基于EEMD和MFFOA-SVM滚动轴承故障诊断

摘要/Abstract

摘要： 针对滚动轴承发生故障时，振动信号的时域和频域特征都会发生变化的特点，提出了基于集合经验模态分解（EEMD）、改进果蝇优化算法（MFFOA）和支持向量机（SVM）的滚动轴承故障诊断方法。该方法主要是利用EEMD方法对故障信号进行分解，并计算各IMF分量的均方根值和重心频率，以此进行归一化处理得到特征向量。为了提高诊断精度，采用果蝇优化算法优化SVM参数，建立MFFOA-SVM模型，然后对提取的特征向量进行训练与测试，从而识别故障与否及发生点蚀故障的程度。利用该方法对实测信号进行分析与诊断,并与遗传算法的优化结果进行对比，验证了该方法的有效性，说明其具有良好的应用前景。

关键词: 集合经验模态分解, 改进果蝇优化算法, 支持向量机, 滚动轴承, 故障诊断

Abstract: Both of the time domain and frequency domain of the vibration signals would be changed when rolling bearing faults occured. A rolling bearing fault diagnosis method was proposed based on EEMD, MFFOA and SVM. EEMD was used to decompose the fault signals, and to calculate the root mean square value and frequency of the center of gravity, achieving the normalization processing feature vector. In order to improve the classification accuracy rate, a MFFOA-SVM model was built, and then the feature values were extracted for training and testing, so that it might recognize the faults or not and the degree of pitting corrosion failures. The actual signals were analyzed and diagnosed, and compared with genetic algorithm optimization results, it proves the validity of the method, and the improved method has a good prospect for its applications in rolling bearing diagnosis.

Key words: ensemble empirical mode decomposition（EEMD）, modified fruit fly optimization algorithm（MFFOA）, support vector machine（SVM）, rolling bearing, fault diagnosis

中图分类号:

何青, 褚东亮, 毛新华. 基于EEMD和MFFOA-SVM滚动轴承故障诊断[J]. 中国机械工程.

He Qing, Chu Dongliang, Mao Xinhua. Study on Rolling Bearing Fault Diagnosis Based on EEMD and MFFOA-SVM[J]. China Mechanical Engineering.

参考文献

[1]丁康, 孔正国. 振动调幅调频信号的调制边频带分析及其解调方法[J]. 振动与冲击, 2006, 24(6): 9-12.

Ding Kang, Kong Zhengguo. Modulation Vibration Amplitude Modulation Frequency Modulation Signal Sideband Analysis and Demodulation Method [J]. Vibration & Shock, 2006, 24(6): 9-12.

[2]Tandon N, Choudhury A. A Review of Vibration and Acoustic Measurement Methods for the Detection of Defects in Rolling Element Bearings[J]. Tribology International, 1999, 32: 469-480.

[3]于德介, 程军圣, 杨宇. 机械故障诊断的Hilbert-Huang变换方法[M]. 北京: 科学出版社, 2006.

[4]张涛, 陆森林, 周海超, 等. 内禀模态特征能量法在滚动轴承故障模式识别中的应用[J]. 噪声与振动控制, 2011, 31(3): 125-128.

Zhang Tao, Lu Senlin, Zhou Haichao, et al. Application of Intrinsic Mode Function Feature Energy Method in Fault Pattern Recognition of Rolling Bearing[J]. Noise and Vibration Control, 2011, 31(3): 125-128.

[5]Huang E, Shen Zheng, Long S R, et al. The Empirical Mode Decomposition and the Hilbert Spectrum for Nonlinear and Non- stationary Time Series Analysis [J]. Proc. R. Soc. Lond. A , 1998, 454(12): 903-995.

[6]张俊红, 李林洁, 马文朋，等. EMD-ICA联合降噪在滚动轴承故障诊断中的应用[J]. 中国机械工程, 2013, 24（11）: 1468-1472.

Zhang Junhong, Li Linjie, Ma Wenpeng, et al. Application of EMD-ICA to Fault Diagnosis of Rolling Bearing[J]. China Mechanical Engineering, 2013, 24(11): 1468-1472.

[7]孟宗,李姗姗. 基于小波半软阈值和EMD的旋转机械故障诊断[J]. 中国机械工程,2013,24（10）:1279-1283.

Meng Zong, Li Shanshan. Research on Fault Diagnosis for Rotating Machinery Based on Semi-soft Wavelet Threshold and EMD[J]. China Mechanical Engineering, 2013, 24(10): 1279-1283.

[8]潘文超. 果蝇最佳佳演化算法[M]. 台北: 沧海书局, 2011. [9]Li H, Guo S, Zhao H, et al. Annual Electric Load Forecasting by a Least Squares Support Vector Machine with a Fruit Fly Optimization Algorithm[J]. Energies, 2012,5(11): 4430-4445.

[10]Li H Z, Guo S, Li C J, et al. A Hybrid Annual Power Load Forecasting Model Based on Generalized Regression Neural Network with Fruit Fly Optimization Algorithm[J]. Knowledge-Based Systems, 2013, 37, 378-387.

[11]牛培峰, 麻红波, 李国强, 等. 基于支持向量机和果蝇优化算法的循环流化床锅炉NOx排放特性研究[J]. 动力工程学报, 2013, 33(4): 267-271.

Niu Peifeng, Ma Hongbo, Li Guogiang, et al. Study on Nox Emission from CFB Boilers Based on Support Vector Machine and Fruit Fly Optimization Algorithm[J]. Journal of Chinese Society of Power Engineering, 2013, 33(4): 267-271.

[12]章永来, 史海波, 周晓峰, 等. 基于统计学习理论的支持向量机预测模型[J]. 统计与决策, 2014(5): 72-74.

Zhang Yonglai, Shi Haibo, Zhou Xiaofeng, et al. Support Vector Machine Prediction Model Based on Statistical Learning Theory[J]. Statistics and Decision, 2014(5): 72-74.

[13]杨金芳, 翟永杰, 王东风, 等. 基于支持向量回归的时间序列预测[J]. 中国电机工程学报, 2005, 25(17): 110-114.

Yang Jinfang, Zhai Yongjie, Wang Dongfeng, et al. Time Series Prediction Based on Support Vector Regression[J]. Proceedings of the CSEE, 2005, 25(17): 110-114.

[14]谢宏, 魏江平, 刘鹤立. 短期负荷预测中支持向量机模型的参数选取和优化方法[J]. 中国电机工程学报, 2006, 26(22): 17-22.

Xie Hong, Wei Jiangping, Liu Heli. Parameter Selection and Optimization Method of SVM Model for Short-term Load Forecasting[J]. Proceedings of the CSEE, 2006, 26(22): 17-22.

[15]丁世飞, 齐丙娟, 谭红艳. 支持向量机理论与算法研究综述[J]. 电子科技大学学报, 2011(1): 2-10.

Ding Shifei, Qi Bingjuan, Tan Hongyan. An Overview on Theory and Algorithm of Support Vector Machines[J]. Journal of University of Electronic Science and Technology, 2011(1): 2-10.

[16]叶林, 刘鹏. 基于经验模态分解和支持向量机的短期风电功率组合预测模型[J]. 中国电机工程学报, 2011, 31(31): 102-108.

Ye Lin, Liu Peng. Combined Model Based on EMD-SVM for Short-term Wind Power Prediction [J]. Proceedings of the CSEE, 2011, 31(31): 102-108.

[17]Zhang J, Wang R, Li J, et al. Fruit Fly Optimization Based Least Square Support Vector Regression for Blind Image Restoration[C]// International Symposium on Optoelectronic Technology and Application 2014. Beijing: International Society for Optics and Photonics, 2014: 93011W-93011W-8.

[18]Loparo K A. The Case Western Reserve University Bearing Data Center[EB/OL]. [2012-11-15]. http: //csegroups. ase.edu/hearing data center/ pages/ download-data-file.

[19]Ren Y, Suganthan P N, Srikanth N. A Comparative Study of Empirical Mode Decomposition-based Short-term Wind Speed Forecasting Methods[J]. Sustainable Energy, 2015, 6(1): 236-244.

[20]Yang C Y, Wu T Y. Diagnostics of Gear Deterioration Using EEMD Approach and PCA Process[J]. Measurement, 2015, 61: 75-87.