This paper presents a study about the prediction accuracy of daylight provision and overheating levels in dwellings when considering different methods (machine learning vs prediction formulas), training, and validation data sets. An existing high-rise building located in Tallinn, Estonia was considered to compare the best ML predictive method with novel prediction formulas. The quantification of daylight provision was conducted according to the European daylight standard EN 17037:2018 (based on minimum Daylight Factor (minDF)) and overheating level in terms of the degree-hour (DH) metric included in local regulations. The features included in the dataset are the minDF and DH values related to different combinations of design parameters: window-to-floor ratio, level of obstruction, g-value, and visible transmittance of the glazing system. Different training and validation data sets were obtained from a main data set of 5120 minDF values and 40960 DH values obtained through simulation with Radiance and EnergyPlus, respectively. For each combination of training and validation dataset, the accuracy of the ML model was quantified and compared with the accuracy of the prediction formulas. According to our results, the ML model could provide more accurate minDF/DH predictions than by using the prediction formulas for the same design parameters. However, the amount of room combinations needed to train the machine-learning model is larger than for the calibration of the prediction formulas. The paper discuss in detail the method to use in practice, depending on time and accuracy concerns.
keywords	Optimization, Daylight, Thermal Comfort, Overheating, Machine Learning, Predictive Model, Dwellings, Cold Climates
series	eCAADe
email
last changed	2023/12/10 10:49

No more hits.