DOI QR코드

DOI QR Code

Computer Vision-based Automated Adhesive Quality Inspection Model of Exterior Insulation and Finishing System

컴퓨터 비전 기반 외단열 공사의 접착제 도포품질 감리 자동화 모델

  • Yoon, Sebeen (Department of Architecture, Seoul National University of Science and Technology) ;
  • Kang, Mingyun (Architectural Engineering Program, School of Architecture, Seoul National University of Science and Technology) ;
  • Jang, Hyounseung (Architectural Engineering Program, School of Architecture, Seoul National University of Science and Technology) ;
  • Kim, Taehoon (Architectural Engineering Program, School of Architecture, Seoul National University of Science and Technology)
  • Received : 2022.11.18
  • Accepted : 2022.12.16
  • Published : 2023.04.20

Abstract

This research proposed a model for automatically monitoring the quality of insulation adhesive application in external insulation construction. Upon case implementation, the area segmentation model demonstrated a 92.3% accuracy, while the area and distance calculation accuracies of the proposed model were 98.8% and 96.7%, respectively. These findings suggest that the model can effectively prevent the most common insulation defect, insulation failure, while simultaneously minimizing the need for on-site supervisory personnel during external insulation construction. This, in turn, contributes to the enhancement of the external insulation system. Moving forward, we plan to gather construction images of various external insulation methods to refine the image segmentation model's performance and develop a model capable of automatically monitoring scenarios with a considerable number of insulation materials in the image.

본 연구에서는 외단열 공사의 단열재 접착제 도포 품질을 자동으로 감리할 수 있는 모델을 제안하였다. 사례 적용 결과, 영역 분할 모델은 mAP 92.3%의 정확도를 나타냈고, 제안 모델의 접착제 면적 비율 산출 정확도는 98.8%, 접착제 덩어리 중심 간 거리 산출 정확도는 96.7%로 나타났다. 본 연구 결과는 외단열 공사의 감리를 위한 현장투입 인력을 최소화하면서 외단열 공사의 가장 빈번한 하자인 단열재 탈락 하자를 예방할 수 있으며 나아가 외단열 시스템의 활성화에 기여할 수 있을 것으로 판단된다. 향후에는 다양한 환경에서 외단열 공법의 시공 영상을 수집하여 영상 분할 모델의 성능을 높이고, 영상 내에 다수의 단열재가 포함된 경우에도 자동 감리할 수 있는 모델을 개발하고자 한다.

Keywords

Acknowledgement

This work is supported by the Korea Agency for Infrastructure Technology Advancemen(KAIA) grant funded by the Ministry of Land, Infrastructure and Transport(Grant 1615012983). This work was supported by the National Research Foundation of Korea(NRF) grant funded by the Korea government (MSIT)(No. 1711172933).

References

  1. Kim YS. Zero energy building certification status and future tasks. Seoul(Korea): National Assembly Research Service; 2022 Jun. 14 p. Report No.: 31-9735026-000626-14.
  2. Lim HS, Kim TH, Cho HH, Kang KI. The Conceptual framework of concurrent construction method for EIFS In apartment. Journal of the Korea Institute of Building Construction. 2015 Aug;15(4):413-23. https://doi.org/10.5345/JKIBC.2015.15.4.413
  3. Journal of Architectural Institute of Korea. A study on the standard and management plan for exterior insulation and finishing system. Sejong (Korea): Ministry of Land, Infrastructure and Transport; 2015 Oct. 69p. Report No.: TRKO201600016309
  4. Lee BH, Kim KH, Kim JJ. A study of the improvement plan for the quality control in the construction through by analyzing the claim of the defect repair. Proceeding of Korea Institute of Construction Engineering and Management; 2009 Nov 19-20; Daejon, Korea. Seoul (Korea): Korean Institute of Construction Engineering and Management; 2009. p.342-6.
  5. Lee BS. A study on method for pre-assuring of quality of external insulation installation task by introducing image processing [master's thesis]. [Seoul (Korea)]: Hanyang University; 2012. 63 p.
  6. Martinez P, Al-Hussein M, Ahmad R. Intelligent vision-based online inspection system of screw-fastening operations in light-gauge steel frame manufacturing. The International Journal of Advanced Manufacturing Technology. 2020 Jul;109(3):645-57. https://doi.org/10.1007/s00170-020-05695-y
  7. Cha YJ, You KS, Choi WR. Vision-based detection of loosened bolts using the hough transform and support vector machines. Automation in Construction. 2016 Nov;71(2):181-8. https://doi.org/10.1016/j.autcon.2016.06.008
  8. Lin KL, Fang JL. Applications of computer vision on tile alignment inspection. Automation in Construction. 2013 Nov;35:562-7. https://doi.org/10.1016/j.autcon.2013.01.009
  9. KCS 41 41 02 Exterior Insulation Finishing System. Sejong (Korea): Ministry of Land, Infrastructure and Transport; 2021. Korean.
  10. 46030 Exterior Insulation Finishing System. Jinju (Korea): Korea Land and Housing Corporation; 2012. Korean.
  11. Glenn J, Liu C, Adam H, Lijun Y, Changyu, Prashant R, Trevor S. ultralytics/yolov5: Initial Release [Internet]. Zenodo; 2020 Jun 25 [cited 2023 Mar 30]. Available from: https://zenodo.org/record/3908560#.ZCovgHZByUk