DOI QR코드

DOI QR Code

Novelty detection을 이용한 BIM객체와 IFC 클래스 간 매핑의 무결성 검토에 관한 연구

Applying Novelty Detection for Checking the Integrity of BIM Entity to IFC Class Associations

  • Koo, Bonsang (Department of Civil Engineering, Seoul National University of Science and Technology) ;
  • Shin, Byungjin (Department of Civil Engineering, Seoul National University of Science and Technology)
  • 투고 : 2017.09.15
  • 심사 : 2017.10.27
  • 발행 : 2017.11.30

초록

건설사업의 생애주기 단계별로 BIM의 활용도가 다양해지면서 이를 위한 전문화된 소프트웨어가 증가하고 있다. 이들 소프트웨어 간 BIM 정보 교환 시 상호호환성이 중요하며, 이때 국제표준 포맷인 IFC 데이터 모델을 채택하고 있다. 그러나 BIM 데이터를 IFC로 변환하기 위해서는 개별 객체에 IFC 클래스를 매핑해야 하는데, 현재까지 본 작업은 수동 작업으로 이뤄지고 있어, 매핑 상의 오류나 누락이 발생하게 된다. 본 연구에서는 BIM 객체 및 IFC 클래스 간 매핑의 무결성 검증을 위해 이상탐지분석 기법 중 하나인 Novelty detection을 적용하였다. 동일한 IFC 클래스의 객체들은 기하형상이 유사하다는 전제하에. 매핑이 잘못된 객체를 이상치로 판별하고자 하는 것이다. 3개의 BIM모델로부터 IFC 클래스별로 객체를 분류한 후 이 중 2개의 IFC 클래스(벽체 및 문)에 대해 one-class SVM을 학습시키고 검증하였다. 분석한 결과 총 160개의 이상치 중 141개를 정확하게 분류하여 이상치 판별능력이 높게 나왔다. Novelty detection 기법은 다중 경계면을 형성하고 사전적 학습이 가능하다는 점에서 높은 예측력을 발휘하여, 기존 방식이나 타 알고리즘보다 매핑 오류를 검증하는데 더 적합한 방법인 것으로 확인되었다.

With the growing use of BIM in the AEC industry, various new applications are being developed to meet these specific needs. Such developments have increased the importance of Industry Foundation Classes, which is the international standard for sharing BIM data and thus ensuring interoperability. However, mapping individual BIM objects to IFC entities is still a manual task, and is a main cause for errors or omissions during data transfers. This research focused on addressing this issue by applying novelty detection, which is a technique for detecting anomalies in data. By training the algorithm to learn the geometry of IFC entities, misclassifications (i.e., outliers) can be detected automatically. Two IFC classes (ifcWall, ifcDoor) were trained using objects from three BIM models. The results showed that the algorithm was able to correctly identify 141 of 160 outliers. Novelty detection is thus suggested as a competent solution to resolve the mapping issue, mainly due to its ability to create multiple inlier boundaries and ex ante training of element geometry.

키워드

참고문헌

  1. Belsky, M., Sacks, R., and Brilakis, I. (2016). "Semantic Enrichment for Building Information Modeling" Computer-Aided Civil and Infrastructure Engineering, 31(4), pp. 261-274. https://doi.org/10.1111/mice.12128
  2. Chang, C.-C., Chih-Wei Hsu, and Chih-Jen Lin. (2016). "A Practical Guide to Support Vector Classification" pp. 1-16.
  3. Daum, S., and Borrmann, A. (2014). "Processing of Topological BIM Queries using Boundary Representation Based Methods" Advanced Engineering Informatics, 28(4), pp. 272-286. https://doi.org/10.1016/j.aei.2014.06.001
  4. Dudas, P. M., Ghafourian, M., and Karimi, H. A. (2009) . "ONALIN: Ontology and Algorithm for Indoor Routing" Presented at the 2009 Tenth International Conference on Mobile Data Management: Systems, Taipei, Taiwan.
  5. Froese, T., Grobler, F., Ritzenthaler, J., Yu, K., Akinci, B., Akbas, R., et al. (1999). "Industry Foundation Classes for Project Management - A Trial Implementation" Journal of Information Technology in Construction (ITcon), 4(2), pp. 17-36.
  6. Japkowicz, N., Myers, C., and Gluck, M. (1995). "A novelty detection approach to classification" Proceedings of international joint conferences on artificial intelligence, Quebec, Canada.
  7. Kang, T. W. (2015). "Open source viewer-based BIM Query Development for BIM information visualization" Journal of KIBIM, 5(2), pp. 19-25. https://doi.org/10.13161/kibim.2015.5.2.019
  8. Kim, H., and Grobler, F. (2009). "Design Coordination in Building Information Modeling (BIM) Using Ontological Consistency Checking" Presented at the International Workshop on Computing in Civil Engineering, Austin, Texas.
  9. Kiviniemi, A. (2009). "IFC certification process and data exchange problems" eWork and eBusiness in Architecture, Engineering and Construction, Taylor and Francis Group, London.
  10. Koo, B., and Shin, B. (2017). "Using Geometry based Anomaly Detection to check the Integrity of IFC classification in BIM Models" Journal of KIBIM, pp. 1-10.
  11. Krijnen, T., and Tamke, M. (2015). "Assessing implicit knowledge in BIM models with machine learning" Modelling Behaviour.
  12. Lee, S. K., Kim, K. R., and Yu, J. H. (2014). "BIM and ontology-based approach for building cost estimation" Automation in Construction, 41, pp. 96-105. https://doi.org/10.1016/j.autcon.2013.10.020
  13. Lipman, R., Palmer, M., and Palacios, S. (2011). "Assessment of conformance and interoperability testing methods used for construction industry product models" Automation in Construction, 20(4), pp. 418-428. https://doi.org/10.1016/j.autcon.2010.11.011
  14. Manevitz, L. M., and Yousef, M. (2001). "One-Class SVMs for Document Classification" Journal of Machine Learning Research, 2(Dec), pp. 139-154.
  15. Mazairac, W., and Beetz, J. (2013). "BIMQL - An open query language for building information models" Advanced Engineering Informatics, 27(4), pp. 444-456. https://doi.org/10.1016/j.aei.2013.06.001
  16. Pauwels, P., Terkaj, W., Krijnen, T., and Beetz, J. (2015). Coping with lists in the ifcOWL ontology. Proceedings of 22nd EG-ICE International Workshop, Eindhoven University of Technology, The Netherlands.
  17. Pauwels, P., and Terkaj, W. (2016). "EXPRESS to OWL for construction industry: Towards a recommendable and usable ifcOWL ontology" Automation in Construction, 63, pp. 100-133. https://doi.org/10.1016/j.autcon.2015.12.003
  18. Smola, A., and Vishwanathan, S. V. N. (2008). "Introduction to Machine Learning" Cambridge University Press, pp. 165-172.
  19. Tauscher, E., Bargstadt, H.-J., and Smarsly, K. (2016). "Generic BIM queries based on the IFC object model using graph theory" The 16th International Conference on Computing in Civil and Building Engineering, At Osaka, Japan.