KSCE Journal of Civil and Environmental Engineering Research (대한토목학회논문집)

Korean Society of Civil Engeneers (대한토목학회)
권호 표지
DOI QR코드

DOI QR Code

Monte Carlo Simulation-Based Cost Estimation for Floating Trash Barrier Maintenance

몬테카를로 시뮬레이션 기반 부유 쓰레기 차단막 유지관리 비용 추정 방안

  • 김석환 (연세대학교 건설환경공학과) ;
  • 김태건 (연세대학교 건설환경공학과) ;
  • 김홍조 (연세대학교 건설환경공학과)
  • Received : 2023.11.20
  • Accepted : 2024.01.02
  • Published : 2024.04.01
Download PDF
⟨ Previous Next ⟩

Abstract

Marine debris entering through rivers negatively impacts the environment and poses a direct threat to human health. While barriers to prevent the outflow of floating debris are being installed, attention to their maintenance, especially the scheduling of garbage collection, is insufficient. Currently, maintenance relies on a sequential collection method based on the experience and know-how of field workers, with little systematic research to support it. In response, this study proposes a new feedback-based collection method based on YOLOv7, Monte Carlo simulation for trash collection analysis. The proposed method conducts collection based on the amount of trash detected by remote sensors such as CCTV, and the expected costs are statistically and economically compared using Monte Carlo Simulation (MCS). The results showed that the new collection strategy offers a cost advantage of about 63 % over the existing strategy.

강물을 통해 유입되는 해양 부유 쓰레기는 환경에 부정적인 영향을 주며, 인간의 건강에도 직접적인 위협이 된다. 부유 쓰레기의 유출을 막기 위한 차단시설물을 설치하고 있지만 이들 시설의 유지보수, 특히 차집 쓰레기 수거 스케줄링 대한 관심은 미비하다. 현재 유지관리는 현장 작업자의 경험에 기반한 순차적 수거 방식을 사용하고 있을 뿐이며, 이를 위한 체계적인 연구는 미비하다. 이에 AI기술인 YOLOv7기반 차집량 분석 모니터링 기술을 이용한 새로운 피드백 기반 수거 비용 추정 프레임워크를 제안한다. 제안하는 수거 방식은 CCTV 등의 원격 센서로부터 측정된 차집 쓰레기 정보량을 토대로 수거를 진행하며, MCS로 예상 금액을 통계적으로 경제적 비교를 하였다. 결과적으로 신규 수거 전략을 이용한 방식은 기존 수거 전략 대비 약 63 %의 비용적 우위를 보였다.

Keywords

Acknowledgement

This research was conducted by the support of 2023 Yonsei University Future-Leading Research Initiative (No.2023-22-0114). This paper has been written by modifying and supplementing the KSCE 2023 CONVENTION paper.

References

  1. Fallati, L., Polidori, A., Salvatore, C., Saponari, L., Savini, A. and Galli, P. (2019). "Anthropogenic Marine Debris assessment with Unmanned Aerial Vehicle imagery and deep learning: A case?study along the beaches of the Republic of Maldives." Science of the Total Environment, Elsevier, Vol. 693, 133581, https://doi.org/10.1016/j.scitotenv.2019.133581.
  2. Kim, S., Kim, T., Hyeon, J., Won, J. and Kim, H. (2023). "Comparing object detection models for water trash monitoring." Proceedings of International Conference on Computing in Civil and Building Engieering, Springer, Cape Town, South Africa, pp. 161-170, https://doi.org/10.1007/978-3-031-35399-4_13.
  3. Korea Marine Environment Management Corporation (KOEM) (2020a). 2020 National Coastal Waste Monitoring Service (in Korean).
  4. Korea Marine Environment Management Corporation (KOEM) (2020b). Standard Product Calculation and Design Standards for Marine Waste Purification Business (in Korean).
  5. Kylili, K., Kyriakides, I., Artusi, A. and Hadjistassou, C. (2019). "Identifying floating plastic marine debris using a deep learning approach." Environmental Science and Pollution Research, EuChemS, Vol. 26, pp. 17091-17099, https://doi.org/10.1007/s11356-019-05148-4.
  6. Lee, J. and Kang, Y. (2021). "The criteria for suitable site selection?of floating barriers." Proceedings of the Korean Society for?Marine Environment and Energy, KOSMEE, Incheon, Korea, pp. 1640 (in Korean).
  7. Reinelt, G. (1994). The Traveling Salesman: Computational Solutions for TSP Applications, Springer, Berlin, Heidelberg.
  8. Sanchez-Ferrer, A., Valero-Mas, J. J., Gallego, A. J. and Calvo-Zaragoza, J. (2023). "An experimental study on marine debris location and recognition using object detection." Pattern Recognition Letters, Elsevier, Vol. 168, pp. 154-161, https://doi.org/10.1016/j.patrec.2022.12.019.
  9. Wang, C. Y., Bochkovskiy, A. and Liao, H. Y. M. (2023). "YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors." Proceedings of 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition, IEEE Computer Society and The Computer Vision Foundation, Vancouver, Canada, pp. 7464-7475, https://doi.org/10.1109/CVPR52729.2023.00721.