为了准确高效预测船舶在海上的航行状态，以保证人员、货物和船舶的安全，提出一种自适应变异的粒子群优化算法（self-adapting particle swarm optimization algorithm，SAPSO），将该算法与误差反传（back propagation，BP）神经网络结合。SAPSO-BP预测模型使用SAPSO算法优化BP网络的网络参数。克服传统BP神经网络对初始权值阈值敏感，容易陷入局部极小值的缺点，同时也克服了传统PSO算法早熟收敛、搜索准确度低及迭代效率低等缺点。运用该模型对科研教学船“育鲲”轮在海上航行的横摇情况进行实时预测实验，验证该方法的可行性与有效性具有较高的预测精度。
In order to predict the navigation state of ship in the wind and waves accurately, timely and efficient and ensure the safety of personnel, cargo and ship. We propose a self-adapting particle swarm optimization (SAPSO) algorithm to optimize the back propagation (BP) neural network model. The proposed model is referred to as SAPSO-BP model which employs PSO to adjust control parameters of BP network. This method overcomes the shortcomings of traditional BP neural network, which is sensitive to the threshold value of the initial value and is easy to fall into local minimum. At the same time, it also overcomes the shortcomings of the traditional PSO algorithm, such as premature convergence, low accuracy, and low efficiency and so on. The measurement data from scientific research and training ship Yukun was chosen as the test database. Simulation results have demonstrated that the proposed method can give predictions for ship rolling motion in real time with high accuracy and satisfactory stability.
2016,38(12): 69-73 收稿日期：2016-04-25
DOI：10.3404/j.issn.1672-7619.2016.12.014
分类号：U661.3
基金项目：国家自然科学基金资助项目（51279106，51009017，51379002）；中央高校基本科研业务经费资助项目（3132016116，3132016314）；交通部应用基础研究项目（2014329225010）；辽宁省自然科学基金资助项目（2014025008）
作者简介：张泽国(1991-),男,硕士研究生,主要研究方向为智能算法及船舶运动控制。
参考文献：
[1] FOSSEN T I. Handbook of marine craft hydrodynamics and motion control[M]. Hoboken N.J, USA:John Wiley & Sons Ltd., 2011:20-80.
[2] FOSSEN T I. Guidance and control of ocean vehicles[M]. Chichester, New York, USA:John Wiley & Sons Ltd., 1994:10-100.
[3] 郑丽颖. 混沌神经网络及模糊混沌神经网络的研究与应用[D]. 哈尔滨:哈尔滨工程大学, 2002.
[4] 席剑辉. 混沌时间序列的长期预测方法研究[D]. 大连:大连理工大学, 2005.
[5] LIN Y J. Prevention of transient instability employing rules based on back propagation based ANN for series compensation[J]. International Journal of Electrical Power & Energy Systems, 2011, 33(10):1776-1783.
[6] BASERI H. BAKHSHI-JOOYBARI M. RAHMANI B. Modeling of spring-back in V-die bending process by using fuzzy learning back-propagation algorithm[J]. Expert Systems with Applications, 2011, 38(7):8894-8900.
[7] 贾嵘, 薛建辉, 张文宇, 等. 基于邻域粒子群优化神经网络的异步电动机振动故障诊断[J]. 西安石油大学学报(自然科学版), 2010, 25(2):73-75.
[8] YIN J C, ZOU Z J, XU F, et al. Online ship roll motion prediction based on grey sequential extreme learning machine[J]. Journal of Neurocomputing, 2014, 129:168-174.
[9] KENNEDY J, EBERHART R. Particle swarm optimization[C]//Proceedings of IEEE international conference on neural networks. Perth, WA, Australia:IEEE, 1995(4):1942-1948.
[10] 刘永清, 孙江龙, 王嘉俊, 等. LNG船运动响应数值计算与试验研究[J]. 舰船科学技术, 2016, 38(3):25-30. LIU Yong-qing, SUN Jiang-long, WANG Jia-jun. et al. Numerical and experimental study of LNG ship motion response[J]. Ship Science and Technology, 2016, 38(3):25-30.
[11] 刘胜, 邢博闻, 陈潇. 船舶信息系统数据流设计方案研究[J]. 舰船科学技术, 2016, 38(4):110-115. LIU Sheng, XING Bo-wen, CHEN Xiao. Design of data flow for ship information system[J]. Ship Science and Technology, 2016, 38(4):110-115.
