Fault diagnosis of planetary gearbox based on improved composite multi-scale sample entropy
-
摘要:
针对多尺度样本熵受样本长度影响较大,且粗粒化过程较粗糙,易忽略有效信息的不足,在复合多尺度样本熵的基础上,以采样点间能量分布作为权重进行粗粒化计算,提出了改进的复合多尺度样本熵,并将其应用于行星齿轮箱故障诊断。通过仿真信号研究不同参数和不同噪声特性对改进复合多尺度样本熵算法的影响,将其与多尺度样本熵、广义多尺度样本熵、复合多尺度样本熵进行对比,验证了本文改进算法的稳定性。结合变分模态分解、主成分分析和支持向量机对行星齿轮箱实验信号进行故障诊断。对比结果表明:所提方法能够有效地实现不同工况和不同结构行星齿轮箱太阳轮常见故障诊断,且故障识别率达到95%以上,具有一定的有效性。
Abstract:In view of the fact that the multi-scale sample entropy is greatly affected by the sample length, the coarse graining process is relatively rough, and the shortage of effective information may be easily ignored, based on the composite multi-scale sample entropy, the energy distribution between sampling points was used as the weight for coarse graining calculation, and an improved composite multi-scale sample entropy was proposed and applied to the fault diagnosis of planetary gearbox. The influences of different parameters and noise characteristics on the improved composite multi-scale sample entropy algorithm were studied through simulation signals. The stability of the improved algorithm was verified by comparing it with multi-scale sample entropy, generalized multi-scale sample entropy and composite multi-scale sample entropy. Combined with variational mode decomposition, principal component analysis and support vector machine, the fault diagnosis of planetary gearbox experimental signals was carried out. The comparison results showed that the method can effectively realize the common fault diagnosis of the sun gear of the planetary gearbox under different working conditions and structures, and the fault identification rate was more than 95%, with certain effectiveness.
-
表 1 20 Hz转频下太阳轮常见故障对应VMD参数
Table 1. VMD parameters corresponding to common faults of sun gear at 20 Hz rotating frequency
算法参数 正常 裂纹 缺齿 磨损 K 4 5 6 6 α 2250 2750 1750 1750 表 2 fim与原始信号的相关系数和欧氏距离
Table 2. Correlation coefficient and Euclidean distance between fim and original signal
分量 相关系数 欧氏距离 fim1 0.8153 0.4892 fim2 0.7703 0.6077 fim3 0.7033 0.6924 fim4 0.6567 0.7512 fim5 0.5614 0.8092 fim6 0.4756 0.8331 表 3 支持向量机多故障分类器对4种太阳轮故障识别结果(Qtrain1,Qtest1)
Table 3. Recognition results of support vector machine multi fault classifier for four kinds of sun gear faults (Qtrain1,Qtest1)
特征提取
方法(c,g) SVM多故障分类器对测试样本识别结果/% 正常状态识别率 裂纹故障识别率 缺齿故障识别率 磨损故障识别率 平均故障识别率 MSE (48.50,0.57) 80 55 95 90 80 GMSE (16,1.5) 90 90 100 55 83.75 CMSE (27.8,7.5) 80 90 100 90 90 ICMSE (62.7,3.2) 80 100 100 100 95 表 4 基于ICMSE和SVM的识别结果
Table 4. Recognition results based on ICMSE and SVM
特征提取
方法随机样本 (c,g) SVM多故障分类器对测试样本识别结果/% 正常状态识别率 裂纹故障识别率 缺齿故障识别率 磨损故障识别率 平均故障识别率 ICMSE Qtrain2,Qtest2 (67,4.7) 87 100 100 97 96 Qtrain3,Qtest3 (48,6.2) 83 100 100 100 95.75 -
[1] 周怡娜,董宏丽,张勇,等. 基于VMD去噪和散布熵的管道信号特征提取方法[J]. 吉林大学学报(工学版),2022,52(4): 959-969. ZHOU Yina,DONG Hongli,ZHANG Yong,et al. Feature extraction method of pipeline signals based on VMD denoising and dispersion entropy[J]. Journal of Jilin University (Engineering and Technology Edition),2022,52(4): 959-969. (in ChineseZHOU Yina, DONG Hongli, ZHANG Yong, et al. Feature extraction method of pipeline signals based on VMD denoising and dispersion entropy[J]. Journal of Jilin University (Engineering and Technology Edition), 2022, 52(4): 959-969. (in Chinese) [2] 党建,罗燚,田录林,等. 基于优化的VMD融合信息熵和FA_PNN的风电机组齿轮箱故障诊断[J]. 太阳能学报,2021,42(1): 198-204. DANG Jian,LUO Yi,TIAN Lulin,et al. Fault diagnosis of wind turbine gearbox based on optimized vmd fusion information entropy and FA_PNN[J]. Acta Energiae Solaris Sinica,2021,42(1): 198-204. (in ChineseDANG Jian, LUO Yi, TIAN Lulin, et al. Fault diagnosis of wind turbine gearbox based on optimized vmd fusion information entropy and FA_PNN[J]. Acta Energiae Solaris Sinica, 2021, 42(1): 198-204. (in Chinese) [3] 雷亚国,何正嘉,林京,等. 行星齿轮箱故障诊断技术的研究进展[J]. 机械工程学报,2011,47(19): 59-67. LEI Yaguo,HE Zhengjia,LIN Jing,et al. Research advances of fault diagnosis technique for planetary gearboxes[J]. Journal of Mechanical Engineering,2011,47(19): 59-67. (in Chinese doi: 10.3901/JME.2011.19.059LEI Yaguo, HE Zhengjia, LIN Jing, et al. Research advances of fault diagnosis technique for planetary gearboxes[J]. Journal of Mechanical Engineering, 2011, 47(19): 59-67. (in Chinese) doi: 10.3901/JME.2011.19.059 [4] 冯志鹏,褚福磊. 行星齿轮箱齿轮分布式故障振动频谱特征[J]. 中国电机工程学报,2013,33(2): 118-125,21. FENG Zhipeng,CHU Fulei. Vibration spectral characteristics of distributed gear fault of planetary gearboxes[J]. Proceedings of the CSEE,2013,33(2): 118-125,21. (in ChineseFENG Zhipeng, CHU Fulei. Vibration spectral characteristics of distributed gear fault of planetary gearboxes[J]. Proceedings of the CSEE, 2013, 33(2): 118-125, 21. (in Chinese) [5] HAN Minghong,PAN Jiali. A fault diagnosis method combined with LMD,sample entropy and energy ratio for roller bearings[J]. Measurement,2015,76: 7-19. doi: 10.1016/j.measurement.2015.08.019 [6] WU Huachun,ZHOU Jian,XIE Chunhu,et al. Two-dimensional time series sample entropy algorithm: applications to rotor axis orbit feature identification[J]. Mechanical Systems and Signal Processing,2021,147: 107123. doi: 10.1016/j.ymssp.2020.107123 [7] 杨大为,冯辅周,赵永东,等. VMD样本熵特征提取方法及其在行星变速箱故障诊断中的应用[J]. 振动与冲击,2018,37(16): 198-205. YANG Dawei,FENG Fuzhou,ZHAO Yongdong,et al. A VMD sample entropy feature extraction method and its application in planetary gearbox fault diagnosis[J]. Journal of Vibration and Shock,2018,37(16): 198-205. (in ChineseYANG Dawei, FENG Fuzhou, ZHAO Yongdong, et al. A VMD sample entropy feature extraction method and its application in planetary gearbox fault diagnosis[J]. Journal of Vibration and Shock, 2018, 37(16): 198-205. (in Chinese) [8] 雷春丽,曹鹏瑶,崔攀,等. 样本熵和VMD结合的轴承早期故障预测方法[J]. 机械设计与制造,2022(6): 300-304. LEI Chunli,CAO Pengyao,CUI Pan,et al. An early failure prediction method based on sample entropy and variational modal decomposition[J]. Machinery Design & Manufacture,2022(6): 300-304. (in ChineseLEI Chunli, CAO Pengyao, CUI Pan, et al. An early failure prediction method based on sample entropy and variational modal decomposition[J]. Machinery Design & Manufacture, 2022(6): 300-304. (in Chinese) [9] 刘建昌,权贺,于霞,等. 基于参数优化VMD和样本熵的滚动轴承故障诊断[J]. 自动化学报,2022,48(3): 808-819. LIU Jianchang,QUAN He,YU Xia,et al. Rolling bearing fault diagnosis based on parameter optimization VMD and sample entropy[J]. Acta Automatica Sinica,2022,48(3): 808-819. (in ChineseLIU Jianchang, QUAN He, YU Xia, et al. Rolling bearing fault diagnosis based on parameter optimization VMD and sample entropy[J]. Acta Automatica Sinica, 2022, 48(3): 808-819. (in Chinese) [10] COSTA M,GOLDBERGER A L,PENG C K. Multiscale entropy analysis of complex physiologic time series[J]. Physical Review Letters,2002,89(6): 068102. doi: 10.1103/PhysRevLett.89.068102 [11] 郑近德,潘海洋,张俊,等. 基于多变量多尺度模糊熵的行星齿轮箱故障诊断[J]. 振动与冲击,2019,38(6): 187-193. ZHENG Jinde,PAN Haiyang,ZHANG Jun,et al. Multivariate multiscale fuzzy entropy based planetary gearbox fault diagnosis[J]. Journal of Vibration and Shock,2019,38(6): 187-193. (in ChineseZHENG Jinde, PAN Haiyang, ZHANG Jun, et al. Multivariate multiscale fuzzy entropy based planetary gearbox fault diagnosis[J]. Journal of Vibration and Shock, 2019, 38(6): 187-193. (in Chinese) [12] 董治麟,郑近德,潘海洋,等. 一种时移多尺度排列熵与ELM相结合的滚动轴承故障诊断方法[J]. 机械科学与技术,2021,40(10): 1523-1529. DONG Zhilin,ZHENG Jinde,PAN Haiyang,et al. A rolling bearing fault diagnosis method of time-shifted multi-scale permutation entropy combining with ELM[J]. Mechanical Science and Technology for Aerospace Engineering,2021,40(10): 1523-1529. (in ChineseDONG Zhilin, ZHENG Jinde, PAN Haiyang, et al. A rolling bearing fault diagnosis method of time-shifted multi-scale permutation entropy combining with ELM[J]. Mechanical Science and Technology for Aerospace Engineering, 2021, 40(10): 1523-1529. (in Chinese) [13] 王振亚,姚立纲. 广义精细复合多尺度样本熵与流形学习相结合的滚动轴承故障诊断方法[J]. 中国机械工程,2020,31(20): 2463-2471. WANG Zhenya,YAO Ligang. Rolling bearing fault diagnosis method based on generalized refined composite multiscale sample entropy and manifold learning[J]. China Mechanical Engineering,2020,31(20): 2463-2471. (in ChineseWANG Zhenya, YAO Ligang. Rolling bearing fault diagnosis method based on generalized refined composite multiscale sample entropy and manifold learning[J]. China Mechanical Engineering, 2020, 31(20): 2463-2471. (in Chinese) [14] 吴守军,陈健,冯辅周,等. 改进的熵特征在行星齿轮裂纹故障识别中的应用[J]. 西安交通大学学报,2021,55(6): 61-68. WU Shoujun,CHEN Jian,FENG Fuzhou,et al. An application of improved entropy feature in crack fault identification of planetary gear[J]. Journal of Xi’an Jiaotong University,2021,55(6): 61-68. (in ChineseWU Shoujun, CHEN Jian, FENG Fuzhou, et al. An application of improved entropy feature in crack fault identification of planetary gear[J]. Journal of Xi’an Jiaotong University, 2021, 55(6): 61-68. (in Chinese) [15] 李海平,赵建民,张鑫,等. 行星齿轮箱齿轮磨损故障诊断[J]. 振动与冲击,2019,38(23): 84-89,125. LI Haiping,ZHAO Jianmin,ZHANG Xin,et al. Fault diagnosis for gear wear of planetary gearbox[J]. Journal of Vibration and Shock,2019,38(23): 84-89,125. (in ChineseLI Haiping, ZHAO Jianmin, ZHANG Xin, et al. Fault diagnosis for gear wear of planetary gearbox[J]. Journal of Vibration and Shock, 2019, 38(23): 84-89, 125. (in Chinese) [16] 黄宇斐,石新发,贺石中,等. 一种基于主成分分析与支持向量机的风电齿轮箱故障诊断方法[J]. 热能动力工程,2022,37(10): 175-181. HUANG Yufei,SHI Xinfa,HE Shizhong,et al. A fault diagnosis method of wind turbine gearbox based on PCA and SVM[J]. Journal of Engineering for Thermal Energy and Power,2022,37(10): 175-181. (in ChineseHUANG Yufei, SHI Xinfa, HE Shizhong, et al. A fault diagnosis method of wind turbine gearbox based on PCA and SVM[J]. Journal of Engineering for Thermal Energy and Power, 2022, 37(10): 175-181. (in Chinese) [17] 郑近德,刘涛,孟瑞,等. 基于广义复合多尺度排列熵与PCA的滚动轴承故障诊断方法[J]. 振动与冲击,2018,37(20): 61-66. ZHENG Jinde,LIU Tao,MENG Rui,et al. Generalized composite multiscale permutation entropy and PCA based fault diagnosis of rolling bearings[J]. Journal of Vibration and Shock,2018,37(20): 61-66. (in ChineseZHENG Jinde, LIU Tao, MENG Rui, et al. Generalized composite multiscale permutation entropy and PCA based fault diagnosis of rolling bearings[J]. Journal of Vibration and Shock, 2018, 37(20): 61-66. (in Chinese) [18] 但长林,李三雁,张彬. 基于样本熵和SVM的滚动轴承故障诊断方法研究[J]. 中国测试,2020,46(11): 37-42. DAN Changlin,LI Sanyan,ZHANG Bin. Research on fault diagnosis method for rolling element bearings based on sample entropy and SVM[J]. China Measurement & Test,2020,46(11): 37-42. (in ChineseDAN Changlin, LI Sanyan, ZHANG Bin. Research on fault diagnosis method for rolling element bearings based on sample entropy and SVM[J]. China Measurement & Test, 2020, 46(11): 37-42. (in Chinese) -