针对风电机组柔性塔架因机械疲劳、振动等引起的失稳问题,采用改进的回归方法建立塔架振动预测模型。在风电机组不同运行工况下,通过相关性分析对多源异构数据进行优化,求出影响柔性塔架振动的相关联变量。基于灰狼优化（GWO）算法得到支持向量回归（SVR）方法的最优参数,建立塔架振动预测模型。以某风场2 MW风电机组120 m柔性塔架数据进行仿真分析,结果表明,在额定风速以上工况下,GWO优化SVR模型相较于BP模型、SVR模型、粒子群算法（PSO）优化SVR模型、鲸鱼优化算法（WOA）优化SVR模型,均方根误差RMSE分别降低了11.143、8.925、8.263、3.651;平均绝对误差MAE分别降低了9.032、7.016、2.665、3.233。基于GWO优化的SVR模型提高了柔性塔架振动预测精度,可为柔性塔架的振动控制提供准确数据支持。
Abstract
Aiming at the instability of wind turbine flexible tower caused by mechanical fatigue and vibration, an improved regression method is used to establish the tower vibration prediction model. Under different operating conditions of wind turbines, correlation analysis is performed to optimize the multi-source heterogeneous data in order to find the correlation variables affecting the vibration of flexible towers. The optimal parameters of the support vector regression （SVR） method are obtained based on the grey wolf optimization （GWO） algorithm to establish the tower vibration prediction model. The 120 m flexible tower data of a 2 MW wind turbine in a wind farm are simulated and analyzed. The results show that compared with BP model, SVR model, particle swarm optimization （PSO） optimized SVR model and whale optimization algorithm （WOA） optimized SVR model, the root mean square error（RMSE） of GWO optimized SVR model is reduced by 11.143, 8.925, 8.263 and 3.651 respectively and the average absolute error（MAE） is decreased by 9.032, 7.016, 2.665 and 3.233 respectively under the working conditions above the rated wind speed. The SVR model based on GWO optimization improves the accuracy of flexible tower vibration prediction and can provide accurate data support for the vibration control of flexible towers.
关键词
风电机组 /
塔架 /
振动分析 /
预测模型 /
误差分析
Key words
wind turbines /
towers /
vibration analysis /
prediction model /
error analysis
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] 兰杰, 林淑, 付斌, 等. 风力发电机组塔架减振控制策略设计[J]. 分布式能源, 2021, 6(3): 55-62.
LAN J, LIN S, FU B, et al.Wind turbine tower vibration reduction of control strategy design[J]. Distributed energy, 2021, 6(3): 55-62.
[2] 黄竹也, 倪玲, 裘浩锋, 等. 风机塔架4种TMD振动控制模拟比较研究[J]. 河南理工大学学报(自然科学版), 2020, 39(2): 85-90.
HUANG Z Y, NI L, QIU H F, et al.Comparative study on four TMD vibration control simulation methods of wind turbine tower[J]. Journal of Henan Polytechnic University(natural science edition), 2020, 39(2): 85-90.
[3] QIU B B, LU Y, SUN L P, et al.Research on the damage prediction method of offshore wind turbine tower structure based on improved neural network[J]. Measurement, 2020, 151: 107141.
[4] SU L C, GUO G X, LI Y W.Vibration monitoring of wind turbine tower based on XGBoost[J]. Journal of physics conference series, 2021, 1948(1): 012075.
[5] HUO T, TONG L W.Wind-induced response analysis of wind turbine tubular towers with consideration of rotating effect of blades[J]. Advances in structural engineering, 2020, 23(2): 289-306.
[6] 杜静, 冯博, 何玉林. 风力发电机组塔筒的横向振动分析[J]. 现代制造工程, 2011(9): 116-118,129.
DU J, FENG B, HE Y L.Analysis of transverse vibration for wind turbine tower[J]. Modern manufacturing engineering, 2011(9): 116-118,129.
[7] 郭鹏, 王雪茹. 风电机组高斯过程回归塔架振动监测研究[J]. 动力工程学报, 2015, 35(5): 380-386.
GUO P, WANG X R.Vibration monitoring by Gaussian process regression for of wind turbine tower[J]. Journal of chinese society of power engineering, 2015, 35(5): 380-386.
[8] 魏煜, 谢永和, 李俊来, 等. 三浮体风机塔架振动模型实验与振动时域分析[J]. 浙江海洋大学学报(自然科学版), 2020, 39(3): 245-251.
WEI Y, XIE Y H, LI J L, et al.Vibration model test and time domain analysis of three-floating wind turbine tower[J]. Journal of Zhejiang Ocean University(natural science ), 2020, 39(3): 245-251.
[9] 郭鹏, 徐明, 白楠, 等. 基于SCADA运行数据的风电机组塔架振动建模与监测[J]. 中国电机工程学报, 2013, 33(5): 128-135,20.
GUO P, XU M, BAI N, et al.Wind turbine tower vibration modeling and monitoring driven by SCADA data[J]. Proceedings of the CSEE, 2013, 33(5): 128-135,20.
[10] 颜永龙. 风电机组运行状态评估与短期可靠性预测方法研究[D]. 重庆: 重庆大学, 2015.
YAN Y L.Investigation to approaches of online condition assessment and short-term reliability prediction of wind turbines[D]. Chongqing: Chongqing University, 2015.
[11] 栾祥霖. 考虑尾流效应的双馈风力发电机组并网频率稳定技术研究[D]. 沈阳: 沈阳工程学院, 2020.
LUAN X L.Research on grid-connected frequency stability of doubly-fed wind turbines considering wake effect[D]. Shenyang: Shenyang institnte of engineering, 2020.
[12] 李治琴. 直驱永磁同步风力发电机变桨控制仿真研究[D]. 重庆: 西南大学, 2010.
LI Z Q.Simulation on the pitch control of direct-drive permanent magnet synchronous generator[D]. Chongqing:Southwest University, 2010.
[13] 郭广颂, 高海荣, 张勇. 基于迁移学习灰支持向量回归机的交互式进化计算[J]. 控制与决策, 2021, 36(10): 2399-2408.
GUO G S, GAO H R, ZHANG Y.Interactive evolutionary computation based on transfer learning grey support vector regression machine[J]. Control and decision, 2021, 36(10): 2399-2408.
基金
2021年辽宁省教育厅重点项目（LJKZ1088）
PDF(3733 KB)
