针对随机海浪作用下浮体运动的非线性和非平稳特性，本文提出一种复合的小波-SVR组合方法。该方法首先对数据进行平稳性分析，然后利用小波分析将原始数据分解成有限个细节信号和逼近信号，将细节信号进行整合。采用SVR模型分别对最低频的逼近信号和整合后的细节信号进行预测，最后把2个预测结果进行叠加，得到最终的运动预测。仿真结果表明，复合的小波-SVR组合方法应用于浮体运动极短期预报可行，该方法在理论和工程应用方面具有重要的意义。
The motion of floating bodies usually has nonlinear and non-stable feature, which ARMA model is not suitable. In order to solve this problem, a composite Wavelet-SVR method is proposed. The method first analyzes the data's stability, and then uses wavelet analysis to decompose the original data into detail signals and approximation signals. The SVR model is used to predict the minimum frequency approximation signal and the integrated detail signal respectively. Finally, the two prediction results are summed to obtain the final motion prediction. The simulation results show that it is feasible to apply the combined Wavelet-SVR method to the very short-term motion prediction of floaters. This method is of great significance in theory and engineering application.
2018,40(11): 66-70 收稿日期：2017-12-04
DOI：10.3404/j.issn.1672-7649.2018.11.013
分类号：U6613
基金项目：国家自然科学基金资助项目（51509152）；工信部“第七代超深水钻井平台（船）”和“深水半潜式支持平台研发专项”经费资助项目
作者简介：盖晓娜(1992-),女,硕士研究生,主要从事极短期运动预报研究。
参考文献：
[1] HUANG L M, DUAN W Y, HAN Y, et al. A review of short-term prediction techniques for ship motions in seaway[J]. Journal of Ship Mechanics, 2014, 18(12):1534-1542.
[2] WEINER N, EXTRAPOLATION I. Smoothing of stationary time series[J]. 1949.
[3] FLECK J T. Short time prediction of the motion of a ship in waves[C]//Proc. Ist Conf. On Ships and Waves. 1954.
[4] BATES M R, BOCK D H, POWELL F D. Analog computer applications in predictor design[J]. IRE Transactions on Electronic Computers, 1957(3):143-153.
[5] BROOME D R, PITTARAS A. The time prediction of ship motions at sea[C]//Offshore Technology Conference. Offshore Technology Conference, 1990.
[6] 彭秀艳. 船舶运动姿态在线预报及仿真技术研究[D]. 哈尔滨:哈尔滨工程大学, 2006.
[7] 赵希人, 彭秀艳, 沈艳, 等. 舰船运动极短期建模预报的研究现状[J]. 船舶工程, 2002(3):4-8. ZHAO Xi-ren, PENG Xiu Yan, SHEN Yan. Study status quo of extremely short-time modeling and predicting of ship motion[J]. Ship Engineering, 2002(3):4-8.
[8] 孙李红. 基于组合预测方法的舰船纵摇运动预报[D]. 哈尔滨:哈尔滨工程大学, 2009.
[9] 杨震. 大型船舶横摇运动姿态预报技术研究[D]. 哈尔滨:哈尔滨工程大学, 2013.
[10] HUANG L M, DUAN W Y, HAN Y, et al. Extending the scope of AR model in forecasting non-stationary ship motion by using AR-EMD technique[J]. Journal of Ship Mechanics, 2015, 19(9):1033-1049.
[11] DUAN W, HUANG L, HAN Y, et al. A hybrid AR-EMD-SVR model for the short-term prediction of nonlinear and non-stationary ship motion[J]. Journal of Zhejiang University SCIENCE A, 2015, 16(7):562-576.
[12] 李亚嘉. 小波分析在船舶测试信号中的算法研究[J]. 舰船科学技术, 2017(2):115-117. LI Y-Jia. Research on the algorithm of wavelet analysis in ship test signal[J]. Ship Science and Technology, 2017(2):115-117.
[13] BOSER B E, GUYON I M, VAPNIK V N. A training algorithm for optimal margin classifiers[C]//Proceedings of the Fifth Annual Workshop on Computational Learning Theory. ACM, 1992:144-152.
