多变量非高斯风压的高性能智能预测

李春祥,涂伟平

振动与冲击 ›› 2019, Vol. 38 ›› Issue (11) : 249-257.

PDF(2824 KB)
PDF(2824 KB)
振动与冲击 ›› 2019, Vol. 38 ›› Issue (11) : 249-257.
论文

多变量非高斯风压的高性能智能预测

  • 李春祥,涂伟平
作者信息 +

High performance intelligent prediction for multivariate non-Gaussian wind pressure

  • LI Chunxiang,   TU Weiping
Author information +
文章历史 +

摘要

为了提高最小二乘支持向量机(LSSVM)对多变量非高斯风压预测的精度和泛化能力,本文采用混合蚁群(ACO)和粒子群(PSO)智能算法优化LSSVM的正则化参数和核参数,从而形成了混合智能优化LSSVM(称为ACO+PSO-LSSVM)多变量非高斯风压预测算法。使用现场实测多变量非高斯风压数据,对ACO+PSO-LSSVM多变量非高斯风压预测算法的性能进行验证,并与基于蚁群(ACO)和粒子群(PSO)智能优化LSSVM(分别称为ACO-LSSVM和PSO-LSSVM)的预测结果进行比较。比较结果表明,对于多变量非高斯风压预测,混合智能优化LSSVM(ACO+PSO-LSSVM)是高性能预测性算法,具有工程应用前景。

Abstract

In order to improve prediction accuracy and generalization ability of the least square support vector machine (LSSVM) used for forecasting multivariate non-Gaussian wind pressure, a hybrid intelligent algorithm using the ant colony optimization (ACO) and the particle swarm optimization (PSO) called the ACO+PSO algorithm was employed to optimize regularization parameters and kernel ones of LSSVM, and form the hybrid intelligent optimization LSSVM named the ACO+PSO-LSSVM algorithm for forecasting multivariate non-Gaussian wind pressure. The field measured multivariate non-Gaussian wind pressure data were used to verify the performance of the ACO+PSO-LSSVM algorithm. The prediction results using the ACO+PSO-LSSVM algorithm were compared with those using the ACO-LSSVM algorithm and the PSO-LSSVM one, respectively. The comparison results showed that for multivariable non-Gaussian wind pressure prediction, the ACO+PSO-LSSVM algorithm is a high performance intelligent prediction one, and has a bright prospect of engineering application.

关键词

混合智能优化 / 最小二乘支持向量机 / 多变量 / 非高斯风压 / 预测性能

Key words

 Hybrid intelligent optimization / Least square support sector machine / Multivariate / Non-Gaussian wind pressure / Prediction performance

引用本文

导出引用
李春祥,涂伟平. 多变量非高斯风压的高性能智能预测[J]. 振动与冲击, 2019, 38(11): 249-257
LI Chunxiang, TU Weiping. High performance intelligent prediction for multivariate non-Gaussian wind pressure[J]. Journal of Vibration and Shock, 2019, 38(11): 249-257

参考文献

[1] Suykens J A, Vandewalle J. Least squares support vector machine classifiers. Neural Processing Letters [J], 1999, 9(3), 293–300.
[2] 迟恩楠, 李春祥. 基于优化组合核和Morlet小波核的LSSVM脉动风速预测方法 [J]. 振动与冲击, 2016,35(18): 52-57.
Li Chunxiang, Chi Ennan. Forecasting fluctuating wind velocity using optimized combination kernel and Morlet wavelet kernel based LSSVM [J]. Journal of Vibration and Shock, 2016,35(18): 52-57.
[3] 李春祥, 迟恩楠, 何亮, 李正农. 基于时变ARMA和EMD-PSO-LSSVM算法的非平稳下击暴流风速预测 [J]. 振动与冲击, 2016,35(17): 33-38, 51.
Li Chunxiang, Chi En-nan, He Liang, Li Zhengnong. Prediction of nonstationary downburst wind velocity based on time-varying ARMA and EMD- PSO-LSSVM algorithms [J]. Journal of Vibration and Shock, 2016,35(17): 33-38, 51.
[4] Pardo M, Sberveglieri G. Classification of electronic nose data with support vector machines [J]. Sensors and Actuators B: Chemical, 2005, 107(2): 730–737.
[5] Dorigo M, Sttzle T. The Ant Colony Optimization Metaheuristic: Algorithms, Applications, and Advances [M]. Kluwer Academic Publishers, 2002.
[6] Zlochin M, Birattari M, Meuleau N, Dorigo M. Model-based search for combinatorial optimization [R]. Technical Report TR/IRIDIA/2001-15.
[7] Shi Y, Eberhart R C. A modified particle swarm optimizer, in: Proceedings of IEEE International Conference on Evolutionary Computation [R], IEEE Press, 1998.
[8] 李春祥, 丁晓达, 叶继红. 基于混合蚁群和粒子群优化LSSVM的脉动风速预测 [J]. 振动与冲击, 2016, 35(21): 131-136.
Li Chun-xiang, Ding Xiao-da, Ye Ji-hong. Fluctuating wind velocity forecasting of hybridizing ant colony and particle swarm optimization based LSSVM [J]. Journal of Vibration and Shock, 2016, 35 (21): 131-136.
[9] 李锦华,吴春鹏,陈水生. 矩形结构非高斯风荷载特性研究 [J]. 振动、测试与诊断, 2014, 34(5): 951-959.
Li Jin-hua, Wu Chun-peng, Chen Shui-sheng, Characteristics of Non-Gaussian Wind Pressures on Rectangular Structure [J]. Journal of Vibration, Measurement & Diagnosis, 2014, 34(5): 951-959.

PDF(2824 KB)

Accesses

Citation

Detail

段落导航
相关文章

/