Genel Kargo Gemilerinin Ana Makine Gücü Tahmini İçin Yapay Sinir Ağı Yaklaşımı

Öz

Bir geminin fiziki inşasına başlanmadan önce çok aşamalı bir tasarım sürecinden geçmesi gerekmektedir. Geminin ana makine gücünün belirlenmesi kavram dizaynı sürecinde kritik bir aşamadır. Bu çalışma, genel kargo gemilerinin ana makine gücünü tahmin etmek için bir model sunmaktadır. Modelin girdi parametreleri gemi tam boyu, genişlik, gros tonaj, dedveyt tonaj ve gemi hızını içermektedir. Modelin eğitim aşamasında Levenberg-Marquardt optimizasyon algoritması kullanılmıştır. Çeşitli sayıda gizli nöronla yapılan birçok eğitim denemesinden sonra 22 gizli nöronlu yapı en iyi performansı göstermiştir. Regresyon analizine göre test seti için R değerleri 0.986, doğrulama için 0.988 ve eğitim için 0.992 olarak hesaplanmıştır. Ortalama Mutlak Hata (MAE) ve Ortalama Karekök Hata (RMSE) değerleri, MAE için 0.0128 ile 0.0148 ve RMSE için 0.0178 ile 0.0238 arasında değişerek tüm normalize edilmiş veri kümelerinde tutarlı bir şekilde düşük kalmıştır. Bu sonuçlar, modelin sağlam tahmin yeteneklerini vurgulamaktadır.

Anahtar Kelimeler

• Genel kargo gemisi
• Ana makine gücü
• Tahmin modeli
• Yapay sinir ağı

Artificial Neural Network Approach for Main Engine Power Prediction of General Cargo Vessels

Öz

Before the physical constructing of a ship will start, it must first go through a multistage design process. Determining the ship's main engine power is a critical stage in the concept design process. This work established a model to predict for the main engine power of general cargo ships. The model input parameters included ship length overall, breadth, gross tonnage, DWT and ship service speed. In the training stage of the model, Levenberg-Marquardt optimization algorithm was used. After many training attempts with various numbers of hidden neurons, the structure with 22 hidden neurons showed the best performance. R values for the test set were 0.986, 0.988 for validation, and 0.992 for training, according to regression analysis. Mean Absolute Error (MAE) and Root Mean Squared Error (RMSE) values remained consistently low across all normalized datasets, ranging from 0.0128 to 0.0148 for MAE and 0.0178 to 0.0238 for RMSE. These results underscore the model's robust predictive capabilities.

Anahtar Kelimeler

• General cargo vessel
• Main engine power
• Prediction model
• Artificial neural network

Kaynakça

1. Bayindir, R., Colak, I., Sagiroglu, S. Kahraman, H.T. (2012). Application of adaptive artificial neural network method to model the excitation currents of synchronous motors, 11th International Conference on Machine Learning and Applications, 12-15 December 2012, pp. 498-502, Boca Raton, FL, USA
2. Beale, H.D., Demuth, H.B., Hagan, M. (1996). Neural Network Design, Boston, USA.
3. Cepowski, T. (2019). Regression formulas for the estimation of engine total power for tankers, container ships and bulk carriers on the basis of cargo capacity and design speed. Polish Maritime Research 26.1 (101), 82-94.
4. Cepowski, T., Chorab, P. (2021). The use of artificial neural networks to determine the engine power and fuel consumption of modern bulk carriers, tankers and container ships. Energies, 14(16), 4827.
5. Da Silva, I.N., Spatti, D.H., Flauzino, R.A., Liboni, L. H.B., dos Reis Alves, S.F. (2017). Artificial Neural Networks, Springer International Publishing.
6. Ekinci, S., Çelebi, U.B., Bal, M., Amasyali, M.F., Boyaci, U.K. (2011). Predictions of oil/chemical tanker main design parameters using computational intelligence techniques. Applied Soft Computing, 11(2), 2356-2366.
7. Evans, J. (1959). Basic design concepts. Journal of the American Society for Naval Engineers, 71(4), 671-678.
8. Güneş, U. (2023). Estimating bulk carriers’ main engine power and emissions. Brodogradnja, 74(1), 85-98.

9. Güneş, U., Bashan, V., Ozsarı, İ., Karakurt, A.S. (2023). Predicting tanker main engine power using regression analysis and artificial neural networks. Sigma J Eng Nat Sci, 41(2): 216-225.
10. Gürgen, A. (2022). Güve-Alev Optimizasyon Algoritması Kullanarak Pleurotus cornucopiae var. citrinopileatus Mantarı Ekstraksiyon Koşullarının Optimizasyonu. Düzce Üniversitesi Bilim ve Teknoloji Dergisi 10(3): 1508-1523.
11. Gürgen, S., Altin, I., Ozkok, M. (2018). Prediction of main particulars of a chemical tanker at preliminary ship design using artificial neural network. Ships and Offshore Structures 13(5): 459-465.
12. Gürgen, S. (2023). Artificial Neural Network-Based Approach to Predict Main Engine Power in Reefer Ships, 3. International Mediterranean Congress, 17-18 April 2023, pp. 718-725, Mersin, Türkiye.
13. Hagan, M. T., Menhaj, M.B. (1994). Training feedforward networks with the Marquardt algorithm. IEEE transactions on Neural Networks 5(6): 989-993.
14. Haykin, S. (1994). Neural Networks: A Comprehensive Foundation, Prentice Hall PTR.
15. Majnarić, D., Šegota, S. B., Lorencin, I., and Car, Z. (2022). Prediction of main particulars of container ships using artificial intelligence algorithms. Ocean Engineering, 265, 112571.
16. Okumuş, F., Ekmekçioğlu, A. (2021). Modeling of General Cargo Ship’s Main Engine Powers With Regression Based Machıne Learning Algorithms. Mersin University Journal of Maritime Faculty, 3(1), 1-8.
17. Okumuş, F., Ekmekçioğlu, A., Kara, S.S. (2021). Modelling ships main and auxiliary engine powers with regression-based machine learning algorithms. Polish Maritime Research (1): 83-96.
18. Ozsari, I. (2023). Predicting main engine power and emissions for container, cargo, and tanker ships with artificial neural network analysis. Brodogradnja 74(2): 77-94.
19. Piko, G. (1980). Regression analysis of ship characteristics: Australian Government Publishing Service. Sea-Web Ships. 2021. Data base: https://maritime.ihs.com (accessed at 2021)
20. Żelazny, K. (2015). A method for determination of service speed useful in the preliminary design of cargo vessels under statistical weather conditions occurring on shipping route. Szczecin: Publishing House of West Pomeranian University of Technology in Szczecin.