针对轴承振动信号的非平稳特征和现实中难以提取故障参数的情况,提出了一种基于图像的轴承故障诊断方法即基于递归灰度图(Improved Recurrence Plots,IRP)和双向二维主成分分析(Two directional, Two dimensional Principal Component Analysis,TD2DPCA)的轴承故障诊断法。该方法首先对递归图(Recurrence Plots,RP)中阈值选取的问题进行了优化,提出了IRP算法,对采集到的轴承振动信号进行IRP分析,生成递归灰度图;然后用TD2DPCA对生成的递归灰度图进行特征参数提取,得到系数编码矩阵;最后采用分类器对上述编码矩阵直接进行模式识别,以实现轴承故障的自动化诊断。将该方法应用在轴承4种典型工况的故障诊断实例中,识别率高达99.8%,结果表明:基于IRP和TD2DPCA的轴承故障诊断方法能够自适应的对轴承进行故障诊断,具有故障识别精度高、噪声鲁棒性好等优点,为轴承振动诊断探索了一条新途径。
Abstract
The vibration signals of bearings are usually non-stationary and it is difficult to extract the fault parameters in reality. Therefore we propose a fault diagnosis method that uses the Improved Recurrence Plots(IRP) and Two directional, Two dimensional Principal Component Analysis(TD2DPCA). Firstly, for Recurrence Plots(RP) threshold selection problem, IRP is proposed, then using IRP to bearing vibration acceleration signals to obtain IRP images; on this basis, to get parameters code matrixes, TD-2DPCA is used to bearing IRP images; finally using the classifier to the code matrix for pattern recognition in order to realize the automatic diagnosis of bearing IRP images. The proposed method is used in the four kinds of bearing vibration signals, the fault diagnosis accuracy up to 100%, the results showed that: the roller bearing fault diagnosis method using IRP and TD2DPCA has ability of adaptive bearing fault diagnosis, has good recognition accuracy and noise robustness, explored a new way for the bearing vibration diagnosis.
关键词
轴承 /
递归图 /
递归灰度图 /
双向二维主成分分析 /
故障诊断.
{{custom_keyword}} /
Key words
Bearing /
Recurrence Plots /
Improved Recurrence Plots /
Two directional Two dimensional Principal Component Analysis /
Fault Diagnosis.
{{custom_keyword}} /
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] 唐贵基,王晓龙. 参数优化变分模态分解方法在滚动轴承早期故障诊断中的应用[J].西安交通大学学报,2015,49(5):73-80.
TANG Guiji, WANG Xiaolong. Parameter Optimized Variational Mode Decomposition Method with Application to Incipient Fault Diagnosis of Rolling Bearing[J].Journal of Xi’an JiaoTong University, 2015,49(5):73-80.
[2] 丁建明,林建辉,任愈,等. 基于谐波小波包能量熵的轴承故障实时诊断[J] .机械强度,2011,33(4):483-487.
Ding JianMing, Lin Jianhui, Ren Yu,et al.I.C. REAL-TIME DIAGNOSIS OF BEARING FAULTS BASED ON HARMONIC WAVELET ENERGY ENTROPY [J]. Journal of Mechanical Strengh, 2011,33(4):483-487.
[3] 李学军,何能胜,何宽芳. 基于小波包近似熵和SVM的圆柱滚子轴承诊断[J]. 振动、测试与诊断,2015, 35(6): 1031-1036.
Li Xuejun, He Nengsheng, He Kuanfang. Cylindrical Roller Bearing Diagnosis Based on Wavelet Packet Approximate Entropy and Support Vector Machines [J]. Journal of Vibration, Measurement&Diagnosis, 2011, 35(6): 1031-1036.
[4] 程发斌,汤宝平,刘文艺. 一种抑制维格纳分布交叉项的方法及在故障诊断中应用[J]. 中国机械工程,2008,19(14)1727-1731.
Cheng Fabin,Tang Baoping,Liu Wenyi. A Method to Suppress Cross- terms of Wigner- Ville Distribution and
Its Application in Fault Diagnosis [J]. China Mechanical Engineering, 2008,19(14)1727-1731.
[5] 蔡艳平,李艾华,石林锁,等. 基于EMD与谱峭度的滚动轴承故障检测改进包络谱分析[J].振动与冲击, 2011,30(2) : 167-172.
Cai Yanping, Li Aihua, Shi Linsuo,et al.Roller bearing fault detection using improved envelope spectrum analysis based on EMD and spectrum kurtosis[J]. Journal of Vibration and Shock, 2011,30(2):167-172.
[6] ECKMANN J P, KAMPHORST S O, RUELLE D. Recurrence Plots of Dynamical Systems [J]. Europhys Lett, 1987, 5: 973 - 977.
[7] 蒲晓川,肖涵. 基于EMD降噪的递归图分析方法在齿轮故障诊断中的应用[J].机床与液压, 2015,43(5) : 160-163.
Pu Xiaochuan, Xiao Han. Application of Recurrence Plot Analysis Method to Fault Diagnosis Based on EMD [J]. MACHINE TOOL & HYDRAULICS, 2015,43(5):160-163.
[8]潘玉荣,贾朝勇.基于递归图的电价信号复杂度描述[J]. 洛阳师范学院学报,2013,32(2):11-16.
Pan Yurong, Jia Chaoyong. Complexity Description of Power Price Signals Based onMethods of Recurrence Plots [J]. Journal of Luoyang Normal University, 2013, 32(2): 11-16.
[9]刘秉正,彭建华.非线性动力学[M].北京:高等教育出版社,2003
Liu Bingzheng, Peng Jianhua. Nonlinear Dynamics[M]. Bei Jing: China Higher Education Press, 2003.
[10] 关贞珍,郑海起,杨云涛等.某型滚动轴承故障与分形维数的确定[J].机械科学与技术,2009,28 (9):1147-1152.
Guan Zhenzhen, Zheng Haiqi, Yang Yuntao, et al. Fault Diagnosis of a Bearing Based on Chaos and Fractal Theory[J]. Mechanical Science and Technology for Aerospace Engineering, 2015,35 (3):499-506.
[11]夏勇,薛扬,罗晓春,等. 内燃机振动信号复杂度的定性描述[J]. 机械,2003,30(4):51-53.
Xia Yong, Xue Yang, Luo Xiaochun,et al. Qualitative description for the vibration signals of internal combustion engines [J]. Machine, 2003, 30(4): 51-53.
[12]张淑清,包红燕,李盼,等. 基于RQA与GG聚类的滚动轴承故障识别[J]. 中国机械工程,2015,26(10):1384-1389.
Zhang Shuqing, Bao Hongyan, Li Pan,et al. Fault Diagnosis of Rolling Bearings Based on RQA and GG Clustering [J]. The Chinese Mechanical Engineering, 2015, 26(10): 1384-1389.
[13] Zhang Daoqiang, Zhou Zhihua. (2D) 2PCA: Tow-directional Tow-dimensional PCA for Efficient Face Representation and Recognition[J]. Neuro computing, 2005, 69(1-3): 224-231.
[14] Jian Yang,Zhang D,Frangi A F,et al. Two-dimensional PCA: a new approach to appearance-based face representation and recognition[J].Pattern Analysis and Machine Intelligence, 2004, 26(1):131-137.
[15] 李巍华,林龙,单外平.基于广义S变换与双向2DPCA的轴承故障诊断[J].振动、测试与诊断,2015,35 (3):499-506.
LI Wei-hua,LIN Long,SHAN Wai-ping.I.C. engine vibration time-frequency analysis based on EMD-Wigner-Ville[J]. Journal of Vibration, Measurement&Diagnosis, 2015,35 (3):499-506.
{{custom_fnGroup.title_cn}}
脚注
{{custom_fn.content}}