Journal of Korean Society of Coastal and Ocean Engineers (한국해안·해양공학회논문집)

Korean Society of Coastal and Ocean Engineers (한국해안·해양공학회)
권호 표지
DOI QR코드

DOI QR Code

Wave Height and Downtime Event Forecasting in Harbour with Complex Topography Using Auto-Regressive and Artificial Neural Networks Models

자기회귀 모델과 신경망 모델을 이용한 복잡한 지형 내 항만에서의 파고 및 하역중단 예측

  • Yi, Jin-Hak (Coastal Engineering Division, Korea Institute of Ocean Science and Technology) ;
  • Ryu, Kyong-Ho (Coastal Engineering Division, Korea Institute of Ocean Science and Technology) ;
  • Baek, Won-Dae (Coastal Engineering Division, Korea Institute of Ocean Science and Technology) ;
  • Jeong, Weon-Mu (Coastal Engineering Division, Korea Institute of Ocean Science and Technology)
  • 이진학 (한국해양과학기술원 연안공학연구본부) ;
  • 류경호 (한국해양과학기술원 연안공학연구본부) ;
  • 백원대 (한국해양과학기술원 연안공학연구본부) ;
  • 정원무 (한국해양과학기술원 연안공학연구본부)
  • Received : 2017.08.16
  • Accepted : 2017.08.25
  • Published : 2017.08.31
Download PDF
⟨ Previous Next ⟩

Abstract

Recently, as the strength of winds and waves increases due to the climate change, abnormal waves such as swells have been also increased, which results in the increase of downtime events of loading/unloading in a harbour. To reduce the downtime events, breakwaters were constructed in a harbour to improve the tranquility. However, it is also important and useful for efficient port operation by predicting accurately and also quickly the downtime events when the harbour operation is in a limiting condition. In this study, numerical simulations were carried out to calculate the wave conditions based on the forecasted wind data in offshore area/outside harbour and also the long-term observation was carried out to obtain the wave data in a harbour. A forecasting method was designed using an auto-regressive (AR) and artificial neural networks (ANN) models in order to establish the relationship between the wave conditions calculated by wave model (SWAN) in offshore area and observed ones in a harbour. To evaluate the applicability of the proposed method, this method was applied to predict wave heights in a harbour and to forecast the downtime events in Pohang New Harbour with highly complex topography were compared. From the verification study, it was observed that the ANN model was more accurate than the AR model.

최근에 기후변화로 인해 너울성 고파 등 이상고파의 출현빈도가 높아지고 항만에서의 하역중단이 증가할 가능성이 커지고 있다. 하역중단을 최소화할 수 있도록 방파제(breakwater) 등을 추가적으로 건설하여 정온도(tranquility)를 향상시키는 것도 매우 중요하지만, 하역중단시점을 미리 예보함으로써 항만 운영을 효율적으로 하는 것도 또한 중요하다. 본 연구에서는 효율적인 항만 운영을 위하여 하역중단시점을 사전에 예보할 수 있도록 바람 예보자료를 이용하여 항외 주요 지점에서의 파랑자료를 추산하고, 복잡한 지형을 가진 항내 주요 지점에 대해서는 장기 관측을 실시하여 파랑자료를 수집한 후, 광역 계산지점에서의 파고와 항내 관측지점에서의 파고 사이의 관계를 자기회귀모델(auto-regressive model)과 인공신경망(artificial neural networks) 모델을 이용하여 바람예보자료를 이용한 수치실험 결과만으로 항내 파고를 예측하고, 하역중단시점을 예보할 수 있는 방법을 제안하였다. 제안방법의 적용성을 평가하기 위하여 포켓(pocket) 형상의 비교적 복잡한 지형 조건을 가진 포항신항 내 파랑관측지점에서의 파고 예측 및 하역중단시점을 예측하였으며, 그 결과를 관측자료와 비교하여 제안 방법의 성능을 검증하였다. 인공신경망 모델의 파고 예측결과를 자기회귀모델에 의한 파고 예측결과와 비교할 때, 인공신경망 모델의 예측결과가 관측자료와의 상관계수가 높고 RMS 오차가 작음을 알 수 있었고, 하역중단시점의 예측에 있어서도 인공신경망의 결과가 자기회귀모델의 결과보다 상대적으로 우수함을 알 수 있었다.

Keywords

References

  1. Booij, N. (1981). Gravity waves on water with non-uniform depth and current. Report No. 81-1, Dept. of Civil Eng., Delft Univ. of Technology.
  2. Booij, N., Ris, R.C. and Holthuijsen, L.H. (1999). A third-generation wave model for coastal regions 1. Model description and validation. J. of Geophysical Research, 103(C4), 7649-7666.
  3. Eum, H.-S., Kang, T.-S., Nam, S.-Y. and Jeong, W.-M. (2016). Wave modeling considering water level changes and currents effects. Journal of Korean Society of Coastal and Ocean Engineers, 28(6), 383-396 (in Korean). https://doi.org/10.9765/KSCOE.2016.28.6.383
  4. Haykin, S., Neural networks-a comprehensive foundation, Macmillan, New York, USA, 1994.
  5. Jeong, W.M., Oh, S.B., Chae, J.W. and Kim, S.I. (1997). Analysis of the wave induced downtimes in Pohang New Harbor. Journal of Korean Society of Coastal and Ocean Engineers, 9(1), 24-34 (in Korean).
  6. Jeong, W.M., Jun, K.C., Kim, G., Oh, S.-H. and Ryu, K.-H. (2012). Shallow-water design waves at Gangreung Beach through the analysis of long-term measured wave data and numerical simulation using deepwater wave conditions. Journal of Korean Society of Coastal and Ocean Engineers, 24(5), 343-351 (in Korean). https://doi.org/10.9765/KSCOE.2012.24.5.343
  7. Jeong, W.M., Ryu, K.H., Baek, W.D. and Choi, H.J. (2011). Downtime analysis for Pohang New Harbor through long-term investigation of waves and winds. Journal of Korean Society of Coastal and Ocean Engineers, 23(3), 226-235 (in Korean). https://doi.org/10.9765/KSCOE.2011.23.3.226
  8. Kim, J.M., Hur, D.S., Kim, C.H. and Kim, D.S. (2007). Shallow water wave hindcasting by the combination of MASCON and SWAN models. Journal of Korean Society of Coastal and Ocean Engineers, 19(1), 57-65 (in Korean).
  9. Lopez, M. and Iglesias, G. (2013). Artificial intelligence for estimating infra gravity energy in a harbour. Ocean Engineering, 57, 56-63. https://doi.org/10.1016/j.oceaneng.2012.08.009
  10. Lopez, I., Lopez, M. and Iglesias, G. (2015). Artificial neural networks applied to port operability assessment. Ocean Engineering, 109, 298-308. https://doi.org/10.1016/j.oceaneng.2015.09.016
  11. Sohn, H., Dzwonczyk, M., Straser, E.G., Kiremidjian, A.S., Law, K.H. and Meng, T. (1999). An experimental study of temperature effect on modal parameters of the Alamosa Canyon Bridge. Earthquake Engineering Structural Dynamics, 28, 879-897. https://doi.org/10.1002/(SICI)1096-9845(199908)28:8<879::AID-EQE845>3.0.CO;2-V
  12. The SWAN team (2008). SWAN Cycle III version 40.72 Technical Documentation.
  13. Yi, J.-H., Ryu, K.-H., Jeong, W.-M. and Baek, W.-D. (2014). Downtime forecasting technique in harbour using artificial neural networks model, Proceedings of International Conference on Coastal Engineering, Seoul, Korea.