针对风电机组风轮不平衡的识别与检测问题,提出一种基于多核融合支持向量机的风轮不平衡识别方法。首先,分析风轮不平衡的影响,提出一种基于变分模态分解（VMD）的信号分解与重构方法;其次,提出基于模糊熵的风轮不平衡特征提取方法,以高斯核函数作为模糊函数,该方法具有较好的噪声鲁棒性和较低的数据长度依赖性;再次,提出基于多核融合支持向量机的风轮不平衡识别方法,融合不同特征和尺度的核函数组成核函数库,并选取最优核函数;最后,在不同湍流强度的仿真中建立交叉验证数据库对该方法进行验证,识别准确率在98%以上,证明该方法能有效识别风轮不平衡。
Abstract
For the problem of identification and detection of rotor imbalance, an identification method of rotor imbalance based on multi-kernel learning support vector machine is proposed. Firstly, the influence of rotor imbalance is analyzed, and a signal decomposition and reconstruction method based on VMD is proposed. Secondly, a feature extraction method based on fuzzy entropy is proposed, which uses Gaussian kernel function as fuzzy function. The method has better noise robustness and lower data length dependence. Thirdly, an identification method based on multi-kernel learning support vector machine is proposed. Kernel functions of different features and scales are fused to form the kernel function library, and the optimal kernel function is selected. Finally, a cross-validation database is established to verify the proposed method in the simulation of different turbulence intensities. The accuracy is above 98%. The results show that the proposed method can identify rotor imbalance effectively.
关键词
风电机组 /
状态监测 /
机器学习 /
风轮不平衡 /
模糊熵 /
支持向量机
Key words
wind turbines /
condition monitoring /
machine learning /
rotor imbalance /
fuzzy entropy /
support vector machine
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] MISHNAEVSKY L.Repair of wind turbine blades: review of methods and related computational mechanics problems[J]. Renewable energy, 2019, 140: 828-839.
[2] 刘善超, 宫伟, 傅新鸿, 等. 海上风电机组气动不平衡下发电与振动性能[J]. 船舶工程, 2022, 44(S2): 1-6, 83.
LIU S C, GONG W, FU X H, et al.Power generation and vibration performance of offshore wind turbines under aerodynamic imbalance[J]. Ship engineering, 2022, 44(S2): 1-6, 83.
[3] 秦思远, 李峥峰. 风轮不平衡的风电机组机械振动信号频域特性分析[J]. 可再生能源, 2022, 40(9): 1202-1208.
QIN S Y, LI Z F.Analysis on frequency domain characteristics of mechanical loads on wind turbine rotor imbalance[J]. Renewable energy resources, 2022, 40(9): 1202-1208.
[4] 赵丽军, 张璠, 厉伟, 等. 风电机组风轮不平衡机械载荷时域特性分析[J]. 太阳能学报, 2020, 41(8): 342-350.
ZHAO L J, ZHANG F, LI W, et al.Analysis on time domain characteristics of imbalanced mechanical loads of wind turbine rotor[J]. Acta energiae solaris sinica, 2020, 41(8): 342-350.
[5] XING Z X, CHEN M Y, CUI J, et al.Detection of magnitude and position of rotor aerodynamic imbalance of wind turbines using Convolutional Neural Network[J]. Renewable energy, 2022, 197: 1020-1033.
[6] 李贝, 田德, 唐世泽, 等. 超大型风电机组叶片颤振分析及参数灵敏度研究[J]. 太阳能学报, 2023, 44(9): 295-301.
LI B, TIAN D, TANG S Z, et al.Study on flutter limit of ultra-large wind turbine blades under rotor imbalance loads[J]. Acta energiae solaris sinica, 2023, 44(9): 295-301.
[7] JUNIOR R F R, DOS SANTOS AREIAS METHODOLY I A, CAMPOS M M, et al. Fault detection and diagnosis in electric motors using 1d convolutional neural networks with multi-channel vibration signals[J]. Measurement, 2022, 190:110759.
[8] AWADALLAH M, EL-SINAWI A.Effect and detection of cracks on small wind turbine blade vibration using special Kriging analysis of spectral shifts[J]. Measurement, 2020, 151: 107076.
[9] 石腾, 许波峰, 李振, 等. 基于数字图像处理的风电机组叶片裂纹损伤识别方法研究[J]. 太阳能学报, 2024, 45(2): 86-94.
SHI T, XU B F, LI Z, et al.Research on crack damage identification method of wind turbine blades based on digital image processing[J]. Acta energiae solaris sinica, 2024, 45(2): 86-94.
[10] GROOTEMAN F.Multiple load path damage detection with optical fiber Bragg grating sensors[J]. Structural health monitoring, 2021, 20(1): 46-57.
[11] 党建, 魏晋源, 贾嵘, 等. 基于Hilbert和CA-VMD的风电机组叶轮不平衡故障电信号特征提取方法[J]. 电网与清洁能源, 2021, 37(1): 112-118, 126.
DANG J, WEI J Y, JIA R, et al.Feature extraction method for unbalanced fault electrical signal of wind turbine impeller based on Hilbert and CA-VMD[J]. Power system and clean energy, 2021, 37(1): 112-118, 126.
[12] 高峰, 张鸿, 许琳, 等. 风电机组叶片故障仿真与状态判别研究[J]. 太阳能学报, 2023, 44(4): 52-59.
GAO F, ZHANG H, XU L, et al.Research on fault simulation and state judgment of wind turbine blades[J]. Acta energiae solaris sinica, 2023, 44(4): 52-59.
[13] RAUBER T W, LOCA A, BOLDT F, et al.An experimental methodology to evaluate machine learning methods for fault diagnosis based on vibration signals[J]. Expert systems with applications, 2021, 167(1): 114022.
[14] FREEMAN B, TANG Y F, HUANG Y, et al.Rotor blade imbalance fault detection for variable-speed marine current turbines via generator power signal analysis[J]. Ocean engineering, 2021, 223: 108666.
[15] MALIK H, MISHRA S.Artificial neural network and empirical mode decomposition based imbalance fault diagnosis of wind turbine using TurbSim, FAST and Simulink[J]. IET renewable power generation, 2017, 11(6): 889-902.
[16] 焦静. 基于同轴振动特征融合的滚动轴承故障诊断研究[D]. 北京: 北京交通大学, 2022.
JIAO J.Research of rolling bearing fault diagnosis based on coaxial vibration feature fusion[D]. Beijing: Beijing Jiaotong University, 2022.
[17] HÜBNER G R, PINHEIRO H, DE SOUZA C E, et al. Detection of mass imbalance in the rotor of wind turbines using support vector machine[J]. Renewable energy, 2021, 170(C): 49-59.
PDF(1382 KB)
