Prediction of Surface Ship's Residual Resistance Coefficient Using Neural Networks

Article Preview

Abstract:

The Holtrop method, which provides a prediction of the components of surface ships total resistance, is widely used at ships initial design stage for estimating the resistance. In this paper a neural network model which performs the same role as the Holtrop method is presented to predict the residual resistance. A multilayer perceptron has been trained with the data generated by the Holtrop method to learn the relationship between the input (length-displacement ratio, prismatic coefficient, breadth-draft ratio and Froude number) and the target variable (the residual resistance coefficient). The results of this model have been compared against those provided by the Holtrop method and it is found that the quality of the prediction is improved over the entire range of data. The neural network provides an accurate estimation of the residual resistance with the Froude number and the hull geometry coefficients as variables.

You might also be interested in these eBooks

Info:

Periodical:

Advanced Materials Research (Volumes 756-759)

Pages:

3141-3144

Citation:

Online since:

September 2013

Export:

Price:

[1] Holtrop J. A statistical analysis of performance test results [J]. International Ship Build Progress, 1977, 24(270), pp.23-28.

DOI: 10.3233/isp-1977-2427001

Google Scholar

[2] Holtrop J, Mennen G G J. A statistical power prediction method [J]. International Ship Build Progress, 1978, 25(290), pp.253-256.

DOI: 10.3233/isp-1978-2529001

Google Scholar

[3] Holtrop J, Mennen G G J. An approximate power prediction method [J]. International Ship Build Progress, 1982, 29(335), pp.166-170.

DOI: 10.3233/isp-1982-2933501

Google Scholar

[4] Holtrop J, Mennen G G J. A statistic re-analysis of resistance and Propulsion data [J]. International Ship Build Progress, 1984, 37(363), pp.272-274.

Google Scholar

[5] JIE Zheng-hua. Research on Prediction of Ship Powering Performance Based on Ship Model Testing Database [J]. Journal of Shanghai Ship and Shipping Research Institute, 2004, 2(27).

Google Scholar

[6] YAN Wei, JIN Feng, HAN Jibin. Ship model test technologies and application [J]. Hubei Water Power, 2008, (01).

Google Scholar

[7] NI Chong-ben1, ZHU Ren-chuan1, MIAO Guo-ping1, FAN She-ming2. A method for ship resistance prediction based on CFD computation [J], Chinese Journal of Hydrodynamics, (2010).

Google Scholar

[8] T. Ratcliffe. An Experimental and Computational Study of the Effects of Propulsion on the Free-Surface Flow Astern of Model 5415[J]. Proceedings of the 23rd Symposium of Naval Hydrodynamics, (2000).

Google Scholar

[9] Chi Yang, Francis Noblesse, Rainald Lohner. Practical CFD Applications to Design of a Wave Cancellation Multihull Ship [J]. Proceedings of the 23rd Symposium of Naval Hydrodynamics, (2000).

Google Scholar

[10] Yuan Hongliang. Holtrop method and hull form resistance estimation [J]. Ship & Boat, 2003, (5), pp.13-17.

Google Scholar

[11] CUI Yan, LU Xiao-ping. Hull parameters optimization based on Holtrop formula and genetic algorithm [J]. Journal of Naval University of Engineering, 2009, 21(6), pp.26-29.

Google Scholar

[12] Goutam Kumar Saha, Asim Kumar Sarker. Optimization of ship hull parameter of Inland vessel with respect to regression based resistance analysis[R]. MARTEC 2010 conference, 2010, pp.471-476.

Google Scholar

[13] SHENG Zhenbang, LIU Yingzhong. Principles of Ship [M]. Shanghai: Shanghai Jiao tong university press, 2003, p.272~274.

Google Scholar

[14] Walter A. Shewhart, Samuel S. Wilks. Linear Regression Analysis [M]. New Zealand: Auckland, 2003, pp.35-49.

Google Scholar

[15] Hogan, M.T., Howard, B., Beale, D.M. Neural network design [M]. The Math Works Inc., Colorado (1996).

Google Scholar

[16] Lu, J.J., Chen, H. Researching development on BP neural networks [J]. Control Engineering of China 5, p.449–451 (2006).

Google Scholar