Abstract
The application of building information modeling (BIM) in early design phases requires the support of different levels of detail (LOD). This allows scaling to be supported as an important activity of designing. Furthermore, to achieve well-performing solutions in terms of energy efficiency, it is necessary to consider energy performance in early design stages. Therefore, this paper presents a multiLOD modeling approach for the early phases of building design that integrates energy performance prediction based on component-based machine learning (ML) using artificial neural networks (ANN). A model structure with three adaptive LOD definitions is proposed to support the design process by a digital model that supports flexible scaling back and forth. By linking the ML models to the elements in this structure, components are formed that support quick and flexible modeling and energy performance prediction in the early building design process. The transformation rules flexibly link the ML components to all LOD. This approach was illustrated and validated by a test case with a medium-sized office building. The early design states of the case were reconstructed for the application of the method. For validation purposes, the results of the ML predictions for 60 different design configurations were compared to those of a conventional parametric full-detail simulation model. This comparison showed that the average error was no higher than 3.8% for heating and 3.5% for cooling.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Eastman, C., Teicholz, P., Sacks, R., Liston, K.: BIM Handbook. Wiley, Hoboken (2011)
Borrmann, A., König, M., Koch, C., Beetz, J.: Building Information Modeling - Technologische Grundlagen und industrielle Praxis. Springer, Heidelberg (2015). https://doi.org/10.1007/978-3-658-05606-3
Sawhney, A., Maheswari, J.U.: Design Coordination Using Cloud-based Smart Building Element Models. Int. J. Comput. Inf. Syst. Ind. Manag. Appl. 5, 445–453 (2013)
BuildingSMART: Industry Foundation Classes IFC2x4 (2013). http://www.buildingsmart-tech.org/specifications/ifc-releases/ifc4-release/
König, M., Borrmann, A., Geyer, P., Schneider, P., Lang, W., Petzold, F., Schellenbach-Held, M.: Evaluation of building design variants in early phases on the basis of adaptive detailing strategies and system-based simulation of energy flows for such models. In: Presented at the Beyond BIM Workshop, Ghent (2017)
Kim, H., Anderson, K.: Energy modeling system using building information modeling open standards. J. Comput. Civ. Engi. 27, 203–211 (2013)
Singaravel, S., Geyer, P., Suykens, J.: Component-based Machine Learning Modelling Approach For Design Stage Building Energy Prediction. In: IBPSA 2017 (2017)
Geyer, P., Singaravel, S.: Component-based building performance prediction using systems engineering and machine learning. Appl. Energy (2018, submitted)
Schlueter, A., Thesseling, F.: Building information model based energy/exergy performance assessment in early design stages. Autom. Constr. 18, 153–163 (2009)
Clarke, J., Hensen, J.: Integrated building performance simulation: progress, prospects and requirements. Build. Environ. 91, 294–306 (2015)
Gero, J.S., Kumar, B.: Expanding design spaces through new design variables. Des. Stud. 14, 210–221 (1993)
Gane, V., Haymaker, J.: Design scenarios: enabling transparent parametric design spaces. Adv. Eng. Inform. 26, 618–640 (2012)
Østergård, T., Jensen, R.L., Maagaard, S.E.: Building simulations supporting decision making in early design – a review. Renew. Sustain. Energy Rev. 61, 187–201 (2016)
van Treeck, C., Rank, E.: Dimensional reduction of 3D building models using graph theory and its application in building energy simulation. Eng. Comput. 23, 109–122 (2007)
Ahn, K.U., Kim, Y.J., Park, C.S., Kim, I., Lee, K.: BIM interface for full vs. semi-automated building energy simulation. Energy Build. 68, 671–678 (2014)
Gervásio, H., Santos, P., Martins, R., da Silva, L.S.: A macro-component approach for the assessment of building sustainability in early stages of design. Build. Environ. 73, 256–270 (2014)
Dogan, T., Reinhart, C., Michalatos, P.: Autozoner: an algorithm for automatic thermal zoning of buildings with unknown interior space definitions. J. Build. Perform. Simul. 9, 176–189 (2016)
Granadeiro, V., Duarte, J.P., Palensky, P.: Building envelope shape design using a shape grammar-based parametric design system integrating energy simulation. In: IEEE Africon 2011, pp. 1–6. IEEE, Livingstone (2011)
ASHRAE: Standard 90.1–2013. Energy Standard for Buildings Except Low-Rise Residential Buildings, Atlanta, GA (2013)
Stiny, G.: Shape: Talking About Seeing and Doing. MIT Press, Cambridge (2006)
Mitchell, W.J., Liggett, R.S., Pollalis, S.N., Tan, M.: Integrating shape grammars and design analysis. In: Computer Aided Architectural Design Futures: Education, Research, Applications, proceedings of CAAD Futures 1991. pp. 17–32. CAAD Futures, Zürich (1991)
Geyer, P.: Multidisciplinary grammars supporting design optimization of buildings. Res. Eng. Des. 18, 197–216 (2008)
Schmidt, L.C., Shetty, H., Chase, S.C.: A graph grammar approach for structure synthesis of mechanisms. J. Mech. Des. 122, 371–376 (2000)
Helms, B., Shea, K.: Computational synthesis of product architectures based on object-oriented graph grammars. J. Mech. Des. 134, 021008-14 (2012)
BIMForum: Level of Development Specification (2016)
NATSPEC Construction Information: NATSPEC National BIM Guide (2011)
National Institute of Building Sciences buildingSMART alliance: National BIM Standard - United States TM Version 2 (2015)
National Building Specifications: NBS BIM Toolkit. https://toolkit.thenbs.com/support
Building and Construction Authority: Singapore BIM Guide - Version 2.0., Singapore (2013)
NATSPEC BIM - NATSPEC National BIM Guide. https://bim.natspec.org/documents/natspec-national-bim-guide
Yaneva, A.: Scaling up and down: extraction trials in architectural design. Soc. Stud. Sci. 35, 867–894 (2005)
Ammon, S.: Why designing is not experimenting: design methods, epistemic praxis and strategies of knowledge acquisition in architecture. Philos. Technol. 30, 495–520 (2017)
Borrmann, A., Kolbe, T., Donaubauer, A., Steuer, H., Jubierre, J.R.: Transferring multi-scale approaches from 3D city modeling to IFC-based tunnel modeling. In: Proceedings of the 3DGeoInfo, pp. 27–29 (2013)
Borrmann, A., Jubierre, J.R.: A multi-scale tunnel product model providing coherent geometry and semantics. In: Proceedings of the 2013 ASCE International Workshop on Computing in Civil Engineering, pp. 1–8 (2013)
Meng, L., Forberg, A.: 3D building generalisation. Gen. Geogr. Inf. Cartogr. Model. Appl. Elsevier. (2007)
Glander, T., Döllner, J.: Abstract representations for interactive visualization of virtual 3D city models. Comput. Environ. Urban Syst. 33, 375–387 (2009)
Eisenhower, B., O’Neill, Z., Narayanan, S., Fonoberov, V.: A methodology for meta-model based optimization in building energy models. Energy Build. 47, 292–301 (2012)
Magoulès, F., Zhao, H.: Data Mining and Machine Learning in Building Energy Analysis. Wiley Online Library (2016)
Van Gelder, L., Das, P., Janssen, H., Roels, S.: Comparative study of metamodelling techniques in building energy simulation: guidelines for practitioners. Simul. Model. Pract. Theory 49, 245–257 (2014)
Stavrakakis, G., Zervas, P., Sarimveis, H., Markatos, N.: Optimization of window-openings design for thermal comfort in naturally ventilated buildings. Appl. Math. Model. 36, 193–211 (2012)
Cheng, M.-Y., Cao, M.-T.: Accurately predicting building energy performance using evolutionary multivariate adaptive regression splines. Appl. Soft Comput. 22, 178–188 (2014)
Object Management Group: Systems Modeling Language, Specifications Version 1.5. http://www.omg.org/spec/SysML/1.5/
Singaravel, S., Geyer, P., Suykens, J.: Deep neural network architectures for component-based machine learning model in building energy predictions. Presented at the eg-ice Workshop 2017 (2017)
Singaravel, S., Geyer, P., Suykens, J.: Deep learning neural networks architectures and methods: building design energy prediction by component-based models. Adv. Eng. Inform. (2018, submitted)
Acknowledgements
The research presented in this paper was funded by a KU Leuven starting grant StG/14/020 and by the German Research Foundation (DFG) in the Researcher Unit 2363 “Evaluation of building design variants in early phases using adaptive levels of detail” in Subproject 4 “System-based Simulation of Energy Flows”. The multiLOD approach was developed in discussion with the members of the research group (DFG Researcher Unit).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer International Publishing AG, part of Springer Nature
About this paper
Cite this paper
Geyer, P., Singh, M.M., Singaravel, S. (2018). Component-Based Machine Learning for Energy Performance Prediction by MultiLOD Models in the Early Phases of Building Design. In: Smith, I., Domer, B. (eds) Advanced Computing Strategies for Engineering. EG-ICE 2018. Lecture Notes in Computer Science(), vol 10863. Springer, Cham. https://doi.org/10.1007/978-3-319-91635-4_27
Download citation
DOI: https://doi.org/10.1007/978-3-319-91635-4_27
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-91634-7
Online ISBN: 978-3-319-91635-4
eBook Packages: Computer ScienceComputer Science (R0)