Component-Based Machine Learning for Energy Performance Prediction by MultiLOD Models in the Early Phases of Building Design

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.

[1]  Philipp Geyer,et al.  Component-based machine learning for performance prediction in building design , 2018, Applied Energy.

[2]  Min-Yuan Cheng,et al.  Accurately predicting building energy performance using evolutionary multivariate adaptive regression splines , 2014, Appl. Soft Comput..

[3]  Markus König,et al.  Building Information Modeling: technologische Grundlagen und industrielle Praxis , 2015 .

[4]  Rasmus Lund Jensen,et al.  Building simulations supporting decision making in early design – A review , 2016 .

[5]  Andreas Donaubauer,et al.  TRANSFERRING MULTI-SCALE APPROACHES FROM 3D CITY MODELING TO IFC-BASED TUNNEL MODELING , 2013 .

[6]  Philipp Geyer,et al.  Multidisciplinary grammars supporting design optimization of buildings , 2008 .

[7]  Kristina Shea,et al.  Computational Synthesis of Product Architectures Based on Object-Oriented Graph Grammars , 2012 .

[8]  Philipp Geyer,et al.  Deep Neural Network Architectures for Component-Based Machine Learning Model in Building Energy Predictions , 2017 .

[9]  Jan Hensen,et al.  Integrated building performance simulation: Progress, prospects and requirements , 2015 .

[10]  Scott Curland Chase,et al.  A Graph Grammar Approach for Structure Synthesis of Mechanisms , 2000 .

[11]  S. N. Pollalis,et al.  Integrating Shape Grammars and Design Analysis , 1991 .

[12]  John S. Gero,et al.  Expanding design spaces through new design variables , 1993 .

[13]  John Haymaker,et al.  Design Scenarios: Enabling transparent parametric design spaces , 2012, Adv. Eng. Informatics.

[14]  Christoph van Treeck,et al.  Dimensional reduction of 3D building models using graph theory and its application in building energy simulation , 2007, Engineering with Computers.

[15]  Peter Palensky,et al.  Building envelope shape design using a shape grammar-based parametric design system integrating energy simulation , 2011, IEEE Africon '11.

[16]  Philipp Geyer,et al.  Deep-learning neural-network architectures and methods: Using component-based models in building-design energy prediction , 2018, Adv. Eng. Informatics.

[17]  Young Jin Kim,et al.  BIM interface for full vs. semi-automated building energy simulation , 2014 .

[18]  Staf Roels,et al.  Comparative study of metamodelling techniques in building energy simulation: Guidelines for practitioners , 2014, Simul. Model. Pract. Theory.

[19]  Jürgen Döllner,et al.  Abstract representations for interactive visualization of virtual 3D city models , 2009, Comput. Environ. Urban Syst..

[20]  Paulo Santos,et al.  A macro-component approach for the assessment of building sustainability in early stages of design , 2014 .

[21]  Frédéric Magoulès,et al.  Data Mining and Machine Learning in Building Energy Analysis , 2016 .

[22]  Liqiu Meng,et al.  3D Building Generalisation , 2007 .

[23]  Haralambos Sarimveis,et al.  Optimization of window-openings design for thermal comfort in naturally ventilated buildings , 2012 .

[24]  A Sawhney,et al.  Design Coordination Using Cloud-based Smart Building Element Models , 2013 .

[25]  Zheng O'Neill,et al.  A methodology for meta-model based optimization in building energy models , 2012 .

[26]  Albena Yaneva,et al.  Citations (this article cites 5 articles hosted on the SAGE Journals Online and HighWire Press platforms): , 2022 .

[27]  Christoph F. Reinhart,et al.  Autozoner: an algorithm for automatic thermal zoning of buildings with unknown interior space definitions , 2016 .

[28]  Arno Schlueter,et al.  Building information model based energy/exergy performance assessment in early design stages , 2009 .

[29]  Hyunjoo Kim,et al.  Energy Modeling System Using Building Information Modeling Open Standards , 2013 .

[30]  Sabine Ammon,et al.  Why Designing Is Not Experimenting: Design Methods, Epistemic Praxis and Strategies of Knowledge Acquisition in Architecture , 2017 .

[31]  André Borrmann,et al.  A Multi-Scale Tunnel Product Model Providing Coherent Geometry and Semantics , 2013 .