【摘要】：滾動(dòng)軸承是旋轉(zhuǎn)機(jī)械中使用最為廣泛和最易受損的零部件之一,其工作狀態(tài)直接影響到旋轉(zhuǎn)機(jī)械系統(tǒng)的性能,對(duì)其進(jìn)行故障診斷具有重要的實(shí)際應(yīng)用意義。由于滾動(dòng)軸承運(yùn)行時(shí)產(chǎn)生的振動(dòng)信號(hào)是典型的非平穩(wěn)隨機(jī)信號(hào),從振動(dòng)信號(hào)中提取能準(zhǔn)確反映軸承運(yùn)行狀態(tài)的故障特征是故障診斷的關(guān)鍵。 自回歸(AR)參數(shù)模型是時(shí)序分析方法中最基本、實(shí)際應(yīng)用最廣的時(shí)序模型,但AR模型分析信號(hào)是建立在隨機(jī)平穩(wěn)性的假設(shè)基礎(chǔ)上,無(wú)法準(zhǔn)確分析滾動(dòng)軸承非平穩(wěn)隨機(jī)信號(hào)。為此,論文提出一種基于經(jīng)驗(yàn)?zāi)B(tài)分解(EMD)和AR模型相結(jié)合的滾動(dòng)軸承故障特征提取方法。該方法用EMD分解將滾動(dòng)軸承振動(dòng)信號(hào)分解為若干內(nèi)稟模態(tài)函數(shù)(IMF),采用相關(guān)分析提取前五個(gè)IMF分量建立AR模型,提取模型的參數(shù)和殘差的方差的奇異值作為反映滾動(dòng)軸承運(yùn)行狀態(tài)的特征向量。實(shí)驗(yàn)結(jié)果表明該方法提取特征精度較高,效果較好。 為克服EMD分解信號(hào)精度不高的問(wèn)題,論文利用小波包分解(WPD)具有良好的時(shí)頻局部化特性和多分辨率的特征,將非平穩(wěn)振動(dòng)信號(hào)轉(zhuǎn)化為平穩(wěn)信號(hào)的基礎(chǔ)上,把振動(dòng)信號(hào)分解到各個(gè)頻段中使AR模型能有效跟蹤信號(hào),提出了基于小波包自回歸(WPD_AR)參數(shù)模型和小波包時(shí)變自回歸(WPD_TVAR)參數(shù)模型的兩種滾動(dòng)軸承故障特征提取方法。首先對(duì)滾動(dòng)軸承振動(dòng)信號(hào)進(jìn)行小波包分解,然后對(duì)分解得到的各結(jié)點(diǎn)系數(shù)分別建立AR模型和TVAR模型,分別提取WPD_AR模型和WPD_TVAR模型的參數(shù)奇異值作為反映滾動(dòng)軸承運(yùn)行狀態(tài)的特征向量。實(shí)驗(yàn)結(jié)果表明,WPD_AR模型比EMD_AR模型故障特征提取的效果更明顯,速度更快；WPD_TVAR模型比WPD_AR模型故障特征提取的結(jié)果更準(zhǔn)確,精度更高。 將提出的三種故障特征提取方法獲取的故障特征送入支持向量機(jī)分類器進(jìn)行故障分類與診斷。實(shí)驗(yàn)表明,本文所提方法可以有效、準(zhǔn)確地識(shí)別滾動(dòng)軸承的故障狀況,驗(yàn)證了論文提出的基于非平穩(wěn)時(shí)序分析的滾動(dòng)軸承故障特征提取方法的有效性。
[Abstract]:Rolling bearing is one of the most widely used and easily damaged parts in rotating machinery. Its working state directly affects the performance of rotating machinery system. Because the vibration signal generated by rolling bearing is a typical non-stationary random signal, it is the key to fault diagnosis to extract the fault characteristics from the vibration signal which can accurately reflect the running state of the bearing. The autoregressive (AR) parameter model is the most basic and widely used time series model in time series analysis, but the AR model is based on the assumption of stochastic stationarity and can not accurately analyze the non-stationary random signals of rolling bearings. In this paper, a fault feature extraction method based on empirical mode decomposition (EMD) and AR model is proposed. In this method, the vibration signal of rolling bearing is decomposed into several intrinsic modal functions by EMD decomposition. The first five IMF components are extracted by correlation analysis to establish AR model. The singular values of the parameters of the model and the variance of the residuals are extracted as the eigenvectors to reflect the running state of the rolling bearings. The experimental results show that this method has high accuracy and good effect. In order to overcome the problem that the precision of EMD decomposition signal is not high, this paper uses wavelet packet decomposition (WPD) to have good time-frequency localization and multi-resolution characteristics, and converts the non-stationary vibration signal into stationary signal. Based on wavelet packet autoregressive (WPD_AR) parameter model and wavelet packet time-varying autoregressive (WPD_TVAR) parameter model, two fault feature extraction methods for rolling bearing are proposed. Firstly, the vibration signal of rolling bearing is decomposed by wavelet packet, then AR model and TVAR model are established for each node coefficient obtained by decomposition. The singular values of the WPD_AR model and the WPD_TVAR model are extracted as the characteristic vectors to reflect the running state of the rolling bearing. The experimental results show that the effect of fault feature extraction by WPD-AR model is more obvious than that by EMD_AR model, and the speed of fault feature extraction by WPD-VAR model is more accurate and the accuracy is higher than that by WPD_AR model. The fault features obtained by the three fault feature extraction methods are sent to the support vector machine classifier for fault classification and diagnosis. Experiments show that the proposed method can effectively and accurately identify the fault status of rolling bearings and verify the effectiveness of the fault feature extraction method proposed in this paper based on non-stationary time series analysis.
【學(xué)位授予單位】：中南大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2012
【分類號(hào)】：TH165.3

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 張國(guó)新;劉祚時(shí);;軸承早期故障的小波包-自回歸譜診斷法[J];軸承;2007年02期

2 劉樂(lè)平;林鳳濤;;基于小波包特征向量與神經(jīng)網(wǎng)絡(luò)的滾動(dòng)軸承故障診斷[J];軸承;2008年04期

3 左紅;顧家銘;于錦祿;;基于支持向量機(jī)的滾動(dòng)軸承故障診斷研究[J];軸承;2008年08期

4 方浩,周冰,薛培鼎,馮祖仁;自回歸模型的時(shí)變小波包分解[J];電子與信息學(xué)報(bào);2001年11期

5 陳季云;李娟;;基于小波包-支持向量機(jī)的滾動(dòng)軸承故障診斷[J];化工自動(dòng)化及儀表;2010年09期

6 王小平,沈玉娣;支持向量機(jī)在軸承故障診斷中的應(yīng)用[J];機(jī)床與液壓;2003年04期

7 張雄希;劉振興;;基于倒頻譜分析的電機(jī)故障檢測(cè)[J];電力系統(tǒng)保護(hù)與控制;2010年20期

8 劉志剛,李德仁,秦前清,史文中;支持向量機(jī)在多類分類問(wèn)題中的推廣[J];計(jì)算機(jī)工程與應(yīng)用;2004年07期

9 馬金山;;基于小波包和AR譜分析的滾動(dòng)軸承故障診斷[J];機(jī)械管理開(kāi)發(fā);2011年01期

10 吳虎勝;呂建新;戰(zhàn)仁軍;吳廬山;;基于EMD和AR奇異值的柴油機(jī)故障診斷[J];機(jī)械設(shè)計(jì)與制造;2011年04期

相關(guān)碩士學(xué)位論文 前4條

1 萬(wàn)良虹;基于小波分析的滾動(dòng)軸承故障診斷方法研究[D];華北電力大學(xué)（北京）;2004年

2 黃建鴻;基于小波包分析的滾動(dòng)軸承故障智能診斷[D];南昌大學(xué);2005年

3 盧一相;時(shí)頻分析在軸承故障診斷中的應(yīng)用研究[D];安徽大學(xué);2007年

4 羅志高;基于參數(shù)化模型的非平穩(wěn)特征提取及其智能診斷研究[D];天津大學(xué);2008年

，

本文編號(hào)：2166876