|
|
|
| Multivariate nonstationary fluctuating wind velocity prediction using kernel-based extreme learning machine |
| Zheng Xiaofen1 Zhong Wang2 Li Chunxiang2 |
1. Department of Structural Engineering, Tongji University, Shanghai 200092;
2. Department of Civil Engineering, Shanghai University, Shanghai 200444 |
|
|
|
|
Abstract By resorting to Fast Ensemble Empirical Mode Decomposition (FEEMD), the nonstationary downburst wind velocity sample can be decomposed into a series of intrinsic mode functions (IMFs). Subsequently, the hybridizing FEEMD and kernel-based extreme learning machine, referred to as the FEEMD-KELM, are proposed, so as to forecast training set and testing set partitioned to IMFs. For the purpose of comparison, the results of hybridizing FEEMD and extreme learning machine (FEEMD-ELM) are also taken into consideration. Comparing the results of these two predicting algorithms shows that the FEEMD-KELM renders more stable and higher accuracy than the FEEMD-ELM.
|
|
Received: 02 September 2016
Published: 15 September 2017
|
|
|
|
[1] Huang GB, Zhu QY, Siew CK. Extreme learning machine: a new learning scheme of feedforward neural networks [C]. Proceedings of International joint conference on neural networks (IJCNN2004), 2004, 2: 985-990.
[2] Wang D, Huang GB. Protein sequence classification using extreme learning machine [C]. Proceedings of international joint conference on neural networks, 2005, 3: 1406-1411.
[3] 钟旺, 李春祥. 基于极限学习机的非平稳下击暴流风速预测. 上海大学学报，已录用，2016.
Zhong Wang, Li Chunxiang. Predicting nonstationary downburst wind velocity based on extreme learning machines. Journal of Shanghai University, to be published.
[4] Huang NE, Shen Z, Long SR. The empirical mode decomposition and Hilbert spectrum for nonlinear and non-stationary time series analysis [J]. Proc. Roy. Soc., 1998, 454(17): 903-905.
[5] Wu Z, Huang NE. Ensemble empirical mode decomposition: a noise-assisted data analysis method [J]. Advances in Adaptive Data Analysis, 2009, 1(1): 1-41.
[6] Wang YH, Yeh CH. On the computational complexity of the empirical mode decomposition algorithm [J]. Physica A, 2014, 1: 159-167.
[7] Huang GB, Zhu QY, Siew CK. Extreme learning machine: theory and application [J]. Neurocomputing, 2006, 70(1-3): 489-501.
[8] Fu H, Vong C-M, Wong P-K, Yang Z. Fast detection of impact location using kernel extreme learning machine. Neural Computing & Applications，2014: 1-10.
[9] 李锦华, 吴春鹏, 陈水生. 下击暴流非平稳脉动风速数值模拟 [J]. 振动与冲击, 2014, 33(14): 54-60.
Li JH, Wu CP, Chen SS. Simulation of non-stationary fluctuating wind velocity in downburst [J]. Journal of Vibration and Shock, 2014, 33(14): 54-60.
[10] Li JH, Li CX, He L, Shen JH. Extended modulating functions for simulation of wind velocities with weak and strong nonstationarity [J]. Renewable Energy, 2015, 5: 384-397.
[11] 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.
Li Chunxiang，Chi Ennan，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.
[12] 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): 20-.
Li Chunxiang, Ding xiaoda, Ye Jihong. Fluctuating wind velocity forecasting of hybridizing ant colony and particle swarm optimization based LSSVM. Journal of Vibration and Shock, 2016, 35(21): 20-.
[13] 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. Journal of Vibration and Shock, 2016, 35(18): 52-57.
[14] 张永康, 李春祥,郑晓芬. 基于混合人工蜂群和人工鱼群优化的LSSVM脉动风速预测. 振动与冲击, 2017, 36(18).
Zhang Yongkang, Li Chunxiang. Fluctuating wind velocity forecasting of hybridizing artificial bee colony and artificial fish swarm optimization based LSSVM. Journal of Vibration and Shock, 2017, 36(18).
|
|
|
|
