针对风力发电机组轴承故障振动信号传递路径复杂多变,且故障信号易受到背景噪声的严重干扰,传统方法对故障特征难以准确提取的问题,提出一种自适应经验小波变换（AEWT）与奇异值分解（SVD）的特征提取方法,并结合核极限学习机（KELM）实现风电机组轴承的故障诊断,该方法同时考虑轴承不同故障类型及不同损伤等级的情况。其中,自适应EWT为两阶段调整过程：基于尺度空间法固有模态函数（IMF）分解-确保EWT分解的有效性、基于相关系数最大的敏感分量提取-实现相关特征最大化和冗余信息的消除。通过相关实验结果可明显发现,所提AEWT的分解效果优于EMD、EEMD、CEEMDAN、LMD等方法。对提取敏感分量利用SVD计算奇异值,构建故障特征向量;最后将特征向量作为KELM的输入,建立KELM轴承状态识别模型。通过西储大学平台轴承振动信号和实际风场采集的轴承振动信号对算法进行验证,结果表明,相比SVM、ELM、KNN等识别模型,该方法能有效识别出不同故障类型及不同损伤等级下的轴承故障,整体识别率达99%。
Abstract
Aiming at the problem that the transmission path of the vibration signal of wind turbine bearing fault is complex and changeable, and the fault signal is susceptible to severe interference from background noise, which makes it is difficult to accurately extract fault features with traditional methods, an adaptive empirical wavelet transform （AEWT） and the singular value decomposition （SVD） feature extraction method is proposed in this paper, by which and combined with the kernel extreme learning machine （KELM）, the fault diagnosis of the wind turbine bearing is realized. This method also considers the different fault types and different damage levels of the bearing. Among them, the adaptive EWT is a two-stage adjustment process： that is, based on the intrinsic mode function （IMF） decomposition of the scale space method-to ensure the effectiveness of the EWT decomposition; based on the extraction of the sensitive component with the largest correlation coefficient to maximize the relevant features and redundant information elimination. Through relevant experimental results, it can be clearly found that the decomposition effect of the proposed AEWT is better than EMD, EEMD, CEEMDAN, LMD and other methods. After that, SVD is used to calculate the singular values of the extracted sensitive components to construct the fault feature vector; finally, the feature vector is used as the input of KELM to establish the KELM bearing state recognition model. The algorithm is verified by bearing data collected on the platform of Western Reserve University and bearing data collected from actual wind farms. The results show that compared with recognition models such as SVM, ELM, and KNN, this method can effectively identify bearing faults under different fault types and different damage levels. The overall recognition ratches 99%.
关键词
风电机组 /
故障诊断 /
轴承 /
特征提取 /
信号处理 /
经验小波变换 /
核极限学习机
Key words
wind turbines /
fault detection /
bearing /
feature extraction /
signal processing /
Empirical wavelet transform /
Kernel extreme learning machine
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] CHEN J L, PAN J, LI Z P, et al.Generator bearing fault diagnosis for wind turbine via empirical wavelet transform using measured vibration signals[J]. Renewable energy, 2016, 89: 80-92.
[2] 唐贵基, 庞彬. ITT变换在风电机组滚动轴承故障诊断中的应用[J]. 电力自动化设备, 2017, 37(9): 83-89.
TANG G J, PANG B.Application of ITT transform in fault diagnosis of wind turbine rolling bearing[J]. Electric power automation equipment, 2017, 37(9): 83-89.
[3] HU Y T, ZHANG S Q, JIANG A Q, et al.A new method of wind turbine bearing fault diagnosis based on multi-masking empirical mode decomposition and fuzzy c-means clustering[J]. Chinese journal of mechanical engineering, 2019, 32(1): 1-12.
[4] 李辉, 李洋, 杨东, 等. 基于EMD相关去噪的风电机组振动噪声抑制及特征频率提取[J]. 电机与控制学报, 2016, 20(1): 73-80.
LI H, LI Y, YANG D, et al.Noise suppression and characteristic frequency extraction of wind turbine vibration based on EMD correlation denoising[J]. Electric machines and control, 2016,20(1): 73-80.
[5] 王军辉, 贾嵘, 谭泊. 基于EEMD和模糊C均值聚类的风电机组齿轮箱故障诊断[J]. 太阳能学报,2015, 36(2): 319-324.
WANG J H, JIA R, TAN B.Fault diagnosis of wind turbine's gearbox based on EEMD and fuzzy c means clustering[J]. Acta energiae solaris sinica, 2015, 36(2): 319-324.
[6] 胡显能, 蔡改贫, 罗小燕, 等. 基于CEEMDAN和多尺度排列熵的球磨机负荷识别方法[J]. 噪声与振动控制, 2018, 38(3): 146-151.
HU X N, CAI G P, LUO X Y, et al.Load identification method for ball mills based on CEEMDAN and multi-scale permutation entropy[J]. Noise and vibration control, 2018, 38(3): 146-151.
[7] 梁凯, 刘韬, 马培原, 等. 基于改进CEEMDAN和优化重构的轴承故障特征提取研究[J]. 机械强度, 2019, 41(3): 532-539.
LIANG K, LIU T, MA P Y, et al.Rolling bearing fault feature extraction research based on improved CEEMDAN and reconstruction[J]. Journal of mechanical strength, 2019, 41(3): 532-539.
[8] 付云骁, 贾利民, 秦勇, 等. 基于LMD-CM-PCA的滚动轴承故障诊断方法[J]. 振动·测试与诊断, 2017, 37(2): 249-255.
FU Y X, JIA L M, QIN Y, et al.Roller bearing fault diagnosis method based on LMD-CM-PCA[J]. Journal of vibration, measurement and diagnosis, 2017, 37(2): 249-255.
[9] GILLES J.Empirical wavelet transform[J]. IEEE transactions on signal processing, 2013, 61(16): 3999-4010.
[10] GILLES J, TRAN G, OSHER S.2D Empirical transforms. wavelets, ridgelets and curvelets revisited[J]. SIAM journal on imaging sciences, 2014, 7(1): 157-186.
[11] 吕跃刚, 何洋洋. EWT和ICA联合降噪在轴承故障诊断中的应用[J]. 振动与冲击, 2019, 38(16): 42-48.
LYU Y G, HE Y Y.Application of an EWT-ICA combined method in fault diagnosis of rolling[J]. Journal of vibration and shock, 2019, 38(16): 42-48.
[12] CUI Y H, LI L L, CHEN R L, et al.Incipient fault diagnosis of rolling bearing using accumulative component kurtosis in SVD process[J]. Journal of vibroengineering, 2018, 20(3): 1443-1458.
[13] LUO M, LI C S, ZHANG X Y, et al.Compound feature selection and parameter optimization of ELM for fault diagnosis of rolling element bearings[J]. ISA transactions, 2016, 65: 556-566.
[14] 皮骏, 马圣, 贺嘉诚, 等. 基于IGA-ELM网络的滚动轴承故障诊断[J]. 航空学报, 2018, 39(9): 228-239.
PI J, MA S, HE J C, et al.Rolling bearing fault diagnosis based on IGA-ELM network[J]. Acta aeronautica et astronautica sinica, 2018, 39(9): 228-239.
[15] HUANG G B, ZHOU H M, DING X J, et al.Extreme learning machine for regression and multiclass classification[J]. IEEE transactions on systems, man, and cybernetics, part B, 2012, 42(2): 513-529.
[16] 龙霞飞, 杨苹, 郭红霞, 等. 基于KELM和多传感器信息融合的风电齿轮箱故障诊断[J]. 电力系统自动化, 2019, 43(17): 132-139.
LONG X F, YANG P, GUO H X, et al.Fault diagnosis of wind turbine gearbox based on KELM and multi-sensor information fusion[J]. Automation of electric power systems, 2019, 43(17): 132-139.
[17] TENG W, WANG W, MA H X, et al.Adaptive fault detection of the bearing in wind turbine generators using parameterless empirical wavelet transform and margin factor[J]. Journal of vibration and control, 2019, 25(6): 1263-1278.
基金
国家自然科学基金（61763037,61863029）; 内蒙古自然科学基金（2019LH6007）; 内蒙古科技成果转化项（CGZH2018129）
PDF(3086 KB)
