Simplified Scan-vs-BIM Frameworks for Automated Structural Inspection of Steel Structures
Source abstract
Abstract
This paper presents a deep learning-based Scan-vs-BIM methodology for evaluating structural integrity through the extraction of features from As-Built scan and As-Planned Building Information Modeling (BIM) comparison data. Traditional Scan-vs-BIM frameworks often rely on Scan-to-BIM processes to generate point cloud-based mesh models for comparison, which significantly impairs computational efficiency. In contrast, the proposed streamlined Scan-vs-BIM framework incorporates a deep neural network (DNN) model consisting of two neural networks: one for structural integrity assessment and another for error type analysis. The model evaluates the structural integrity of individual components in a sequential manner, repeating the process across all elements to comprehensively assess the entire structure. Rather than converting point cloud data into mesh models for comparison, this approach directly measures the spatial discrepancies between the As-Built point cloud and As-Planned BIM, analyzing the distribution tendencies of these distance values. Experimental validation on actual steel structures demonstrated that the proposed method effectively predicts structural integrity, providing significant improvements in both accuracy and computational performance.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Infrastructure Maintenance and Monitoring · 3D Surveying and Cultural Heritage · BIM and Construction Integration
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Architectural Engineering, Hanyang University, Seoul 04763, Republic of Korea
Department of Digital Architecture and Urban Engineering, Hanyang Cyber University, Seoul 04763, Republic of Korea
References (45)
Show source-provided references
1. Usmen, M., and Vilnitis, M. (2015). Evaluation of safety, quality and productivity in construction. IOP Conference Series: Materials Science and Engineering, IOP Publishing.10.1088/1757-899X/96/1/012061 ↗
2. Schaufelberger, J.E., and Holm, L. (2017). Management of Construction Projects: A Constructor’s Perspective, Routledge.10.4324/9781315529097 ↗
3. Stage-wise evaluation of integrity risks in public works procurement in India
4. Ladars for construction assessment and update10.1016/S0926-5805(00)00058-3 ↗
5. Point cloud quality requirements for Scan-vs-BIM based automated construction progress monitoring10.1016/j.autcon.2017.09.021 ↗
6. D4AR–a 4-dimensional augmented reality model for automating construction progress monitoring data collection, processing and communication
7. Patterns and trends in building information modeling (BIM) research: A latent semantic analysis10.1016/j.autcon.2015.07.012 ↗
8. Automated progress control using laser scanning technology10.1016/j.autcon.2013.08.012 ↗
9. Tracking the built status of MEP works: Assessing the value of a Scan-vs-BIM system10.1061/(ASCE)CP.1943-5487.0000343 ↗
10. The value of integrating Scan-to-BIM and Scan-vs-BIM techniques for construction monitoring using laser scanning and BIM: The case of cylindrical MEP components10.1016/j.autcon.2014.05.014 ↗
11. Wallbaum, M., and Soman, R.K. (2021, January 26–28). Towards real-time Scan-versus-BIM: Methods applications and challenges. Proceedings of the 2021 European Conference on Computing in Construction, Online.10.35490/EC3.2021.176 ↗
12. Wang, Q., Guo, J., and Kim, M.-K. (2019). An application oriented scan-to-BIM framework. Remote Sens., 11.10.3390/rs11030365 ↗
13. Integrating as-built BIM model from point cloud data in construction projects10.1108/ECAM-12-2022-1196 ↗
14. Classification and analysis of deep learning applications in construction: A systematic literature review10.1016/j.autcon.2021.103760 ↗
15. Deep learning in the construction industry: A review of present status and future innovations10.1016/j.jobe.2020.101827 ↗
16. A comparison between photogrammetry and laser scanning10.1016/S0924-2716(99)00014-3 ↗
17. Integrating 3D laser scanning and photogrammetry for progress measurement of construction work10.1016/j.autcon.2008.05.006 ↗
18. US General Services Administration (2009). GSA Building Information Modeling Guide Series: 03.
19. Automated retrieval of 3D CAD model objects in construction range images10.1016/j.autcon.2007.09.001 ↗
20. Comparison of point cloud data and 3D CAD data for on-site dimensional inspection of industrial plant piping systems10.1016/j.autcon.2018.03.008 ↗
21. Kim, S., Kim, S., and Lee, D.-E. (2020). 3D point cloud and BIM-based reconstruction for evaluation of project by as-planned and as-built. Remote Sens., 12.10.3390/rs12091457 ↗
22. Automatic modeling of prefabricated components with laser-scanned data for virtual trial assembly10.1111/mice.12627 ↗
23. Maalek, R. (2021). Field Information Modeling (FIM)™: Best Practices Using Point Clouds. Remote Sens., 13.10.20944/preprints202102.0304.v1 ↗
24. Deep learning10.1038/nature14539 ↗
25. Werbos, P. (1974). Beyond Regression: New Tools for Prediction and Analysis in the Behavioral Sciences. [Ph.D. Thesis, Harvard University].
26. Goodfellow, I., Bengio, Y., and Courville, A. (2016). Deep Learning, MIT Press.
27. Vargas, R., Mosavi, A., and Ruiz, R. (2018). Deep Learning: A Review. Preprints, 2018100218.10.20944/preprints201810.0218.v1 ↗
28. Automatic classification of wall and door BIM element subtypes using 3D geometric deep neural networks10.1016/j.aei.2020.101200 ↗
29. A novel DNN tracking algorithm for structural system identification
30. Structure-aware 3D reconstruction for cable-stayed bridges: A learning-based method10.1111/mice.12568 ↗
31. Vision-assisted BIM reconstruction from 3D LiDAR point clouds for MEP scenes10.1016/j.autcon.2021.103997 ↗
32. Scan2BIM-NET: Deep learning method for segmentation of point clouds for scan-to-BIM10.1061/(ASCE)CO.1943-7862.0002132 ↗
33. Automated extraction of structural beam lines and connections from point clouds of steel buildings10.1111/mice.12699 ↗
34. Real-time detection of cracks in tiled sidewalks using YOLO-based method applied to unmanned aerial vehicle (UAV) images10.1016/j.autcon.2023.104745 ↗
35. Extracting full-field subpixel structural displacements from videos via deep learning10.1016/j.jsv.2021.116142 ↗
36. American Institute of Steel Construction (2016). Code of Standard Practice for Steel Buildings and Bridges, American Institute of Steel Construction.
37. Approximate boolean operations on large polyhedral solids with partial mesh reconstruction10.1109/TVCG.2010.106 ↗
38. Gelfand, N., Ikemoto, L., Rusinkiewicz, S., and Levoy, M. (2003, January 6–10). Geometrically stable sampling for the ICP algorithm. Proceedings of the Fourth International Conference on 3-D Digital Imaging and Modeling 2003 (3DIM 2003 Proceedings), Banff, AB, Canada.
39. Compatibility-guided sampling consensus for 3-D point cloud registration10.1109/TGRS.2020.2982221 ↗
40. Qi, C.R., Yi, L., Su, H., and Guibas, L.J. (2017, January 4–9). Pointnet++: Deep hierarchical feature learning on point sets in a metric space. Proceedings of the 31st International Conference on Neural Information Processing Systems (NIPS’17), Long Beach, CA, USA.
41. The farthest point strategy for progressive image sampling10.1109/83.623193 ↗
42. Lang, I., Manor, A., and Avidan, S. (2020, January 13–19). Samplenet: Differentiable point cloud sampling. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.10.1109/CVPR42600.2020.00760 ↗
43. Efficient dimension reduction for high-dimensional matrix-valued data10.1016/j.neucom.2015.12.096 ↗
44. A simple embedding method for solving partial differential equations on surfaces10.1016/j.jcp.2007.10.009 ↗
45. 3D Scanning Data Coordination and As-Built-BIM Construction Process Optimization-Utilization of Point Cloud Data for Structural Analysis