基于调和分析和ARIMA-SVR的组合潮汐预测模型
|
摘要
为提高潮汐预测精度,解决单一调和分析预测精度不高的问题,提出一种基于调和分析和自回归综合移动平均-支持向量回归机(autoregressive integrated moving average support vector machine for regression,ARIMA-SVR)的组合潮汐预测模型。潮汐分析中,潮汐可认为是由受引潮力影响的天文潮位和受环境因素影响的非线性水位的叠加。采用小波分析对潮汐样本数据进行去噪处理,使用调和分析法计算天文潮位,以调和分析法计算产生的残差作为非线性水位样本数据,并使用ARIMA-SVR模型进行潮高计算,最后将两部分的计算结果进行线性求和得到最终的潮汐预测值。利用美国旧金山港口实测潮汐数据进行预测仿真,结果表明,该组合模型解决了调和分析忽略非线性影响的问题,提高了潮汐预测准确率,可行且高效。
To improve the accuracy of tide prediction and solve the problem of low accuracy of single harmonic analysis, a combined tide prediction model based on the harmonic analysis and the autoregressive integrated moving average-support vector machine for regression(ARIMA-SVR) is proposed. In tide analysis, tide can be considered as the superposition of astronomical tide level affected by tide-generating force and non-linear water level affected by environmental factors. The wavelet analysis is used to denoise the tide sample data. The harmonic analysis method is used to calculate the astronomical tide level. The residual sequence generated by the harmonic analysis method is used as the sample data of non-linear water level, and ARIMA-SVR model is used to calculate the tide height. The tide prediction value is obtained by linear summation of the calculated results of the two parts. The simulation of prediction is carried out using measured tide data of San Francisco Port of the United States. The results show that: the combined model solves the problem of ignoring nonlinear effects in the traditional harmonic analysis, and the accuracy of tide prediction is improved; the combined model is feasible and efficient.
To improve the accuracy of tide prediction and solve the problem of low accuracy of single harmonic analysis, a combined tide prediction model based on the harmonic analysis and the autoregressive integrated moving average-support vector machine for regression(ARIMA-SVR) is proposed. In tide analysis, tide can be considered as the superposition of astronomical tide level affected by tide-generating force and non-linear water level affected by environmental factors. The wavelet analysis is used to denoise the tide sample data. The harmonic analysis method is used to calculate the astronomical tide level. The residual sequence generated by the harmonic analysis method is used as the sample data of non-linear water level, and ARIMA-SVR model is used to calculate the tide height. The tide prediction value is obtained by linear summation of the calculated results of the two parts. The simulation of prediction is carried out using measured tide data of San Francisco Port of the United States. The results show that: the combined model solves the problem of ignoring nonlinear effects in the traditional harmonic analysis, and the accuracy of tide prediction is improved; the combined model is feasible and efficient.
引文
[1] TSAI Ching-Piao,LIN Chang,SHEN Jia-N.Neural network for wave forecasting among multi-stations[J].Ocean Engineering,2002,29(13):1683-1695.DOI:10.1016/S0029-8018(01)00112-3.
[2] LIN Li-Ching,CHANG Hsien-Kuo.An adaptive neuro-fuzzy inference system for sea level prediction considering tide-generating forces and oceanic thermal expansion[J].Terrestrial Atmospheric & Oceanic Sciences,2008,19(1/2):163-172.DOI:10.3319/TAO.2008.19.1-2.163(SA).
[3] JAIN P,DEO M C.Real-time wave forecasts off the western Indian coast[J].Applied Ocean Research,2007,29(1/2):72-79.DOI:10.1016/j.apor-2007.05.003.
[4] 孟二浩.基于改进的EMD混合模型月径流预测研究[D].西安:西安理工大学,2018.
[5] 康军,段宗涛,唐蕾,等.一种LS-SVM在线式短时交通流预测方法[J].计算机应用研究,2018,35(10):2965-2968.
[6] 刘爱国,薛云涛,胡江鹭,等.基于GA优化SVM的风电功率的超短期预测[J].电力系统保护与控制,2015,43(2):90-95.
[7] 甘泽,李志刚,张岩.潮汐发电中调和分析与人工神经网络预测潮位[J].河北联合大学学报(自然科学版),2014,36(1):84-87.
[8] 姚德峰.基于调和分析的短期潮位粗差探测与修复方法研究[J].勘察科学技术,2016(6):28-30.
[9] 柳成,尹建川.一种高精度的短期潮汐预报模型[J].上海海事大学学报,2016,37(3):74-80.DOI:10.13340/j.jsmu.2016.03.014.
[10] 梁昌勇,马银超,陈荣,等.基于SVR-ARMA组合模型的日旅游需求预测[J].管理工程学报,2015,29(1):122-127.DOI:10.13587/j.cnki.jieem.2015.01.016.
[11] 柳成.基于支持向量机的模块化潮汐预报[D].大连:大连海事大学,2017.
[12] 孙映宏,章国稳,姬战生.基于支持向量机的钱塘江潮时预报方法[J].水力发电,2017,43(7):17-21.
[13] 张泽国,尹建川,柳成,等.基于SAPSO-BP网络模型的港口潮汐实时预报[J].水运工程,2017(1):34-40.DOI:10.16233/j.cnki.issn1002-4972.2017.01.006.
[14] ZHANG Zeguo,YIN Jianchuan,WANG Nini,et al.A precise tidal prediction mechanism based on the combination of harmonic analysis and adaptive network-based fuzzy inference system model[J].Acta Oceanologica Sinica,2017,36(11):94-105.DOI:10.1007/s13131-017-1140-x.
[2] LIN Li-Ching,CHANG Hsien-Kuo.An adaptive neuro-fuzzy inference system for sea level prediction considering tide-generating forces and oceanic thermal expansion[J].Terrestrial Atmospheric & Oceanic Sciences,2008,19(1/2):163-172.DOI:10.3319/TAO.2008.19.1-2.163(SA).
[3] JAIN P,DEO M C.Real-time wave forecasts off the western Indian coast[J].Applied Ocean Research,2007,29(1/2):72-79.DOI:10.1016/j.apor-2007.05.003.
[4] 孟二浩.基于改进的EMD混合模型月径流预测研究[D].西安:西安理工大学,2018.
[5] 康军,段宗涛,唐蕾,等.一种LS-SVM在线式短时交通流预测方法[J].计算机应用研究,2018,35(10):2965-2968.
[6] 刘爱国,薛云涛,胡江鹭,等.基于GA优化SVM的风电功率的超短期预测[J].电力系统保护与控制,2015,43(2):90-95.
[7] 甘泽,李志刚,张岩.潮汐发电中调和分析与人工神经网络预测潮位[J].河北联合大学学报(自然科学版),2014,36(1):84-87.
[8] 姚德峰.基于调和分析的短期潮位粗差探测与修复方法研究[J].勘察科学技术,2016(6):28-30.
[9] 柳成,尹建川.一种高精度的短期潮汐预报模型[J].上海海事大学学报,2016,37(3):74-80.DOI:10.13340/j.jsmu.2016.03.014.
[10] 梁昌勇,马银超,陈荣,等.基于SVR-ARMA组合模型的日旅游需求预测[J].管理工程学报,2015,29(1):122-127.DOI:10.13587/j.cnki.jieem.2015.01.016.
[11] 柳成.基于支持向量机的模块化潮汐预报[D].大连:大连海事大学,2017.
[12] 孙映宏,章国稳,姬战生.基于支持向量机的钱塘江潮时预报方法[J].水力发电,2017,43(7):17-21.
[13] 张泽国,尹建川,柳成,等.基于SAPSO-BP网络模型的港口潮汐实时预报[J].水运工程,2017(1):34-40.DOI:10.16233/j.cnki.issn1002-4972.2017.01.006.
[14] ZHANG Zeguo,YIN Jianchuan,WANG Nini,et al.A precise tidal prediction mechanism based on the combination of harmonic analysis and adaptive network-based fuzzy inference system model[J].Acta Oceanologica Sinica,2017,36(11):94-105.DOI:10.1007/s13131-017-1140-x.
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |