基于振动信号最优特征提取算法的风力机齿轮箱SVM故障诊断

李俊逸; 尧远; 刘明浩

doi:10.19912/j.0254-0096.tynxb.2023-0484

PDF(1438 KB)

太阳能学报 ›› 2024, Vol. 45 ›› Issue (7) : 626-633. DOI: 10.19912/j.0254-0096.tynxb.2023-0484

基于振动信号最优特征提取算法的风力机齿轮箱SVM故障诊断

李俊逸^1,2, 尧远^1,2, 刘明浩^1,2

作者信息 +

SVM FAULT DIAGNOSIS OF WIND TURBINE'S GEARBOX BASED ON OPTIMAL FEATURE EXTRACTION ALGORITHM OF VIBRATION SIGNAL

Li Junyi^1,2, Yao Yuan^1,2, Liu Minghao^1,2

Author information +

文章历史 +

摘要

针对风力机齿轮箱故障诊断的特征提取过程,提出基于振动信号最优特征提取算法的风力机齿轮箱SVM故障诊断方法。首先,分析3种主要特征提取算法各自适应性高的信号类型;然后,根据不同类型信号所具有的信号特性,利用信号分析对传入的振动信号进行特性提取并分类,将不同类别信号与适应性高的特征提取算法进行匹配,实现振动信号的最优特征提取;最后,将匹配算法与支持向量机模型结合实现故障诊断。对实际采集的3种齿轮故障信号进行测试与验证,结果表明该方法可有效进行最优特征提取与算法匹配,相比未经过匹配算法具有更高的故障诊断准确率。

Abstract

Aiming at the feature extraction process of wind turbine's gear box fault diagnosis, a SVM fault diagnosis method based on the optimal feature extraction algorithm of vibration signal is proposed. Firstly, the signal types with high adaptability of the three main feature extraction algorithms are analyzed. Then, according to the signal characteristics of different types of signals, the characteristics of incoming vibration signals are extracted and classified by signal analysis, and the different types of signals are matched with the feature extraction algorithm with high adaptability to achieve the optimal feature extraction of vibration signals. Finally, the matching algorithm and support vector machines model are combined to realize fault diagnosis. Three kinds of gear fault signals collected in practice are tested and verified. The results show that this method can effectively extract the optimal features and match the algorithm, and has a higher fault diagnosis accuracy than the unmatched algorithm.

导出引用

李俊逸, 尧远, 刘明浩. 基于振动信号最优特征提取算法的风力机齿轮箱SVM故障诊断[J]. 太阳能学报. 2024, 45(7): 626-633 https://doi.org/10.19912/j.0254-0096.tynxb.2023-0484

Li Junyi, Yao Yuan, Liu Minghao. SVM FAULT DIAGNOSIS OF WIND TURBINE'S GEARBOX BASED ON OPTIMAL FEATURE EXTRACTION ALGORITHM OF VIBRATION SIGNAL[J]. Acta Energiae Solaris Sinica. 2024, 45(7): 626-633 https://doi.org/10.19912/j.0254-0096.tynxb.2023-0484

中图分类号： TM315

参考文献

[1] HUANG N E, SHEN Z, LONG S R, et al.The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis[J]. Proceedings of the Royal Society of London series A, 1998, 454(1971): 903-998.
[2] 赵国庆, 王志刚, 李友荣, 等. 希尔伯特黄变换在齿轮故障诊断中的应用[J]. 武汉科技大学学报(自然科学版), 2007, 30(1): 54-56, 78.
ZHAO G Q, WANG Z G, LI Y R, et al.Application of Hilbert-Huang transform in gear fault diagnosis[J]. Journal of Wuhan University of Science and Technology (natural science edition), 2007, 30(1): 54-56, 78.
[3] 周旭明, 徐鹏, 赵芬妮, 等. 基于自混合干涉技术和希尔伯特-黄变换的齿轮箱故障检测[J]. 激光与光电子学进展, 2022, 59(23): 144-149.
ZHOU X M, XU P, ZHAO F N, et al.Gearbox fault detection based on self-mixing interference technology and Hilbert-Huang transform[J]. Laser & optoelectronics progress, 2022, 59(23): 144-149.
[4] 张旋. 基于振动信号稀疏分解的风电机组故障诊断方法研究[D]. 北京: 华北电力大学, 2018.
ZHANG X.Research on fault diagnosis method of wind turbine based on sparse decomposition of vibration signals[D]. Beijing: North China Electric Power University, 2018.
[5] 高永新, 戴忠林, 秦灿. GASA-PSO优化算法共振稀疏分解齿轮故障诊断研究[J]. 噪声与振动控制, 2022, 42(5): 123-127.
GAO Y X, DAI Z L, QIN C.Study on gearbox fault diagnosis methods using GSAA-PSO optimization algorithm[J]. Noise and vibration control, 2022, 42(5): 123-127.
[6] 张守京, 慎明俊, 杨静雯, 等. 改进的共振稀疏分解方法及其在滚动轴承复合故障诊断中的应用[J]. 中国机械工程, 2022, 33(14): 1697-1706.
ZHANG S J, SHEN M J, YANG J W, et al.Improved RSSD and its applications to composite fault diagnosis of rolling bearings[J]. China mechanical engineering, 2022, 33(14): 1697-1706.
[7] WU J D, CHUANG C Q.Fault diagnosis of internal combustion engines using visual dot patterns of acoustic and vibration signals[J]. NDT & E international, 2005, 38(8): 605-614.
[8] 杨乐. 基于奇异值差分谱和SDP图像相关分析的故障诊断方法[J]. 机械设计与研究, 2017, 33(4): 113-116, 126.
YANG L.Fault diagnosis method based on difference spectrum of singular value and SDP image correlation analysis[J]. Machine design & research, 2017, 33(4): 113-116, 126.
[9] 张苏颖, 竺兴妹, 许曙青. 基于深度置信网络和对称点模式电机轴承故障诊断研究[J]. 噪声与振动控制, 2022, 42(3): 98-104, 143.
ZHANG S Y, ZHU X M, XU S Q.Research of motor bearing fault diagnosis based on deep belief network and symmetric dot pattern[J]. Noise and vibration control, 2022, 42(3): 98-104, 143.
[10] 胡澜也, 蒋文博, 李艳婷. 基于LightGBM的风力发电机故障诊断[J]. 太阳能学报, 2021, 42(11): 255-259.
HU L Y, JIANG W B, LI Y T.Fault diagnosis for wind turbine based on LightGBM[J]. Acta energiae solaris sinica, 2021, 42(11): 255-259.
[11] 王宏伟, 孙文磊, 张小栋, 等. 基于优化VMD复合多尺度散布熵及LSTM的风力发电机齿轮箱故障诊断方法研究[J]. 太阳能学报, 2022, 43(4): 288-295.
WANG H W, SUN W L, ZHANG X D, et al.Fault diagnosis method of wind turbine's gearbox based on composite multiscale dispersion entropy of optimised VMD and LSTM[J]. Acta energiae solaris sinica, 2022, 43(4): 288-295.
[12] 雷春丽, 薛林林, 焦孟萱, 等. 结合改进ResNet与迁移学习的风力机滚动轴承故障诊断方法[J]. 太阳能学报, 2023, 44(6): 436-444.
LEI C L, XUE L L, JIAO M X, et al.Fault diagnosis method of wind turbines rolling bearing based on improved ResNet and transfer learning[J]. Acta energiae solaris sinica, 2023, 44(6): 436-444.
[13] 张龙, 宋成洋, 邹友军, 等. 基于VMD多特征融合与PSO-SVM的滚动轴承故障诊断[J]. 机械设计与研究, 2019, 35(6): 96-104.
ZHANG L, SONG C Y, ZOU Y J, et al.A rolling bearingfault diagnosis method bsaed on VMD multi feature fusion and PSO-SVM[J]. Machine design & research, 2019, 35(6): 96-104.
[14] 范志锋, 华鉴波. 基于多特征融合的行星齿轮箱点蚀故障诊断研究[J]. 机械与电子, 2022, 40(9): 46-50.
FAN Z F, HUA J B.Research on pitting fault diagnosis of planetary gearbox based on multi-feature fusion[J]. Machinery & electronics, 2022, 40(9): 46-50.
[15] 程军圣, 王健, 桂林. 改进的EEMD方法及其在滚动轴承故障诊断中的应用[J]. 振动与冲击, 2018, 37(16): 51-56.
CHENG J S, WANG J, GUI L.An improved EEMD method and its application in rolling bearing fault diagnosis[J]. Journal of vibration and shock, 2018, 37(16): 51-56.
[16] 宋向金, 王卓, 胡静涛, 等. Hilbert解调制方法诊断异步电机轴承故障[J]. 电工技术学报, 2018, 33(21): 4941-4948.
SONG X J, WANG Z, HU J T, et al.Diagnosis of bearing fault in induction motors using Hilbert demodulation approach[J]. Transactions of China Electrotechnical Society, 2018, 33(21): 4941-4948.
[17] 萧如珀, 杨信男. 1927年2月: 海森堡的测不准原理[J]. 现代物理知识, 2010, 22(1): 66-67.
XIAO R P, YANG X N.February 1927: Heisenberg's uncertainty principle[J]. Modern physics, 2010, 22(1): 66-67.
[18] 龚永涛, 肖涵, 易灿灿. 基于粒子群优化的共振稀疏分解在轴承故障诊断中的应用[J]. 机械设计与制造, 2017(4): 21-25.
GONG Y T, XIAO H, YI C C.Application of particle swarm optimization based resonance sparse decomposition on bearing fault diagnosis[J]. Machinery design & manufacture, 2017(4): 21-25.
[19] 李强, 韩军, 汪满新, 等. 基于信号共振稀疏分解的自动换刀装置故障诊断[J]. 组合机床与自动化加工技术, 2019(4): 107-110.
LI Q, HAN J, WANG M X, et al.The fault diagnosis of automatic tool changer on the resonance-based sparse signal decomposition[J]. Modular machine tool & automatic manufacturing technique, 2019(4): 107-110.
[20] 马增强, 李亚超, 刘政, 等. 基于变分模态分解和Teager能量算子的滚动轴承故障特征提取[J]. 振动与冲击, 2016, 35(13): 134-139.
MA Z Q, LI Y C, LIU Z, et al.Rolling bearings'fault feature extraction based on variational mode decomposition and Teager energy operator[J]. Journal of vibration and shock, 2016, 35(13): 134-139.
[21] VAPNIK V N.An overview of statistical learning theory[J]. IEEE transactions on neural networks, 1999, 10(5): 988-999.
[22] 史庆军, 郭晓振, 刘德胜. 基于特征量融合和支持向量机的轴承故障诊断[J]. 电子测量与仪器学报, 2019, 33(10): 104-111.
SHI Q J, GUO X Z, LIU D S.Bearing fault diagnosis based on feature fusion and support vector machine[J]. Journal of electronic measurement and instrumentation, 2019, 33(10): 104-111.
[23] 刘永前, 王飞, 时文刚, 等. 基于支持向量机的风电机组运行工况分类方法[J]. 太阳能学报, 2010, 31(9): 1191-1197.
LIU Y Q, WANG F, SHI W G, et al.Operation condition classification method for wind turbine based on support vector machine[J]. Acta energiae solaris sinica, 2010, 31(9): 1191-1197.