Application of ELMD Entropy Feature Fusion and PSO-SVM in Gear Fault Diagnosis
-
摘要: 提出基于ELMD熵特征融合与PSO-SVM的齿轮故障诊断方法。该方法首先对原始信号进行总体局部均值分解（Ensemble local mean decomposition，ELMD），得到若干乘积函数（PF）；其次，对ELMD分解得到的前5个PF分量进行求取能量熵和近似熵，并利用KPCA对其进行特征融合；然后，选取部分融合特征作为训练样本，其余作为测试样本；最后，利用PSO优化的支持向量机对融合特征样本进行训练与测试。实验中，将单特征和融合特征分别进行SVM和PSO-SVM识别精度的对比。实验结果证明，所提方法可有效地应用在齿轮故障诊断中。Abstract: A gear fault diagnosis method based on ELMD entropy feature fusion and PSO-SVM is proposed in this paper. Firstly, the original signal is decomposed by ensemble local mean decomposition (ELMD), and several product functions (PF) are obtained. Secondly, the energy entropy and approximate entropy of the first five PF components obtained by ELMD decomposition were obtained and characterized by KPCA. Then, some of the fusion features are selected as training samples, the rest as test samples; finally, the PSO-optimized support vector machine is used to train and test the fusion feature samples. In the experiment, the singular and fusion features are compared with the recognition accuracy of SVM and PSO-SVM respectively. Experimental results show that the proposed method can be effectively applied in gear fault diagnosis.
-
Key words:
- ELMD /
- PSO /
- support vector machine /
- energy entropy /
- fault diagnosis
-
表 1 齿轮断齿故障信号的不同PF分量下ELMD熵值
PF ELMD近似熵 ELMD能量熵 PF1 0.436 8 0.453 0 0.429 8 0.425 3 0.442 5 0.032 7 0.022 3 0.048 3 0.030 8 0.045 9 PF2 0.272 9 0.281 2 0.265 9 0.266 0 0.266 8 0.470 4 0.423 7 0.501 2 0.464 2 0.494 3 PF3 0.195 9 0.190 5 0.212 6 0.201 7 0.175 0 0.178 1 0.192 4 0.220 2 0.194 6 0.254 6 PF4 0.070 8 0.041 5 0.071 9 0.079 8 0.081 1 0.090 7 0.180 7 0.099 4 0.093 8 0.116 5 C 0.023 3 0.033 5 0.019 5 0.027 0 0.034 4 0.029 3 0.042 1 0.043 6 0.023 2 0.029 9 
下载: 导出CSV
表 2 PSO-SVM识别精度结果
项目 断齿 磨损 缺齿 齿根裂纹 正常 样本标签 1 2 3 4 5 训练样本 25 25 25 25 25 测试样本 15 15 15 15 15 单特征 & SVM/% 88.3 86.2 78 93 80 单特征 & PSO-SVM/% 96.6 95 97 100 98 KPCA融合特征 & SVM/% 100 97 98 100 95 KPCA融合特征 & PSO-SVM/% 100 98 100 100 100
下载: 导出CSV
-
[1] 戴桂平.基于EMD近似熵和LS-SVM的机械故障智能诊断[J].机械强度, 2011, 33(2):165-169 http://d.old.wanfangdata.com.cn/Periodical/jxqd201102002Dai G P. Mechanicalfault intelligent diagnosis based on EMD-approximate entropy and LS-SVM[J]. Journal of Mechanical Strength, 2011, 33(2):165-169(in Chinese) http://d.old.wanfangdata.com.cn/Periodical/jxqd201102002 [2] 张超, 陈建军.基于LMD近似熵和支持向量机的轴承故障诊断[J].机械科学与技术, 2012, 31(9):1539-1542, 1548 http://journals.nwpu.edu.cn/jxkxyjs/CN/abstract/abstract5585.shtmlZhang C, Chen J J. Diagnosing faults of bearings with LMD approximate entropy and SVM[J]. Mechanical Science and Technology for Aerospace Engineering, 2012, 31(9):1539-1542, 1548(in Chinese) http://journals.nwpu.edu.cn/jxkxyjs/CN/abstract/abstract5585.shtml [3] Yang Y, Cheng J S, Zhang K. An ensemble local means decomposition method and its application to local rub-impact fault diagnosis of the rotor systems[J]. Measurement, 2012, 45(3):561-570 doi: 10.1016/j.measurement.2011.10.010 [4] 张超, 陈建军, 杨立东, 等.奇异值熵和支持向量机的齿轮故障诊断[J].振动、测试与诊断, 2011, 31(5):600-604 doi: 10.3969/j.issn.1004-6801.2011.05.014Zhang C, Chen J J, Yang L D, et al. Fault diagnosis of gear based on EEMD entropy of singular values and support vector machine[J]. Journal of Vibration, Measurement & Diagnosis, 2011, 31(5):600-604(in Chinese) doi: 10.3969/j.issn.1004-6801.2011.05.014 [5] 张曹, 陈珺, 刘飞.基于EMD近似熵和TWSVM的齿轮箱故障诊断[J].煤矿机械, 2017, 38(4):142-145 http://d.old.wanfangdata.com.cn/Periodical/mkjx201704051Zhang C, Chen J, Liu F. Gearbox fault diagnosis based on EMD-approximate entropy and TWSVM[J]. Coal Mine Machinery, 2017, 38(4):142-145(in Chinese) http://d.old.wanfangdata.com.cn/Periodical/mkjx201704051 [6] 向丹, 岑健.基于EMD熵特征融合的滚动轴承故障诊断方法[J].航空动力学报, 2015, 30(5):1149-1155 http://d.old.wanfangdata.com.cn/Periodical/hkdlxb201505016Xiang D, Cen J. Method of roller bearing fault diagnosis based on feature fusion of EMD entropy[J]. Journal of Aerospace Power, 2015, 30(5):1149-1155(in Chinese) http://d.old.wanfangdata.com.cn/Periodical/hkdlxb201505016 [7] 刘志强, 姜万录, 谭文振, 等.基于多特征融合多核学习支持向量机的液压泵故障识别方法[J].中国机械工程, 2016, 27(24):3355-3361 doi: 10.3969/j.issn.1004-132X.2016.24.016Liu Z Q, Jiang W L, Tan W Z, et al. Fault identification method for hydraulic pumps based on multi-feature fusion and multiple kernel learning SVM[J]. China Mechanical Engineering, 2016, 27(24):3355-3361(in Chinese) doi: 10.3969/j.issn.1004-132X.2016.24.016 [8] 张伟, 白恺, 宋鹏, 等.基于VMD和奇异值能量差分谱的风机滚动轴承故障特征提取方法[J].华北电力技术, 2017(3):59-64 http://d.old.wanfangdata.com.cn/Periodical/hbdljs201703009Zhang W, Bai K, Song P, et al. Wind turbine rolling bearing fault feature extraction method based on VMD and singular value energy difference spectrum[J]. North China Electric Power, 2017(3):59-64(in Chinese) http://d.old.wanfangdata.com.cn/Periodical/hbdljs201703009 [9] 秦波, 刘永亮, 王建国, 等.基于K-L散度与PSO-SVM的齿轮故障诊断[J].现代制造工程, 2017, 39(3):24-30 http://d.old.wanfangdata.com.cn/Periodical/jxgys201703006Qin B, Liu Y L, Wang J G, et al. The gear fault diagnosis based on K-L divergence and PSO-SVM[J]. Modern Manufacturing Engineering, 2017, 39(3):24-30(in Chinese) http://d.old.wanfangdata.com.cn/Periodical/jxgys201703006 [10] 王建国, 陈帅, 张超.噪声参数最优ELMD与LS-SVM在轴承故障诊断中的应用于与研究[J].振动与冲击, 2017, 36(5):72-78, 86 http://www.cnki.com.cn/Article/CJFDTOTAL-ZDCJ201705012.htmWang J G, Chen S, Zhang C. Application of noise parametric optimization with ELMD and LS-SVM in bearing fault diagnosis[J]. Journal of Vibration and Shock, 2017, 36(5):72-78, 86(in Chinese) http://www.cnki.com.cn/Article/CJFDTOTAL-ZDCJ201705012.htm [11] 曾旭, 慕晓冬, 王舒洋, 等.基于LMD频域近似熵频谱感知算法研究[J].火力与指挥控制, 2017, 42(5):47-51 doi: 10.3969/j.issn.1002-0640.2017.05.011Zeng X, Mu X D, Wang S Y, et al. LMD frequency domain approximate entropy-based spectrum sensing algorithm[J]. Fire Control & Command Control, 2017, 42(5):47-51(in Chinese) doi: 10.3969/j.issn.1002-0640.2017.05.011 [12] 徐乐, 邢邦圣, 郎超男, 等.LMD能量熵和SVM相结合的滚动轴承故障诊断[J].机械科学与技术, 2017, 36(6):915-918 http://journals.nwpu.edu.cn/jxkxyjs/CN/abstract/abstract6738.shtmlXu L, Xing B S, Lang C N, et al. Fault diagnosis of rolling bearing combined LMD energy entropy and SVM[J]. Mechanical Science and Technology for Aerospace Engineering, 2017, 36(6):915-918(in Chinese) http://journals.nwpu.edu.cn/jxkxyjs/CN/abstract/abstract6738.shtml [13] Štimac G, Braut S, Žigulić R. Comparative analysis of PSO algorithms for PID controller tuning[J]. Chinese Journal of Mechanical Engineering, 2014, 27(5):928-936 doi: 10.3901/CJME.2014.0527.302 [14] 肖健华, 樊可清, 吴今培, 等.应用于故障诊断的SVM理论研究[J].振动、测试与诊断, 2001, 21(4):258-262 http://cdmd.cnki.com.cn/Article/CDMD-10704-2007046299.htmXiao J H, Fan K Q, Wu J P, et al. A study on SVM for fault diagnosis[J]. Journal of Vibration, Measurement & Diagnosis, 2001, 21(4):258-262(in Chinese) http://cdmd.cnki.com.cn/Article/CDMD-10704-2007046299.htm [15] 王红军, 徐小力, 张建民.设备状态趋势的SVM预示技术研究[J].机械科学与技术, 2006, 25(4):379-381 doi: 10.3321/j.issn:1003-8728.2006.04.001Wang H J, Xu X L, Zhang J M. Support vector machine condition trend prediction technology[J]. Mechanical Science and Technology, 2006, 25(4):379-381(in Chinese) doi: 10.3321/j.issn:1003-8728.2006.04.001 -
点击查看大图
图(9) / 表(2)
计量
- 文章访问数: 423
- HTML全文浏览量: 126
- PDF下载量: 28
- 被引次数: 0
