한국안전학회지 (Journal of the Korean Society of Safety)

  • 제33권6호
  • /
  • Pages.42-49
  • /
  • 2018
  • /
  • 1738-3803(pISSN)
  • /
  • 2383-9953(eISSN)
한국안전학회 (The Korean Society of Safety)
권호 표지
DOI QR코드

DOI QR Code

머신러닝 기법과 계측 모니터링 데이터를 이용한 광안대교 신축거동 모델링

Modeling on Expansion Behavior of Gwangan Bridge using Machine Learning Techniques and Structural Monitoring Data

  • Park, Ji Hyun (Busan Infrastructure Corporation) ;
  • Shin, Sung Woo (Department of Safety Engineering, Pukyong National University) ;
  • Kim, Soo Yong (Department of Civil Engineering, Pukyong National University)
  • 투고 : 2018.09.12
  • 심사 : 2018.10.06
  • 발행 : 2018.12.31
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

In this study, we have developed a prediction model for expansion and contraction behaviors of expansion joint in Gwangan Bridge using machine learning techniques and bridge monitoring data. In the development of the prediction model, two famous machine learning techniques, multiple regression analysis (MRA) and artificial neural network (ANN), were employed. Structural monitoring data obtained from bridge monitoring system of Gwangan Bridge were used to train and validate the developed models. From the results, it was found that the expansion and contraction behaviors predicted by the developed models are matched well with actual expansion and contraction behaviors of Gwangan Bridge. Therefore, it can be concluded that both MRA and ANN models can be used to predict the expansion and contraction behaviors of Gwangan Bridge without actual measurements of those behaviors.

키워드

HOJHB0_2018_v33n6_42_f0001.png 이미지

Fig. 1. Expansion Joint Damage1).

HOJHB0_2018_v33n6_42_f0002.png 이미지

Fig. 2. Measured displacement data and sensor.

HOJHB0_2018_v33n6_42_f0003.png 이미지

Fig. 2. Artificial neural network model structure.

HOJHB0_2018_v33n6_42_f0004.png 이미지

Fig. 3. Prediction performance.

HOJHB0_2018_v33n6_42_f0005.png 이미지

Fig. 4. Comparison of actual and predicted values.

Table 1. Descriptive statistics

HOJHB0_2018_v33n6_42_t0001.png 이미지

Table 2. Design of artificial neural network model topology

HOJHB0_2018_v33n6_42_t0002.png 이미지

Table 3. Coefficients of multiple regression analysis model

HOJHB0_2018_v33n6_42_t0003.png 이미지

Table 4. Pearson's correlations

HOJHB0_2018_v33n6_42_t0004.png 이미지

Table 5. Training options

HOJHB0_2018_v33n6_42_t0005.png 이미지

Table 6. Independent variable importance

HOJHB0_2018_v33n6_42_t0006.png 이미지

Table 7. Comparison of predictive model validation

HOJHB0_2018_v33n6_42_t0007.png 이미지

참고문헌

  1. http://www.yonhapnews.co.kr/photos/1990000000.html?cid=PYH20180716225000061&from=search
  2. J. H. Park, "The optimum design of expansion joints by long-term monitoring data for the Diamond Bridge", Master Thesis, Pukyong National University, 2015.
  3. J. C. Park, "Evaluation of Thermal Movements of a Cable-Stayed Bridge Using Temperatures and Displacements Data", Journal of the Korean Society of Civil Engineers, Vol. 35, No. 4, pp.779-789, 2015. https://doi.org/10.12652/Ksce.2015.35.4.0779
  4. J. S. Chung, and J. S. Lee, "Effects of Bridge Bearings by Structure-Track Interaction for Continuous Bridge applied CWR with Rail Expansion Joint under Temperature Load", J. Korean Soc. Saf., Vol. 25, No. 5, pp. 54-61, 2010.
  5. Korean Society of Civil Engineers, Explanations for highway bridge design code, pp.92-94, 2008.
  6. Ministry of Land, Infrastructure and Transport, 'Highway bridge design code-(Limit state design)', 2016.
  7. Ministry of Land.Transport and Maritime Affairs, 'Highway design manual', 2008.
  8. J. Shu, Z. Zhang, I. Gonzalez, and R. Karoumi, "The Application of a Damage Detection Method using Artificial Neural Network and Train-induced Vibrations on a Simplified Railway Bridge Model", Engineering Structures, Vol. 52, pp.408-421, 2013. https://doi.org/10.1016/j.engstruct.2013.02.031
  9. M. Mehrjoo, N. Khaji, H. Moharrami and A. Bahreininejad, "Damage Detection of Truss Bridge Joints using Artificial Neural Networks", Expert Systems with Applications, Vol. 35, No. 3, pp.1122-1131, 2008. https://doi.org/10.1016/j.eswa.2007.08.008
  10. T. H. Chan, Y. Q. Ni, and J. M. Ko, "Neural Network Novelty Filtering for Anomaly Detection of Tsing Ma Bridge Cables", Proceedings of Structural Health Monitoring Conference, California: Stanford University, pp.430-439, 1999.
  11. J. H. Park, S. W. Shin, and S. Y. Kim, "Traffic Volume Dependent Displacement Estimation Model for Gwangan Bridge Using Monitoring Big Data ", Journal of the Korean Society of Civil Engineers. Vol. 38, No. 2, pp.183-191, 2018. https://doi.org/10.12652/KSCE.2018.38.2.0183
  12. J. H. Park, and S. Y. Kim, "Analysis of Suspension Bridge Reinforced Truss Strain by Traffic", 2017 Proceedings of KSMI Annual Conference, pp.357-358, 2017.
  13. S. R. Chen, and J. Wu, "Dynamic Performance Simulation under Combined Loads of Stochastic of Long-Span Bridge Traffic and Wind", Journal of Bridge Engineering, Vol. 15, No. 3, pp. 219-230, 2009. https://doi.org/10.1061/(ASCE)BE.1943-5592.0000078
  14. Y. C. Kim, W. S. Yoo, and Y. S. Shin, "Application of Artificial Neural Networks to Prediction of Construction Safety Accidents", Journal of the Korean Society of Hazard Mitigation . Vol. 17, No. 1, pp.7-14, 2017. https://doi.org/10.9798/KOSHAM.2017.17.1.7
  15. S. W. Shin, "Construction Safety and Health Management Cost Prediction Model using Support Vector Machine", J. Korean Soc. Saf., Vol. 32, No. 1, pp. 115-120, 2017. https://doi.org/10.14346/JKOSOS.2017.32.1.115
  16. Korea Statistics Training Institute, 'Statistical Thesis Writing Process for Graduate Students', 2016.
  17. J. S. Lee and B. G. Cha, "Structure Design of Artificial Neural Networks using Genetic Algorithm", Journal of the Korean Operations Research and Management Science, Vol. 24, No. 3, pp.49-62, 1999.
  18. J. H. Park, C. S. Kim, S. W. Shin, and S. Y. Kim, "Partial Correlation Analysis Excluding Temperature Effects in Gwangan Bridge Girder Expansion and Vertical Displacement" 2018 Proceedings of KSMI Annual Conference, pp.337-338, 2018.