基于小波和乘法混合核函數(shù)LSSVM的順風(fēng)向非高斯空間風(fēng)壓預(yù)測(cè)
發(fā)布時(shí)間:2019-05-06 18:59
【摘要】:提出了基于Marr小波核函數(shù)最小二乘支持向量機(jī)(Marr-LSSVM)的順風(fēng)向非高斯空間風(fēng)壓預(yù)測(cè)算法。通過傳統(tǒng)高斯核函數(shù)(RBF)和多項(xiàng)式核函數(shù)(Poly)的乘法運(yùn)算,提出了Poly*RBF-LSSVM(MK-LSSVM)的空間風(fēng)壓預(yù)測(cè)算法。運(yùn)用粒子群優(yōu)化(PSO)算法,對(duì)Marr-LSSVM、傳統(tǒng)單核CSK-LSSVM和MK-LSSVM的懲罰參數(shù)、核函數(shù)參數(shù)、權(quán)重、尺度因子進(jìn)行優(yōu)化,建立基于智能優(yōu)化的非高斯空間風(fēng)壓預(yù)測(cè)算法;以30 m和50 m處模擬順風(fēng)向風(fēng)壓時(shí)程作為輸入樣本,使用提出的預(yù)測(cè)算法對(duì)40 m處風(fēng)壓時(shí)程進(jìn)行了預(yù)測(cè)。數(shù)值分析表明,Marr-LSSVM、MK-LSSVM比CSK-LSSVM具有明顯高的非高斯風(fēng)壓預(yù)測(cè)性能。
[Abstract]:Based on the Marr wavelet kernel function least squares support vector machine (Marr-LSSVM), a forward wind pressure prediction algorithm for non-Gao Si space is proposed. Based on the multiplication of traditional Gao Si kernel function (RBF) and polynomial kernel function (Poly), a spatial wind pressure prediction algorithm for Poly*RBF-LSSVM (MK-LSSVM) is proposed. Particle swarm optimization (PSO) algorithm is used to optimize the penalty parameters, kernel function parameters, weights and scale factors of traditional single-core CSK-LSSVM and MK-LSSVM in Marr-LSSVM, and a non-Gaussian spatial wind pressure prediction algorithm based on intelligent optimization is established. Taking 30 m and 50 m as input samples, the time history of wind pressure at 40 m is predicted by using the proposed prediction algorithm. Numerical analysis shows that Marr-LSSVM,MK-LSSVM has significantly higher non-Gao Si wind pressure prediction performance than CSK-LSSVM.
【作者單位】: 上海大學(xué)土木工程系;同濟(jì)大學(xué)建筑工程系;
【基金】:國(guó)家自然科學(xué)基金(51378304)
【分類號(hào)】:TP18
本文編號(hào):2470410
[Abstract]:Based on the Marr wavelet kernel function least squares support vector machine (Marr-LSSVM), a forward wind pressure prediction algorithm for non-Gao Si space is proposed. Based on the multiplication of traditional Gao Si kernel function (RBF) and polynomial kernel function (Poly), a spatial wind pressure prediction algorithm for Poly*RBF-LSSVM (MK-LSSVM) is proposed. Particle swarm optimization (PSO) algorithm is used to optimize the penalty parameters, kernel function parameters, weights and scale factors of traditional single-core CSK-LSSVM and MK-LSSVM in Marr-LSSVM, and a non-Gaussian spatial wind pressure prediction algorithm based on intelligent optimization is established. Taking 30 m and 50 m as input samples, the time history of wind pressure at 40 m is predicted by using the proposed prediction algorithm. Numerical analysis shows that Marr-LSSVM,MK-LSSVM has significantly higher non-Gao Si wind pressure prediction performance than CSK-LSSVM.
【作者單位】: 上海大學(xué)土木工程系;同濟(jì)大學(xué)建筑工程系;
【基金】:國(guó)家自然科學(xué)基金(51378304)
【分類號(hào)】:TP18
【相似文獻(xiàn)】
相關(guān)期刊論文 前2條
1 王宏健;徐金龍;李娟;張愛華;;非平穩(wěn)非高斯測(cè)量噪聲條件下改進(jìn)差分粒子濾波算法研究[J];兵工學(xué)報(bào);2014年07期
2 ;[J];;年期
相關(guān)博士學(xué)位論文 前2條
1 王剛;基于最大非高斯估計(jì)的獨(dú)立分量分析理論研究[D];國(guó)防科學(xué)技術(shù)大學(xué);2005年
2 屈毅;非高斯隨機(jī)分布系統(tǒng)控制與故障檢測(cè)方法的研究[D];蘭州理工大學(xué);2013年
相關(guān)碩士學(xué)位論文 前2條
1 楊楠;基于改進(jìn)核獨(dú)立元分析的非高斯過程監(jiān)測(cè)方法研究[D];東北大學(xué);2014年
2 許大星;非線性系統(tǒng)的幾種濾波算法研究[D];杭州電子科技大學(xué);2014年
,本文編號(hào):2470410
本文鏈接:http://sikaile.net/kejilunwen/zidonghuakongzhilunwen/2470410.html
最近更新
教材專著