Belirgin dalga yüksekliklerinin Neuro-Fuzzy yaklaşımı ile tahmini: filyos Deniz yöresi örneği

Belirgin dalga yüksekliğinin (Hs) tahmini, yüksek maliyetli Deniz Mühendisliği yapılarının tasarımında ilk ve enönemli aşamayı oluşturmaktadır. Bu çalışmada, literatürde var olan deterministik ve stokastik yöntemlerealternatif oluşturacak bir yaklaşım önerilmiştir. Neuro-Fuzzy yöntemi, Yapay Sinir Ağları (ANN, ArtificialNeural Networks) ve Bulanık Mantık (FL, Fuzzy Logic) yöntemlerinin avantajlı yönlerinin kombine olarakkullanıldığı bir yöntemdir. Geliştirilen tahmin modelinde, günlük ortalama Hs ve belirgin dalga periyodu (Ts)verileri kullanılarak günlük Hs tahmini yapabilen Neuro-Fuzzy modeller önerilmiştir. Önerilen modeller, farklızaman aralıklarında kaydedilmiş Hs ve Ts verilerini kullanmaktadır. Çalışmada, Filyos deniz yöresinde ölçülmüşolan Hs ve Ts değerleri, Uyarlamalı Ağ Temelli Bulanık Çıkarım Sistemi (ANFIS, Adaptive Network-basedFuzzy Inference System) ile tahmin edilmiştir. Elde edilen tahmin sonuçları gerçek dalga verileri ilekarşılaştırılmış ve yüksek korelasyon değerlerinin elde edildiği; modellerin eksik dalga verilerinin tahminedilmesinde verimli olarak kullanılabileceği sonucuna ulaşılmıştır.

Neuro-Fuzzy approximation for prediction of significant wave heights: the case of Filyos region

First and the most important phase of designing high cost coastal structures is to forecast the significant waveheight (Hs). In this study, an alternative approach to the deterministic and stochastic methods found in literatureis proposed. Neuro-fuzzy is a method in which advantages of Artificial Neural Networks (ANN) and FuzzyLogic (FL) are combined. In the Neuro-Fuzzy models developed in this study, daily significant wave height canbe estimated using daily average Hs and significant wave period (Ts) data. Hs and Ts data recorded at differenttime intervals were used in the proposed models. In this study, Hs and Ts measured in Filyos region of the BlackSea was estimated by the Adaptive Network-based Fuzzy Inference System (ANFIS). Predicted results fromproposed models were compared with the measured wave data and it is found that high correlation values areobtained. It is thus concluded that the proposed models can efficiently be used to estimate missing wave data.

PDF

___

1. More, A., Deo, M.C., “Forecasting Wind with Neural Networks”, Marines Structures, Cilt 16, No 1, 35-49, 2003.
2. Mahjoobi, M., Mosabbeb, E.A., “Prediction of Significant Wave Height using Regressive Support Vector Machines”, Ocean Engineering, Cilt 36, No 5, 339-347, 2009.
3. Özger, M., Şen, Z., “Prediction of Wave Parameters by using Fuzzy Logic Approach”, Ocean Engineering, Cilt 34, No 3-4, 460-469, 2007.
4. Günaydın, K., “The Estimation of Monthly Mean Significant Wave Heights by using Artificial Neural Network and Regression Methods”, Ocean Engineering, Cilt 35, No 14-15, 1406- 1415, 2008.
5. Hasselmann, K., Barnett, T.P., Bouws, E., Carlson, H., Cartwright, D.E., Enke, K., Weing, J.A., Gienapp, H., Hasselmann, D.E., Krusemann, P., Meerburg, A., Muller, P., Olbers, K.J., Richter, K., Sell, W., Walden, W.H., “Measurements of Wind-Wave Growth and Swell Decay During The Joint North Sea Wave Project (JONSWAP)”, Deutsche Hydrograph, Zeit, Erganzung-self Reihe, Cilt 12, No A 8, 1973.
6. Kazeminezhad, M.H., Etemad-Shahidi, A., Mousavi, S.J., “Application of Fuzzy Inference System in The Prediction of Wave Parameters”, Ocean Engineering, Cilt 32, No 14-15, 1709- 1725, 2005.
7. Mahjoobi, J., Etemad-Shahidi, A.,Kazeminezhad, M.H., “Hindcasting of Wave Parameters using Different Soft Computing Methods”, Applied Ocean Engineering, Cilt 30, No 1, 28-36, 2008.
8. Browne, M., Castelle, B., Strauss, D., Tomlinson, R., Blumenstein, M., Lane, C., “Near-shore Swell Estimation from A Global Wind-wave Model: Spectral Process, Linear, and Artificial Neural Network Models”, Coastal Engineering, Cilt 54, No 5, 445-460, 2007.
9. Agrawal, J.D., Deo, M.C., “On-line Wave Prediction”, Marine Structures, Cilt 15, No 1, 57-74, 2002.
10. Deo, M.C., Jha, A., Chaphekar, A.S., Ravikant, K., “Neural Networks for Wave Forecasting”, Ocean Engineering, Cilt 28, No 7, 889-898, 2001.
11. Makarynskyy, O., Pires-Silva, A.A., Makarynska, D., Ventura-Soares, C., “Artificial Neural Networks in Wave Predictions at the West Coast of Portugal”, Computer and Geosciences, Cilt 31, No 4, 415-424, 2005.
12. Tsai, C.P., Lin, C., Shen, J.N., “Neural Network for Wave Forecasting among Multi-stations”, Ocean Engineering, Cilt 29, No 13, 1683-1695, 2001.
13. Deo, M.C., Naidu, C.S., “Real Time Wave Forecasting using Neural Networks”, Ocean Engineering, Cilt 26, No 3, 191-203, 1999.
14. Zamani, A., Solomatine, D., Azimian, A., Heemink, A., “Learning from Data for Wind- wave Forecasting”, Ocean Engineering, Cilt 35, No 10, 953-962, 2008.
15. Altunkaynak, Z., Özger, M., “Temporal Significant Wave Height Estimation from Wind Speed by Perceptron Kalman Filtering”, Ocean Engineering, Cilt 31, No 10, 1245-1255, 2004.
16. Balas, C.E., Koç, L., Balas, L., “Predictions of Missing Wave Data by Recurrent Neuronets”, Journal of Waterway, Port, Coastal and Ocean Engineering, Cilt 130, No 5, 256-265, 2004.
17. Nayak, P.C., Sudheer, K.P., “Fuzzy Model Identification Based on Cluster Estimation for Reservoir Inflow Forecasting”, Hydrological Processes, Cilt 22, No X, 827-841, 2008.
18. Google maps, Filyos deniz yöresi, http://maps.google.com/, 2009.
19. Özçalık, H.R., Uygur, A.F., “Dinamik Sistemlerin Uyumlu Sinirsel-Bulanık Ağ Yapısına Dayalı Etkin Modellenmesi”, KSÜ Fen ve Mühendislik Dergisi, Cilt 6, No 1, 36-46, 2003.
20. Tsoukalas, L.H., Uhrig, R.E., Fuzzy and Neural Approaches in Engineering, John Wiley & Sons, New York, A.B.D., 1996.
21. 21. Mandal, S., Prabaharan, N., “Ocean Wave Forecasting using Recurrent Neural Networks”, Ocean Engineering, Cilt 33, No 10, 1401-1410, 2006.