Assessing Implicit Knowledge in BIM Models with Machine Learning

  • Thomas Krijnen
  • Martin Tamke


The promise, which comes along with Building Information Models, is that they are information rich, machine readable and represent the insights of multiple building disciplines within single or linked models. However, this knowledge has to be stated explicitly in order to be understood. Trained architects and engineers are able to deduce non-explicitly explicitly stated information, which is often the core of the transported architectural information. This paper investigates how machine learning approaches allow a computational system to deduce implicit knowledge from a set of BIM models.


  1. Beetz J et al (2014) D3.3 semantic digital archive prototype. Accessed May 2015
  2. buildingSMART (2014) buildingSMART. Accessed May 2015
  3. Corney J et al (2002) Coarse filters for shape matching. IEEE Comput Graph Appl 22(3):65–74CrossRefGoogle Scholar
  4. Daum S, Borrmann A (2014) Processing of topological BIM queries using boundary representation based methods. Adv Eng Inform 28(4):272–286CrossRefGoogle Scholar
  5. Davis D (2014) Quantitatively Analysing Parametric Models. Int J Archit Comput 12(3):307–320CrossRefGoogle Scholar
  6. DURAARK (2015) DURAARK Project. Accessed May 2015
  7. Geospatial Media and Communications (2014) GeoBim. Accessed May 2015
  8. Krijnen T (2015a) DURAARK/pyIfcExtract. Accessed May 2015
  9. Krijnen T (2015b) IfcOpenShell. Accessed May 2015
  10. Mazairac W, Beetz J (2013) BIMQL—An open query language for building information models. Adv Eng Inform 27(4):444–456CrossRefGoogle Scholar
  11. Mitchell T (1997) Machine learning. McGraw Hill, New York CityzbMATHGoogle Scholar
  12. NIBS (2013) Buildingsmart alliance common building information model files and tools—national institute of building sciences. Accessed May 2015
  13. Paviot T (2014) Pythonocc, 3D CAD/CAE/PLM development framework for the python programming language. Accessed May 2015
  14. Pedregosa F et al (2011) Scikit-learn: machine learning in python. J Mach Learn Res 12:2825–2830MathSciNetzbMATHGoogle Scholar
  15. Schaul T et al (2010) PyBrain. J Mach Learn Res 11:743–746Google Scholar
  16. Solibri (2015) Solibri model checker. Accessed May 2015
  17. Stasiuk D, Thomsen MR (2014) Learning to be a vault—implementing learning strategies for design exploration in inter-scalar systems. Newcastle upon Tyne, England, pp 381–390Google Scholar
  18. Tamke M et al (2014a) D7.7.1—Current state of 3D object processing in architectural research and practice.
  19. Tamke M et al (2014b) Building information deduced—state and potentials for information query in building information modelling. Newcastle upon Tyne, England, pp 375–384Google Scholar
  20. Zhang C, Beetz J, Weise M (2014) Interoperable validation for IFC building models using open standards. ITcon vol 20, Special Issue ECPPM 2014—10th European conference on product and process modelling, pp 24–39Google Scholar

Copyright information

© Springer International Publishing Switzerland 2015

Authors and Affiliations

  • Thomas Krijnen
    • 1
  • Martin Tamke
    • 2
  1. 1.Department of the Built EnvironmentEindhoven University of TechnologyEindhovenThe Netherlands
  2. 2.Centre for IT and ArchitectureRoyal Danish Academy of Fine Art, School of ArchitectureCopenhagenDenmark

Personalised recommendations