多变量非高斯风压的高性能智能预测
|
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,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。
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.
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.
引文
[1] SUYKENS J A,VANDEWALLE J.Least squares support vector machine classifiers[J].Neural Processing Letters,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.CHI Ennan,LI Chunxiang.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,等.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.LI Chunxiang,CHI Ennan,HE Liang,et al.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.
[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].Norwell,MA:Kluwer Academic Publishers,2002.
[6] ZLOCHIN M,BIRATTARI M,MEULEAU N,et al.Model-based search for combinatorial optimization[R].Technical Report TR/IRIDIA/2001-15.
[7] SHI Y,EBERHART R C.A modified particle swarm optimizer[C]//Proceedings of IEEE International Conference on Evolutionary Computation.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 Chunxiang,DING Xiaoda,YE Jihong.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 Jinhua,WU Chunpeng,CHEN Shuisheng.Characteristics of non-Gaussian wind pressures on rectangular structure[J].Journal of Vibration,Measurement & Diagnosis,2014,34(5):951-959.
[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.CHI Ennan,LI Chunxiang.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,等.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.LI Chunxiang,CHI Ennan,HE Liang,et al.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.
[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].Norwell,MA:Kluwer Academic Publishers,2002.
[6] ZLOCHIN M,BIRATTARI M,MEULEAU N,et al.Model-based search for combinatorial optimization[R].Technical Report TR/IRIDIA/2001-15.
[7] SHI Y,EBERHART R C.A modified particle swarm optimizer[C]//Proceedings of IEEE International Conference on Evolutionary Computation.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 Chunxiang,DING Xiaoda,YE Jihong.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 Jinhua,WU Chunpeng,CHEN Shuisheng.Characteristics of non-Gaussian wind pressures on rectangular structure[J].Journal of Vibration,Measurement & Diagnosis,2014,34(5):951-959.