Multi-objective optimisation of a free-form building shape to improve the solar energy utilisation potential using artificial neural networks

Xin Zhao; Yunsong Han; Linhai Shen

Multi-objective optimisation of a free-form building shape to improve the solar energy utilisation potential using artificial neural networks

Xin Zhao
, Yunsong Han^*
, Linhai Shen

^*Corresponding author for this work

Harbin institute of technology

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

6 Scopus citations

Abstract

Optimisation of free-form building design is more challenging in terms of building information modelling and performance evaluation compared to conventional buildings. The paper provides a "Photogrammetry-based BIM Modelling - Machine Learning Modelling - Multi-objective Optimisation" framework to improve the solar energy utilisation potential of free-form buildings. Low altitude photogrammetry is used to collect the building and site environmental information. An ANN prediction model is developed using the control point coordinates and simulation data. Through parametric programming, the multi-objective algorithm is coupled with the ANN model to obtain the trade-off optimal building form. The results show that the maximum solar radiation value in winter can increase by 30.60% and the minimum solar radiation in summer can decrease by 13.99%. It is also shown that the integration of ANN modelling and photogrammetry-based BIM modelling into the multi-objective optimisation method can accelerate the optimisation process.

Original language	English
Title of host publication	Projections - Proceedings of the 26th International Conference of the Association for Computer-Aided Architectural Design Research in Asia, CAADRIA 2021
Editors	Anastasia Globa, Jeroen van Ameijde, Adam Fingrut, Nayeon Kim, Tian Tian Sky Lo
Publisher	The Association for Computer-Aided Architectural Design Research in Asia (CAADRIA)
Pages	221-230
Number of pages	10
ISBN (Electronic)	9789887891758
State	Published - 2021
Externally published	Yes
Event	26th International Conference of the Association for Computer-Aided Architectural Design Research in Asia: Projections, CAADRIA 2021 - Hong Kong, Hong Kong Duration: 29 Mar 2021 → 1 Apr 2021

Publication series

Name	Projections - Proceedings of the 26th International Conference of the Association for Computer-Aided Architectural Design Research in Asia, CAADRIA 2021
Volume	1

Conference

Conference	26th International Conference of the Association for Computer-Aided Architectural Design Research in Asia: Projections, CAADRIA 2021
Country/Territory	Hong Kong
City	Hong Kong
Period	29/03/21 → 1/04/21

Keywords

Artificial neural network
Free-form shape building
Multi-objective optimisation
Solar energy utilisation

Cite this

Zhao, X., Han, Y., & Shen, L. (2021). Multi-objective optimisation of a free-form building shape to improve the solar energy utilisation potential using artificial neural networks. In A. Globa, J. van Ameijde, A. Fingrut, N. Kim, & T. T. S. Lo (Eds.), Projections - Proceedings of the 26th International Conference of the Association for Computer-Aided Architectural Design Research in Asia, CAADRIA 2021 (pp. 221-230). (Projections - Proceedings of the 26th International Conference of the Association for Computer-Aided Architectural Design Research in Asia, CAADRIA 2021; Vol. 1). The Association for Computer-Aided Architectural Design Research in Asia (CAADRIA).

Zhao, Xin ; Han, Yunsong ; Shen, Linhai. / Multi-objective optimisation of a free-form building shape to improve the solar energy utilisation potential using artificial neural networks. Projections - Proceedings of the 26th International Conference of the Association for Computer-Aided Architectural Design Research in Asia, CAADRIA 2021. editor / Anastasia Globa ; Jeroen van Ameijde ; Adam Fingrut ; Nayeon Kim ; Tian Tian Sky Lo. The Association for Computer-Aided Architectural Design Research in Asia (CAADRIA), 2021. pp. 221-230 (Projections - Proceedings of the 26th International Conference of the Association for Computer-Aided Architectural Design Research in Asia, CAADRIA 2021).

@inproceedings{ee0f057664e641619fb3b4b51c9b4266,

title = "Multi-objective optimisation of a free-form building shape to improve the solar energy utilisation potential using artificial neural networks",

abstract = "Optimisation of free-form building design is more challenging in terms of building information modelling and performance evaluation compared to conventional buildings. The paper provides a {"}Photogrammetry-based BIM Modelling - Machine Learning Modelling - Multi-objective Optimisation{"} framework to improve the solar energy utilisation potential of free-form buildings. Low altitude photogrammetry is used to collect the building and site environmental information. An ANN prediction model is developed using the control point coordinates and simulation data. Through parametric programming, the multi-objective algorithm is coupled with the ANN model to obtain the trade-off optimal building form. The results show that the maximum solar radiation value in winter can increase by 30.60\% and the minimum solar radiation in summer can decrease by 13.99\%. It is also shown that the integration of ANN modelling and photogrammetry-based BIM modelling into the multi-objective optimisation method can accelerate the optimisation process.",

keywords = "Artificial neural network, Free-form shape building, Multi-objective optimisation, Solar energy utilisation",

author = "Xin Zhao and Yunsong Han and Linhai Shen",

note = "Publisher Copyright: {\textcopyright} 2021 and published by the Association for Computer-Aided Architectural Design Research in Asia (CAADRIA), Hong Kong.; 26th International Conference of the Association for Computer-Aided Architectural Design Research in Asia: Projections, CAADRIA 2021 ; Conference date: 29-03-2021 Through 01-04-2021",

year = "2021",

language = "英语",

series = "Projections - Proceedings of the 26th International Conference of the Association for Computer-Aided Architectural Design Research in Asia, CAADRIA 2021",

publisher = "The Association for Computer-Aided Architectural Design Research in Asia (CAADRIA)",

pages = "221--230",

editor = "Anastasia Globa and \{van Ameijde\}, Jeroen and Adam Fingrut and Nayeon Kim and Lo, \{Tian Tian Sky\}",

booktitle = "Projections - Proceedings of the 26th International Conference of the Association for Computer-Aided Architectural Design Research in Asia, CAADRIA 2021",

}

Zhao, X, Han, Y & Shen, L 2021, Multi-objective optimisation of a free-form building shape to improve the solar energy utilisation potential using artificial neural networks. in A Globa, J van Ameijde, A Fingrut, N Kim & TTS Lo (eds), Projections - Proceedings of the 26th International Conference of the Association for Computer-Aided Architectural Design Research in Asia, CAADRIA 2021. Projections - Proceedings of the 26th International Conference of the Association for Computer-Aided Architectural Design Research in Asia, CAADRIA 2021, vol. 1, The Association for Computer-Aided Architectural Design Research in Asia (CAADRIA), pp. 221-230, 26th International Conference of the Association for Computer-Aided Architectural Design Research in Asia: Projections, CAADRIA 2021, Hong Kong, Hong Kong, 29/03/21.

Multi-objective optimisation of a free-form building shape to improve the solar energy utilisation potential using artificial neural networks. / Zhao, Xin; Han, Yunsong; Shen, Linhai.
Projections - Proceedings of the 26th International Conference of the Association for Computer-Aided Architectural Design Research in Asia, CAADRIA 2021. ed. / Anastasia Globa; Jeroen van Ameijde; Adam Fingrut; Nayeon Kim; Tian Tian Sky Lo. The Association for Computer-Aided Architectural Design Research in Asia (CAADRIA), 2021. p. 221-230 (Projections - Proceedings of the 26th International Conference of the Association for Computer-Aided Architectural Design Research in Asia, CAADRIA 2021; Vol. 1).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Multi-objective optimisation of a free-form building shape to improve the solar energy utilisation potential using artificial neural networks

AU - Zhao, Xin

AU - Han, Yunsong

AU - Shen, Linhai

PY - 2021

Y1 - 2021

N2 - Optimisation of free-form building design is more challenging in terms of building information modelling and performance evaluation compared to conventional buildings. The paper provides a "Photogrammetry-based BIM Modelling - Machine Learning Modelling - Multi-objective Optimisation" framework to improve the solar energy utilisation potential of free-form buildings. Low altitude photogrammetry is used to collect the building and site environmental information. An ANN prediction model is developed using the control point coordinates and simulation data. Through parametric programming, the multi-objective algorithm is coupled with the ANN model to obtain the trade-off optimal building form. The results show that the maximum solar radiation value in winter can increase by 30.60% and the minimum solar radiation in summer can decrease by 13.99%. It is also shown that the integration of ANN modelling and photogrammetry-based BIM modelling into the multi-objective optimisation method can accelerate the optimisation process.

AB - Optimisation of free-form building design is more challenging in terms of building information modelling and performance evaluation compared to conventional buildings. The paper provides a "Photogrammetry-based BIM Modelling - Machine Learning Modelling - Multi-objective Optimisation" framework to improve the solar energy utilisation potential of free-form buildings. Low altitude photogrammetry is used to collect the building and site environmental information. An ANN prediction model is developed using the control point coordinates and simulation data. Through parametric programming, the multi-objective algorithm is coupled with the ANN model to obtain the trade-off optimal building form. The results show that the maximum solar radiation value in winter can increase by 30.60% and the minimum solar radiation in summer can decrease by 13.99%. It is also shown that the integration of ANN modelling and photogrammetry-based BIM modelling into the multi-objective optimisation method can accelerate the optimisation process.

KW - Artificial neural network

KW - Free-form shape building

KW - Multi-objective optimisation

KW - Solar energy utilisation

UR - https://www.scopus.com/pages/publications/85104658828

M3 - 会议稿件

AN - SCOPUS:85104658828

T3 - Projections - Proceedings of the 26th International Conference of the Association for Computer-Aided Architectural Design Research in Asia, CAADRIA 2021

SP - 221

EP - 230

BT - Projections - Proceedings of the 26th International Conference of the Association for Computer-Aided Architectural Design Research in Asia, CAADRIA 2021

A2 - Globa, Anastasia

A2 - van Ameijde, Jeroen

A2 - Fingrut, Adam

A2 - Kim, Nayeon

A2 - Lo, Tian Tian Sky

PB - The Association for Computer-Aided Architectural Design Research in Asia (CAADRIA)

T2 - 26th International Conference of the Association for Computer-Aided Architectural Design Research in Asia: Projections, CAADRIA 2021

Y2 - 29 March 2021 through 1 April 2021

ER -

Zhao X, Han Y, Shen L. Multi-objective optimisation of a free-form building shape to improve the solar energy utilisation potential using artificial neural networks. In Globa A, van Ameijde J, Fingrut A, Kim N, Lo TTS, editors, Projections - Proceedings of the 26th International Conference of the Association for Computer-Aided Architectural Design Research in Asia, CAADRIA 2021. The Association for Computer-Aided Architectural Design Research in Asia (CAADRIA). 2021. p. 221-230. (Projections - Proceedings of the 26th International Conference of the Association for Computer-Aided Architectural Design Research in Asia, CAADRIA 2021).

Multi-objective optimisation of a free-form building shape to improve the solar energy utilisation potential using artificial neural networks

Abstract

Publication series

Conference

Keywords

Other files and links

Fingerprint

Cite this