Modeling of wind turbine blade root loads based on extreme learning machine

PDF(1263 KB)

Journal of Vibration and Shock ›› 2018, Vol. 37 ›› Issue (4) : 257-262.

QIN Bin YI Huai-yang WANG Xin

Author information +

History +

Abstract

In view of load variety, nonlinear and strong coupling of the wind turbine system, and complex mechanism and large amount of computation of traditional blade root load models, a neural network model based on extreme learning machine (ELM) was proposed to predict the blade root loads in this paper. Firstly, the factors that affect the blade root loads were analyzed, and the model inputs were determined by the principal component analysis. The data from National Renewable Energy Laboratory (NREL) was then used to set up training and test sets, and the blade root loads of a 5MW wind turbine system were modelled and predicted by the proposed method. Finally, the model performance was compared with that of the model established based on the support vector machine (SVM). The simulation results show that the ELM model has high training speed and high prediction accuracy, which verified its feasibility and effectiveness.

Key words

wind turbine / blade root load modeling / ELM / SVM

Cite this article

EndNote

Ris (Procite)

Bibtex

Download Citations

QIN Bin YI Huai-yang WANG Xin. Modeling of wind turbine blade root loads based on extreme learning machine[J]. Journal of Vibration and Shock, 2018, 37(4): 257-262

References

[1] Johnson S J, Baker J P, Van D C P, et al. An overview of active load control techniques for wind turbine with an emphasis on microtabs[J]. Wind Energy, 2010, 13(2‐3):239-253
[2] 肖帅, 杨耕, 耿华. 抑制载荷的大型风电机组滑模变桨距控制[J]. 电工技术学报, 2013, 28(7):145-150.
     XIAO Shuai, YANG Geng, GENG Hua. Sliding-mode pitch control strategy for large wind turbines to reduce loads[J]. Transactions of China Electrotechnical Society, 2013, 28(7):145-150.
[3] Yao X, Wang X, Xing Z, et al. Individual pitch control for variable speed turbine blade load mitigation[C]// IEEE International Conference on Sustainable Energy Technologies. IEEE, 2008:769-772.
[4] 曹九发, 王同光, 王枭. 大型风力机的几何非线性动态响应研究[J]. 振动与冲击, 2016, 35(14):182-187.
CAO Jiu-fa, WANG Tong-guang, WANG Xiao. Geometric nonlinear dynamics response of large-scale wind turbine[J]. Journal of Vibration and Shock, 2016, 35(14):182-187.
[5] 王爽心, 李朝霞. 变桨距风电机组自适应PI优化控制[J]. 太阳能学报, 2013, 34(9):1579-1586.
     WANG Shuang-xin, LI Zhao-xia. Adaptive PI optimization control for variable-pitch wind turbines[J]. 2013, 34(9):1579-1586.
[6] 郝云霄, 闫楚良, 刘克格. 基于支持向量机的机翼载荷模型研究[J]. 科学技术与工程, 2013, 13(25):7432-7437.
     HAO Yun-xiao, YAN Chu-liang, LIU Ke-ge. Modeling Aircraft Wing Loads Based on Support Vector Machine[J]. Science Technology & Engineering, 2013.
[7] Mohammadi K, Shamshirband S, Yee P L, et al. Predicting the wind power density based upon extreme learning machine[J]. Energy, 2015, 16:232-239.
[8] Huang G B, Zhu Q Y, Siew C K. Extreme learning machine: Theory and applications[J]. Neurocomputing, 2006, 70(1–3):489-501.
[9] 刘军, 陈东亮. 基于神经网络风力发电机组载荷优化控制策略研究[J]. 电气传动, 2014, 44(2):59-63.
     LIU Jun, CHEN Dong-liang. Optimal Control Strategy for Wind Turbine Load Reduction Based on Neural Network[J]. Electric Drive, 2014.
[10] 刘皓明, 唐俏俏, 张占奎,等. 基于方位角和载荷联合反馈的独立变桨距控制策略研究[J]. 中国电机工程学报, 2016, 36(14):3798-3805.
     LIU Hao-ming, TANG Qiao-qiao, ZHANG Zhan-kui, et al. Study of Individual Pitch Control Based on Azimuth Angle and Load Feedback[J]. Proceedings of The Chinese Society for Electrical Engineering, 2016, 36(14).
[11] 何伟. 湍流风场模拟与风力发电机组载荷特性研究[D]. 华北电力大学, 2013.
[12] 张小桃, 倪维斗, 李政,等. 基于主元分析与现场数据的过热汽温动态建模研究[J]. 中国电机工程学报, 2005, 25(5):131-135.
     ZHANG Xiao-tao, NI Wei-dou, LI Zheng, et al. Dynamic modeling study of superheater steam temperature based on principal component analysis method and online data[J]. Proceedings of the Csee, 2005, 25(5):131-135.
[13] Huang G B, Zhu Q Y, Siew C K. Extreme learning machine: a new learning scheme of feedforward neural networks[J]. Proc.int.joint Conf.neural Netw, 2004, 2:985-990 vol.2.
[14] Bartlett P L. For Valid Generalization, the Size of the Weights is More Important Than the Size of the Network[J]. Advances in Neural Information Processing Systems, 1997:134-140.
[15] 陈严, 张林伟, 刘雄,等. 水平轴风力机叶片疲劳载荷的计算分析[J]. 太阳能学报, 2013, 34(5):902-908.
     CHEN Yan, ZHANG Lin-wei, LIU Xiong, et al. Fatigue load calculation and analysis of the blade of horizontal axis wind turbine[J]. Taiyangneng Xuebao/acta Energiae Solaris Sinica, 2013, 34(5):902-908.
[16] Ding C Y, Li G Q, Guo H C. Fatigue Analysis of Wind Turbine[J]. Applied Mechanics & Materials, 2012, 229-231:621-624.
[17] 张颖, 李梅, 高倩倩,等. 基于 ELMR-SVMR 的海水水质预警模型研究[J]. 大连理工大学学报, 2016, 56(2):185-192.
     ZHANG Ying, LI Mei, GAO Qian-qian, et al. Research on forewarning model of seawater quality based on ELMR-SVMR[J]. Journal of Dalian University of Technology, 2016.