한국건축시공학회지 (Journal of the Korea Institute of Building Construction)

  • 제24권3호
  • /
  • Pages.355-362
  • /
  • 2024
  • /
  • 1598-2033(pISSN)
  • /
  • 2233-5706(eISSN)
한국건축시공학회 (The Korean Institute of Building Construction)
권호 표지
DOI QR코드

DOI QR Code

아파트 수선유지 비용 예측을 위한 딥러닝 프레임워크 제안

A Deep Learning Framework for Prediction of Apartment Repair and Maintenance Costs

  • 김지명 ;
  • 손승현
  • Kim, Ji-Myong (Department of Architectural Engineering, Mokpo National University) ;
  • Son, Seunghyun (Department of Architectural Engineering, Mokpo National University)
  • 투고 : 2024.04.17
  • 심사 : 2024.05.12
  • 발행 : 2024.06.20
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

본 연구의 주요 목표는 아파트 단지 수선유지 비용을 예측하기 위해 딥러닝 기법을 적용한 예측 모델 구축 프레임워크를 제안하는 것이다. 아파트 건물을 이상적인 상태로 관리하기 위해서는 지속적인 유지 및 시의적절한 수리가 필수적이다. 아파트 단지는 광범위한 면적, 공동 시설, 다수의 주거 동, 서비스 지역 등으로 인해 유지관리가 복잡하다. 또한, 아파트의 안전성 보장, 가치 유지 및 경제적 효율성 때문에 경제적이고 합리적인 유지보수의 중요성이 점점 커지고 있다. 그러나 아파트 단지 수선유지는 다양한 외부 요인의 영향을 받고 데이터 수집이 어려워 연구가 부족한 상황이다. 따라서 본 연구는 실제 아파트 단지 유지보수 비용 데이터를 기반으로 딥러닝 기법을 활용해 유지보수 비용을 예측하는 모델 개발 프레임워크를 제시하고자 한다. 본 연구의 프레임워크 및 결과는 실질적으로 아파트 단지의 유지보수 비용 예측에 활용될 수 있으며, 궁극적으로 아파트 단지의 시설 관리 향상에 기여할 것이다.

The sustained upkeep of apartment buildings necessitates ongoing maintenance and timely repairs, particularly given their complex nature due to extensive areas, common facilities, and multiple residential and service structures. Additionally, the need for cost-effective maintenance is paramount for ensuring safety, preserving value, and maintaining economic efficiency. However, the multitude of external variables influencing apartment complex maintenance, coupled with the challenges in data collection, have resulted in limited research in this domain. To address this gap, the current study aims to develop a framework for predicting maintenance costs utilizing deep learning techniques, grounded in real-world apartment complex maintenance cost data. This study intends to provide a practical and valuable contribution to the field of apartment complex management, empowering stakeholders with enhanced predictive capabilities for optimizing maintenance strategies and resource allocation.

키워드

과제정보

This research was supported by a grant(NRF-2022R1F1A106314113 and NRF-2021R1C1C2091677) from the National Research Foundation of Korea by Ministry of Science and ICT.

참고문헌

  1. Islam R, Nazifa TH, Mohammed SF, Zishan MA, Yusof ZM, Mong SG. Impacts of design deficiencies on maintenance cost of high-rise residential buildings and mitigation measures. Journal of Building Engineering. 2021 Jul;39:102215. https://doi.org/10.1016/j.jobe.2021.102215 
  2. Kim S, Lee S, Ahn YH. Evaluating housing maintenance costs with loss-distribution approach in South Korean apartment housing. Journal of Management in Engineering. 2018 Dec;35(2):04018062. https://doi.org/10.1061/(ASCE)ME.1943-5479.0000672 
  3. Lee KH, Ahn YH, Chae CU. Establishment of the repair cycle of the components of the apartment housing. KIEAE Journal. 2014 Apr;14(2):69-75. https://doi.org/10.12813/kieae.2014.14.2.069 
  4. Choi SM, Lee YS. Economic analysis for setting appropriate repair cycles on the fixed materials and facilities in the public rental housing. Advances in Materials Science and Engineering. 2016 Nov;2016(1):7423801. https://doi.org/10.1155/2016/7423801 
  5. Jeong Y, Lee Y, Jung Y. Requirements management framework for design management and information characteristics. Korean Journal of Construction Engineering and Management. 2020 Nov;21(6):3-15. https://doi.org/10.6106/KJCEM.2020.21.6.003 
  6. Lee IH, Jung YS. Evaluation of construction information transfer requirements for efficient asset management. Journal of the Korean Society of Construction Management. 2018 Jul;19(4):12-20. https://doi.org/10.6106/KJCEM.2018.19.4.012 
  7. Atkin B, Brooks A. Total facility management. 5th Edition. UK: Wiley Blackwell; 2021. 464 p. 
  8. Ghodoosi F, Abu-Samra S, Zeynalian M, Zayed T. Maintenance cost optimization for bridge structures using system reliability analysis and genetic algorithms. Journal of Construction Engineering and Management. 2018 Dec;144(2):04017116. https://doi.org/10.1061/(ASCE)CO.1943-7862.0001435 
  9. Krstic H, Marenjak S. Maintenance and operation costs model for university buildings. Tehnicki vjesnik. 2017 May; 24(Supplement 1):193-200. https://doi.org/10.17559/TV-20140606093626 
  10. Bayzid SM, Mohamed Y, Al-Hussein M. Prediction of maintenance cost for road construction equipment: a case study. Canadian Journal of Civil Engineering. 2016 Mar;43(5):480-92. https://doi.org/10.1139/cjce-2014-0500 
  11. Meshref A, El-Dash K, Basiouny M, El-Hadidi O. Implementation of a life cycle cost deep learning prediction model based on building structure alternatives for industrial buildings. Buildings. 2022 Apr;12(5):502. https://doi.org/10.3390/buildings12050502 
  12. Au-Yong CP, Ali AS, Ahmad F. Prediction cost maintenance model of office building based on condition-based maintenance. Eksploatacja i Niezawodnosc-Maintenance and Reliability. 2014 Dec;16(2):319-24. 
  13. Yang C, Trudel E, Liu Y. Machine learning-based methods for analyzing grade crossing safety. Cluster Comput. 2017 Jan; 20:1625-35. https://doi.org/10.1007/s10586-016-0714-2 
  14. Xia Y, Wang J, Wei D, Zhang Z. Combined framework based on data preprocessing and multi-objective optimizer for electricity load forecasting. Engineering Applications of Artificial Intelligence. 2023 Mar;119:105776. https://doi.org/10.1016/j.engappai.2022.105776 
  15. Huk M. Stochastic optimization of contextual neural networks with RMSprop. In Intelligent Information and Database Systems. Proceedings of the 12th Asian Conference, ACIIDS; 2020 Mar 23-26; Phuket, Thailand, Berlin (Germany): Springer International Publishing. 2020. p. 343-52. 
  16. Lim KK. Analysis of railroad accident prediction using zero-truncated negative binomial regression and artificial neural network model: A case study of national railroad in south korea. KSCE Journal of Civil Engineering. 2023 Oct;27(1):333-44. https://doi.org/10.1007/s12205-022-1198-7 
  17. Krizhevsky A, Sutskever I, Hinton GE. ImageNet classification with deep convolutional neural networks. Communications of the ACM. 2017 May;60(6):84-90. https://doi.org/10.1145/3065386