Please use this identifier to cite or link to this item:
標題: 以類神經網路預測直立堤波浪越波量之研究
Determination of Wave Overtopping Rates at Vertical Breakwater Using Neural Network
作者: 何俊燐
Ho, Chuen-Lin
關鍵字: neural network;類神經網路;overtopping;vertical breakwater;越波量;直立堤
出版社: 土木工程學系所
引用: 1.Ahrens J., “Rpediction of Irregular Wave Overtopping,” CETA 77-2 , U.S. Army Engineer Waterways Experiment Station, Coastal Engineering Research Center, Vicksburg, M.S(1977). 2.Daemrich, K.-F., J. Meyering, N. Ohle, C. Zimmermann, “Irregular wave overtopping at vertical walls – Learning from regular wave tests,” Proc. 30th ICCE, San Diego. ASCE (2006). 3.Daemrich, K.-F., Tack, G., Zimmermann, C., Cheng, H.-Y, “ Irregular wave overtopping based on regular wave tests,” Proc. 3rd Chinese-German Joint Symposium on Coastal and Ocean Engineering, National Cheng Kung University, Tainan (2006). 4.Endo, S. and Miura, A., “Experimental study on sea wave movement facing a vertical wall,” Rept. Res. Inst. Of Industrial Tech., Nihon Univ.,Japan, 20pp (1983). 5.Franco, L., de Gerloni, M., and van der Meer, J.W., “Wave Overtopping on Vertical and Composite Breakwaters,” Proceedings of the 24th International Coastal Engineering Conference, American Society of Civil Engineers, Vol. 1, pp 1030-1045 (1994). 6.Goda, Y. and S. Tsuruta, “Expected discharge of irregular wave overtopping,” Proc. 11th Coastal Eng. Conf., ASCE, pp.833-852 (1968). 7.Goda, Y., “A synthese of breaker indices,” Trans. Japan Soc. Civil Engrs.” Vol. 2, Part 2, pp.227-230 (1970). 8.Goda, Y., ”Estimation of the rate of irregural wave overtopping of seawalls,” Rept. Port and Harbour Res. Inst., Vol. 9, No. 4, pp. 3-41 (1970). 9.Goda, Y., Random seas and design of marine structures, University of Tokyo Press, pp323 (1985). 10.Goda, Y., Random seas and design of marine structures, World Scientific, Advanced Series on Ocean Engineering, Vol. 15. (2000). 11.Iwagaki, Y., Shima, A. and Inoue, M., “Effects of Wave Height and Sea Water Level on Wave Overtopping and Wave Run-up,” Coastal Eng. In Japan, Vol.8, pp.141-154 (1965). 12.Kikkawa, H. Shi-Igai, H. Kono, T., “Fundamental study of water over-topping on levees”, Coastal Eng. In Japan, Vol. 11, pp. 107-115 (1968). 13.Lee, T.L. “Back-propagation neural network for long-term tidal predictions,” Ocean Engineering, Vol. 31, pp. 225-238 (2004). 14.Owen M.W., “Design of Seawalls Allowing for Wave Overtopping,” Report No. Ex 924, Hydraulics Research Station, Wallingford, U.K(1980). 15.Saville, T. and Caldwell, J.M., “Experimental Study of Wave Overtopping on Shore Structures,” Proc. IAHR., pp.261-269 (1953). 16.Sibul, O.J., “Flow over Structure by Wave Action,” Trans.A.G.U., 36(1), pp. 61-69 (1955). 17.Serre, S., “Tidal-level forecasting and filtering by neural network model,” Costal Engineering Journal, Vol. 45, pp.119-137 (2003). 18.Takada, A., "On relations among wave run-up, overtopping and reflection", Proc. Japan Soc. Civil Eng., No. 182, pp.19-30 (1970). 19.Tsai, C.P., Lee, T.L. and Chu, L.H., “Forecasting of wave time series using back propagation neural network,” Journal of the Chinese Institute of Civil and Hydraulic Engineering, Vol.11, pp.589-596 (1999). 20.Tsai, C. P., Lin, C. and Shen, J. N. “Neural network for wave forecasting among multi-stations,” Ocean Engineering, Vol. 29, pp.1683-1695 (2002). 21.Tsai, C.P., Lee, T.L., Yang, T.J., Hsu, Y.J. “Back-propagation neural networks for Prediction of Storm Surge,” Structural and Environmental Engineering, Civil-comp Press. Vol.11. 589–596 (2005). 22.Umeyama, m., “Wave overtopping on vertical boundary and water-surface displacement,” J. Waterway Port Coastal Ocean, ASCE, Vol. 119, No. 3, pp. 243-260 (1993). 23.Van Gent, M.R.A., van den Boogaard, H.F.P., Pozueta, B., Medina, J.R., “Neural network modeling of wave overtopping at coastal structures,” Coastal Engineering, 54, pp. 586-593 (2007). 24.Villiers, J. and Barnard, E., “Back-propagation neural nets with one and two hidden layers,” IEEE Transaction On Neural Network, Vol.4, pp.136-141 (1992). 25.Verhaeghe, H., De Rouck, J., van der Meer, J., “Combined classifier-quantifier model : A 2-phases neural model for prediction of wave overtopping at coastal structures,” Coastal Engineering, 55, pp. 357-374 (2008). 26.Weggel, J.R.,, “Wave Overtopping eguation,” Proc. 15th Conf. Coastal Eng., ASCE, pp. 2737-2755 (1976). 27.葉怡成,「類神經網路模式應用與實作」,儒林圖書有限公司(1998)。 28.李宗霖、S. Rajasekaran、徐月娟、楊宗儒(2003),「序列學習神經網路在颱風期間之潮位預測」,第25屆海洋工程研討會論文集, 第275-279頁。

本文首先由規則波試驗之結果,經由類神經網路之訓練及測試,探討最佳之類神經網路參數和架構,包括最佳之輸入參數、隱藏層層數、隱藏層神經元數目、學習速率、慣性因子和循環次數等,得出以輸入相對出水高、胸牆寬度和波浪尖銳度可得最小之訓練及測試誤差,因此建立本文類神經網路預測模式,以輸入上述3個參數即可得最佳之預測結果。而後於模式驗證中,得出該模式對於直立堤有無胸牆之情形皆有良好之預測結果,可知類神經網路具有相當良好之應用。基此,對於不規則波之越波量預測可由JONSWAP波譜以零下切法分割出1000個成份波,而後以類神經網路對這些個別成份波預測其越波量,再由Goda (2000)不規則波越波量計算式,即由個別成份波越波量總和除以總時間,求得不規則波平均越波量。由所得之預測結果可知,相對出水高越大則越波量越小,增加胸牆寬度可降低越波量,而在固定波高情況下,對於較大之波浪尖銳度有較小之越波量。由具有胸牆直立堤之越波量與無胸牆直立堤之越波量的比值關係,本文提出可供實際設計參考之曲線圖。

The determination of wave overtopping is an important item for the design of a breakwater or a coastal structure. There was no empirical formula available for overtopping rates of irregular waves including influences simultaneous of the freeboard, wave steepness, and the width of the parapets. This paper presents application of artificial neural network (ANN) to the determination of the overtopping rate at a vertical wall with a parapet, including these parameters.

The ANN first learned from physical model tests of regular waves, from which the ANN obtained a very good agreement between the predicted and measured values of the normalized overtopping rates. For an irregular wave train with JONSWAP spectrum, a time series of 1000 waves was created using zero-downcrossing method. The ANN then calculated the overtopping volumes of individual waves. Exemplary design curves of mean overtopping rate over the duration of the time series are obtained for practical application.
其他識別: U0005-2208200815251800
Appears in Collections:土木工程學系所

Show full item record
TAIR Related Article

Google ScholarTM


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.