DOI QR코드

DOI QR Code

Proposal of a Prediction Framework Based on Deep Learning Algorithm to Predict Safety Accidents at Small-scale Construction Sites

소규모 건설현장의 안전사고 예측을 위한 딥러닝 알고리즘 기반의 예측프레임워크 제안

  • Kim, Ji-Myong (Department of Architectural Engineering, Mokpo National University)
  • Received : 2023.09.27
  • Accepted : 2023.11.09
  • Published : 2023.12.20

Abstract

This study aims to develop a framework for an accident prediction model leveraging a deep neural network algorithm, specifically tailored for small-scale construction sites. Notably, the incidence of accidents in the construction sector is markedly higher compared to other industries, with a significant contribution from small-scale sites. The challenging nature of construction in urban settings, coupled with the increasing frequency of adverse weather conditions, is likely to escalate accident risks at these sites. Anticipating and mitigating accidents at small-scale construction sites is therefore crucial to decrease the overall industry accident rate. Consequently, this research introduces a Deep Neural Network-based model for forecasting accidents at small-scale construction sites. The framework and findings of this study are poised to serve as a guideline for the safety management of small-scale construction projects, ultimately aiding in the realization of safer, more sustainable construction practices at these sites.

건설산업의 재해율은 다른 산업에 비해 매우 높다. 그 이유로 다른 규모에 비해 상대적으로 더 사고에 취약한 소규모 건설현장의 높은 재해발생율을 꼽고 있다. 최근 난이도 높은 도심 건설공사의 증가, 악천후의 증가 등으로 앞으로 소규모 건설현장의 사고 발생 위험은 더 커질 것으로 예상된다. 따라서 소규모 건설현장의 사고를 사전에 예측하고 이를 통한 사고 예방 및 저감은 건설산업의 재해율을 낮추기 위해 반드시 필요하다. 따라서, 본 연구에서는 소규모 건설현장 사고를 예측하기 위한 Deep Neural Network Algorithm 기반의 사고 예측 모델 개발 프레임워크를 제안하였다. 본 연구의 프레임워크와 결과를 활용하여 소규모 건설현장 안전관리의 가이드 라인으로 활용이 가능하며, 궁극적으로 소규모 건설현장에서의 사고 위험을 줄임으로써 지속가능한 건설사업관리에 기여할 수 있을 것이다.

Keywords

Acknowledgement

This research was funded by Basic Science Research Program through the National Research Foundation of Korea(NRF) funded by the Ministry of Education(2022R1F1A106314112).

References

  1. Gledson BJ, Greenwood D. The adoption of 4d bim in the UK construction industry: an innovation diffusion approach. Engineering, Construction and Architectural Management. 2017 Nov;24(6):950-67. https://doi.org/10.1108/ECAM-03-2016-0066
  2. Kim JM, Kim T, Son K, Bae J, Son S. A quantitative risk assessment development using risk indicators for predicting economic damages in construction sites of South Korea. Journal of Asian Architecture and Building Engineering. 2019 Oct;18(5):472-8. https://doi.org/10.1080/13467581.2019.1681274
  3. Kim JM, Kim T, Ahn S. Loss assessment for sustainable industrial infrastructure: Focusing on bridge construction and financial losses. Sustainability. 2020 Jul;12(13):5316. https://doi.org/10.3390/su12135316
  4. Kim JM, Kim T, Bae J, Son K, Ahn S. Analysis of plant construction accidents and loss estimation using insurance loss records. Journal of Asian Architecture and Building Engineering. 2019 Nov;18(6):507-16. https://doi.org/10.1080/13467581.2019.1687089
  5. Kim JM, Ha KC, Ahn S, Son S, Son K. Quantifying the third-party loss in building construction sites utilizing claims payouts: A case study in South Korea. Sustainability. 2020 Dec;12(23):1015. https://doi.org/10.3390/su122310153
  6. Yum SG, Ahn S, Bae J, Kim JM. Assessing the risk of natural disaster-induced losses to tunnel-construction projects using empirical financial-loss data from South Korea. Sustainability. 2020 Sep;12(19):8026. https://doi.org/10.3390/su12198026
  7. Jang YR, Go SS. A study on the priority safety management items in the medium and small sized construction sites. Korean Journal of Construction Engineering and Management. 2020 Jul;21(4):38-49. https://doi.org/10.6106/KJCEM.2020.21.4.038
  8. Bae KS, Yoon JD, Ahn HS, Shim KB. Industrial accident status analysis and policy direction: Focusing on small and medium-sized construction sites. Sejong (Korea): Korea Labor Institute; 2013. 268 p.
  9. Won JH, Yoon YH, Oh TG, Park HG, Jeong SH. Measures for assigning responsibility to the client to prevent accidents at small-scale construction sites in the construction industry. Ulsan (Korea): Korea Occupational Safety and Health Agency; 2019. 184 p.
  10. Jeong M. Kingpin for the prevention of safety accidents at construction sites and the act on punishment of serious accidents. Construction Engineering and Management. 2020 Jan;12(8):3435-45.
  11. Ahn S, Kim T, Kim JM. Sustainable risk assessment through the analysis of financial losses from third-party damage in bridge construction. Sustainability. 2020 Apr;12(8):3435. https://doi.org/10.3390/su12083435
  12. Laryea S. Risk pricing practices in finance, insurance and construction. Proceedings of the Construction and Building Research Conference of the Royal Institution of Chartered Surveyors; 2008 Sep 4-5; Londom, United Kingdom. Reading (United Kingdom): Reading; of University; 2008. 16 p.
  13. Baker S, Ponniah D, Smith S. Techniques for the analysis of risks in major projects. Journal of the operational research society. 1998 Jun;49(6):567-72. https://doi.org/10.2307/3010665
  14. Dikmen I, Birgonul MT, Arikan AE. A critical review of risk management support tools. Proceedings of the 20th Annual Conference of Association of Researchers in Construction Management. 2004 Sep;2:1145-54.
  15. Wood G, Ellis RCT. Risk management practices of leading UK cost consultants. Engineering, Construction and Architectural Management. 2003 Aug;10(4):254-62. https://doi.org/10.1108/09699980310489960
  16. Molenaar KR. Programmatic cost risk analysis for highway megaprojects. Journal of construction engineering and management. 2005 Mar;131(3):343-53. https://doi.org/10.1061/(ASCE)0733-9364(2005)131:3(343)
  17. Cagno E, Caron F. Mancini M. A multi-dimensional analysis of major risks in complex projects. Risk Management. 2007 Feb;9(1):1-18. https://doi.org/10.1057/palgrave.rm.8250014
  18. Zou PX, Zhang G, Wang J. Understanding the key risks in construction projects in China. International Journal of Projects Management. 2007 Aug;25(6):601-14. https://doi.org/10.1016/j.ijproman.2007.03.001
  19. Baloi D, Price AD. Modelling global risk factors affecting construction cost performance. International Journal of Projects Management. 2003 May;21(4):261-9. https://doi.org/10.1016/S0263-7863(02)00017-0
  20. Allison WR, Hon KHC, Xia B. Construction accidents in australia : Evaluating the true costs. Safety Science. 2019 Dec;120:886-96. https://doi.org/10.1016/j.ssci.2019.07.037
  21. Weili F, Lieyun D, Hanbin L, Peter EL. Falls from heights: A computer vision-based approach for safety harness detection. Automation in Construction. 2018 Jul;91:53-61. https://doi.org/10.1016/j.autcon.2018.02.018
  22. Kim JM, Son K, Yum SG, Ahn S. Analyzing the risk of safety accidents: The relative risks of migrant workers in construction industry. Sustainability. 2020 Jul;12(13):5430. https://doi.org/10.3390/su12135430
  23. Ahmed S. Causes and effects of accident at construction site: A study for the construction industry in Bangladesh. International journal of sustainable construction engineering and technology. 2019 Dec;10(2):18-40.
  24. Nevada Department of Transport. Risk Management and Risk-Based Cost Estimation Guidelines. NV: Nevada Department of Transport; 2012. 10 p.
  25. Zhong G, Wang LN, Ling X, Dong J. An overview on data representation learning: From traditional feature learning to recent deep learning. The Journal of Finance and Data Science. 2016 Dec;2(4):265-78. https://doi.org/10.1016/j.jfds.2017.05.001
  26. Gu J, Wang Z, Kuen J. Recent advances in convolutional neural networks. Pattern recognition. 2018 May;77:354-77. https://doi.org/10.1016/j.patcog.2017.10.013
  27. Na H, Park BH. Developing accident models of rotary by accident occurrence location. International Journal of Highway Engineering. 2012 Aug;14(4):83-91. https://doi.org/10.7855/IJHE.2012.14.4.083
  28. Bae SW, Yoo JS. Apartment price estimation using machine learning: Gangnam-gu, Seoul as an example. Real Estate Stud. 2018 Jun;24(1):69-85. https://doi.org/10.19172/KREAA.24.1.5
  29. Kim J, Yum S, Son S, Son K, Bae J. Modeling deep neural networks to learn maintenance and repair costs of educational facilities. Buildings. 2021 Apr;11(4):165. https://doi.org/10.3390/buildings11040165
  30. Kim JM, Bae J, Son S, Son K, Yum SG. Development of model to predict natural disaster-induced financial losses for construction projects using deep learning techniques. Sustainability. 2021 May;13(9):5304. https://doi.org/10.3390/su13095304
  31. Ryu JD, Park SM, Park SH, Kwon CW, Yoon IS. A study on the development of a model for predicting the number of highway traffic accidents using deep learning. Journal of Korean Society. 2018 Jan;17(1):14-25. https://doi.org/10.12815/kits.2018.17.4.14
  32. Dikshit A, Pradhan B. Interpretable and explainable AI (XAI) model for spatial drought prediction. Science of the Total Environment. 2021 Dec;801:149797. https://doi.org/10.1016/j.scitotenv.2021.149797