Ship Service Speed Estimation Based on the Backpropagation Neural Network

Wei Pan

doi:10.6911/WSRJ.202507_11(7).0007

Authors

Wei Pan

DOI:

https://doi.org/10.6911/WSRJ.202507_11(7).0007

Keywords:

Service Speed; Estimation; Regression formula; BP Neural Network.

Abstract

To enhance the accuracy of ship service speed estimation, a model based on a Backpropagation (BP) Neural Network was developed. This model was trained using data from 53 bulk carriers built over the past 30 years, and the corresponding model parameters were derived. A reference regression formula was then generated by re-fitting the training data to evaluate the BP Neural Network's estimation performance. Comparative analysis of the results demonstrates that both the BP Neural Network model and the reference regression formula significantly outperform the original regression formula in terms of estimation accuracy. Furthermore, residual analysis indicates that the BP Neural Network model offers greater estimation stability than the reference regression approach, making it well-suited for practical applications in ship service speed prediction.

Downloads

Download data is not yet available.

References

[1] Katsoulis P S . Optimizing block coefficient by an exponential formula[J]. Shipping World & Shipbuilder, 1975, 168.

[2] Jiang QW, Yang YZ, and Liu ZJ. The Selection of principal dimensions and parameters of large merchant ships[J] Shipbuilding of China, 1979(1):65-87.

[3] Pan WW, Zhang RL. Block Coefficient of Full Containerships[J]. Journal of Shanghai Jiaotong University, 1981(4):17-23.

[4] Cheng HY, Wang AS. Statistic rules to determine the principal ship form parameters of large container vessels[J]. Journal of Shanghai Maritime University, 1986(2):4-21.

[5] Bao P. A Block coefficient estimation formula for container ship of small and medium size[J]. Jiangsu Ship, 1992(2):17-19.

[6] Wu WL. Statistical analysis on the principal parameters of large container ships[J].Ship Engineering, 1992(1):11-14.

[7] Song ZP. Estimating formula for large and middle-sized containership[J]. Journal of Ship Design, 1997(2):1-4.

[8] Liu KZ, Wang ZX. Application of modified BP algorithm to calculate vessel collision risk degree[J]. Journal of Wuhan University of Technology(Transportation Science & Engineering) , 2003(3):412-414.

[9] Cui WB, Zhang YW, Wu GT, et al. Applying back propagation neural networks to remote monitoring of ocean going ships[J]. Journal of Harbin Engineering University, 2009(8):935-939.

[10] Zeng ZB, Ding EB, Tang DH. Ship propeller design optimization based on BP neural network and genetic algorithm[J]. Journal of Ship Mechanics, 2010, 14(z1):20-27.

[11] Zhang HM, Sun ZL, Gao MZ. Application of the improved BP neural network in ship and ocean engineering[J]. Journal of Ship Mechanics, 2010, 14(z1):20-27.

[12] Hu XR , Lin CC. A Preliminary Study on Targets Association Algorithm of Radar and AIS Using BP Neural Network[J]. Procedia Engineering, 2011, 15:1441-1445.

[13] Zhu JS, Sun LC, Yin JC, et al. Simulation of ship lights recognition model based on back propagation neural network[J]. Journal of Basic Science and Engineering, 2012, 20(3).

[14] He ZW, Yang F, Liu LR. Ship safe navigation depth reference map based on AIS data[J]. Journal of Traffic and Transportation Engineering, 2018,18(04):171-181.