非趋势波动分析用于齿轮故障识别时常采用标度指数作为特征量，该特征量容易导致齿轮故障模式间存在混叠。根据对数尺度波动函数图，将标度指数与表征信号强度的截距组成齿轮振动信号的特征向量。根据齿轮振动信号的双标度性，提出滑动加窗算法，实现标度指数的自适应提取，并结合神经网络算法进行故障分类。设计单级齿轮减速器的实验平台，并采集齿轮的径向振动信号进行自适应非趋势波动分析，研究表明，该方法能够提高标度指数的提取精度和提取效率。
Abstract
Scaling exponent is often used as the feature quantity for gear fault identification in detrended fluctuation analysis (DFA), but it easily leads to this problem that aliasing is emerged in among the gear failure modes. According to a logarithmic scale wave function diagram, the scaling exponents and the intercept of characterization of signal intensity were combined to a feature vector of gear vibration signal. According to a dual of gear vibration signal, sliding windowing algorithm was projected to extract adaptive scaling exponent, and used for fault classification combining with neural network algorithm. Studies show that the method can improve the extraction accuracy and extraction efficiency of the scaling exponent.
关键词
非趋势波动分析 /
标度指数 /
长程相关性 /
聚类 /
神经网络
{{custom_keyword}} /
Key words
DFA /
Scaling exponent /
Long-range correlation /
Clustering /
Neural Network
{{custom_keyword}} /
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] 于德介,程军圣,杨宇. Hilbert-Huang 变换在齿轮故障诊断中的应用[J]. 机械工程学报,2005,41(6):102-107.
CHEN Xiangmin，YU Dejie，LUO Jiesi. Gear tooth fault diagnosis by using order cyclostationary demodulating approach based on chirplet path pursuit[J]. Journal of
Mechanical Engineering，2012，48(3)：95-101.
[2] 陈向民,于德介,罗洁思. 基于线调频小波路径追踪阶比循环平稳解调的齿轮故障诊断[J]. 机械工程学报, 2012,48(3):95-101.
CHEN Xiangmin,YU Dejie,LUO Jiesi. Gear tooth fault diagnosis by using order cyclostationary demodulatingapproach based on chirplet path pursuit[J]. Journal of Mechanical
Engineering,2012,48(3):95-101.
[3] 吕勇,李友荣,徐金梧. 延时矢量方差算法及其在齿轮故障识别中的应用[J]. 振动与冲击,2006,(25)6:59-61
LV LI Yourong,XU Jinwu, Delay Vector Variance Method and Its Application to Gear Fault Diagnosis[J]. Vibration and Shock
[4] C K Peng, S V Buldyrev, A L Gold berger,etc. Long-range correlations in nucleotide sequences
[5] 张淑清,翟欣沛,刘永富,唐佰文,赵玉春等,滑动去趋势波动分析在电能质量暂态扰动检测中的应用[J].电力系统自动化2012.30（8）:52-57.
ZHANG Shuqing， ZHAI Xinpei， LIU Yongfu， TANG Baiwen， ZHAO Yuchun.Application of Sliding Detrended Fluctuation Analysis in Detection of Transient Power Quality
Disturbances[J].Automation of Electric Power Systems,2012,36(8):52-57.
[6] Fractal and nonlinear changes in the long-term baseline fluctuations of fetal heart rat
[7] 李力,彭中笑,彭书志. 去趋势波动分析在齿轮故障诊断中的应用研究[J]. 中国机械工程,2009,20(19): 2311-2314.
LI Li,PENG Zhongxiao,PENG Shuzhi. Detrended fluctuation analysis for gear fault diagnosis[J]. China Mechanical Engineering,2009,20(19):2311-2314.
[8] 何文平. 动力学结构突变检测方法的研究及其应用[D].兰州:兰州大学,2008.
HE Wenping. The research and application of the abruptdetecting methods in dynamical structures[D]. Lanzhou: Lanzhou University,2008.
[9] 林近山,陈前.基于非平稳时间序列双标度指数特征的齿轮箱故障诊断.机械工程学报,2012,43（13）:108-114.
LIN Jinshan,CHEN Qian, Fault Diagnosis of Gearboxes Based on the Double-scaling-exponent Characteristic of Nonstationary Time Series[J]. Journal of Mechanical Engineering. 2012,43（13）:108-114.
[10]夏志明,郭鹏江,赵文芝等.IV模型中变点检测的 Cramer-VonMises方法[J].西北大学学报.2010.40(1):6-8.
XIA Zhinming,GUO Pengjiang,ZHAO Wenzhi.Cramer-von Mises method in detecting change points in IV models[J].Journal of Northwest University. 2010.40(1):6-8.
[11] 郭建英,周源泉等.可靠性增长突变点辨识与MIL-HDBK-189[J].方法与应用.1998.1:30-32
GUO Jianying,ZHOU Yuanquan. Reliability Growth mutations identified with MIL-HDBK-189[J]. Methods and Applications. 1998.1:30-32
{{custom_fnGroup.title_cn}}
脚注
{{custom_fn.content}}
PDF(1238 KB)
