發(fā)布時(shí)間：2018-05-23 17:37

  本文選題：航空發(fā)動(dòng)機(jī)滾動(dòng)軸承 + 故障診斷　； 參考：《南京航空航天大學(xué)》2016年碩士論文

【摘要】：滾動(dòng)軸承作為航空發(fā)動(dòng)機(jī)關(guān)鍵部件直接影響著飛行安全,對(duì)滾動(dòng)軸承進(jìn)行狀態(tài)檢測(cè),盡早發(fā)現(xiàn)軸承的故障征兆,對(duì)于有效減少飛行事故的發(fā)生,實(shí)施滾動(dòng)軸承剩余壽命預(yù)測(cè)具有重要意義。現(xiàn)有的滾動(dòng)軸承狀態(tài)評(píng)估較少考慮載荷和轉(zhuǎn)速變化對(duì)軸承狀態(tài)評(píng)估的影響,缺乏對(duì)特征靈敏度的研究和融合,對(duì)早期故障檢測(cè)不靈敏,對(duì)軸承狀態(tài)評(píng)估不準(zhǔn)確,因此需要進(jìn)行變工況下多特征融合。本文研究了航空發(fā)動(dòng)機(jī)滾動(dòng)軸承在變工況狀態(tài)下的多特征提取與融合技術(shù)。主要研究工作體現(xiàn)在:(1)提出了三種多特征融合方法,即距離判別法、一類分類法和后驗(yàn)概率法。距離判別法是利用滾動(dòng)軸承運(yùn)行的正常數(shù)據(jù)的振動(dòng)特征進(jìn)行歐氏距離學(xué)習(xí),并對(duì)未知狀態(tài)與正常狀態(tài)的距離進(jìn)行比較。一類分類法是對(duì)正常數(shù)據(jù)樣本的分布做出正確的描述,檢驗(yàn)對(duì)未知樣本的分類就是檢驗(yàn)其是否服從分布。后驗(yàn)概率法是基于后驗(yàn)概率的支持向量機(jī)算法,使用正常狀態(tài)和嚴(yán)重故障狀態(tài)的樣本數(shù)據(jù),形成訓(xùn)練樣本,對(duì)后驗(yàn)概率支持向量機(jī)進(jìn)行學(xué)習(xí),既可以實(shí)現(xiàn)分類問(wèn)題,又可以結(jié)合貝葉斯決策規(guī)則實(shí)現(xiàn)分類結(jié)果的概率估計(jì)。(2)進(jìn)行滾動(dòng)軸承單點(diǎn)故障模擬試驗(yàn),得到4組振動(dòng)加速度信號(hào),從時(shí)域、頻域和時(shí)頻域中提取出了13個(gè)無(wú)量綱特征,進(jìn)行了13個(gè)特征的靈敏度分析。提取轉(zhuǎn)速信號(hào),比較了不同轉(zhuǎn)速對(duì)故障特征靈敏度的影響。利用特征融合方法,對(duì)多維特征進(jìn)行了融合,試驗(yàn)結(jié)果充分驗(yàn)證了方法的正確性。(3)進(jìn)行滾動(dòng)軸承性能退化試驗(yàn),得到航空滾動(dòng)軸承在整個(gè)從正常到異常狀態(tài)下的不同工作狀態(tài)的振動(dòng)試驗(yàn)數(shù)據(jù)。利用本文特征融合方法進(jìn)行了特征融合和狀態(tài)評(píng)估,結(jié)果證明:提取的多維特征通過(guò)融合后進(jìn)行狀態(tài)評(píng)估能明顯區(qū)分出軸承正常與異常狀態(tài),即本文的特征融合狀態(tài)評(píng)估方法有很好的工程應(yīng)用價(jià)值。
[Abstract]:As the key component of aero-engine, rolling bearing has a direct impact on flight safety. To detect the status of rolling bearing and find the bearing fault as soon as possible can effectively reduce the occurrence of flight accident. It is of great significance to predict the remaining life of rolling bearing. The present status evaluation of rolling bearings seldom considers the influence of load and rotational speed change on bearing state evaluation, and lacks the research and fusion of characteristic sensitivity, which is insensitive to early fault detection and inaccurate for bearing state evaluation. Therefore, it is necessary to perform multi-feature fusion under variable operating conditions. In this paper, the multi-feature extraction and fusion technology of aeroengine rolling bearing under variable working condition is studied. In this paper, three multi-feature fusion methods are proposed, which are distance discrimination, classification and posteriori probability. The distance discriminant method is based on the vibration characteristics of the normal data of rolling bearing operation to study the Euclidean distance and to compare the distance between unknown state and normal state. A kind of classification is to describe the distribution of normal data samples correctly, and to test the classification of unknown samples is to test whether they are subordinate to the distribution. A posteriori probability method is a support vector machine algorithm based on a posteriori probability, which forms a training sample by using the sample data of the normal state and the serious fault state, and studies the posteriori probabilistic support vector machine, which can realize the classification problem. In addition, the probability estimation of classification results based on Bayesian decision rule can be used to simulate the single point fault of rolling bearing. Four sets of vibration acceleration signals are obtained, and 13 dimensionless features are extracted from time domain, frequency domain and time frequency domain. Sensitivity analysis of 13 features was carried out. The effect of different rotational speed on fault characteristic sensitivity was compared by extracting rotational speed signal. The feature fusion method is used to fuse the multi-dimensional features. The experimental results fully verify the correctness of the method. (3) the rolling bearing performance degradation test is carried out. Vibration test data of aeronautical rolling bearings in different working states from normal to abnormal state are obtained. The feature fusion and state evaluation are carried out by using the method of feature fusion in this paper. The results show that the extracted multidimensional features can distinguish the normal and abnormal states of bearings obviously by the state evaluation after fusion. That is to say, the method of feature fusion state evaluation in this paper has good engineering application value.
【學(xué)位授予單位】：南京航空航天大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2016
【分類號(hào)】：V263.6

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 艾延廷;馮研研;周海侖;;LMD和改進(jìn)小波閾值去噪的軸承聲發(fā)射信號(hào)故障診斷[J];科學(xué)技術(shù)與工程;2014年33期

2 劉鐵軍;何學(xué)科;;基于鐵譜圖像分析的大型養(yǎng)路機(jī)械發(fā)動(dòng)機(jī)故障研究[J];機(jī)車電傳動(dòng);2014年06期

3 ;Construction of adaptive redundant multiwavelet packet and its application to compound faults detection of rotating machinery[J];Science China(Technological Sciences);2012年08期

4 楊宇;王歡歡;程軍圣;鄒憲軍;;基于LMD的包絡(luò)譜特征值在滾動(dòng)軸承故障診斷中的應(yīng)用[J];航空動(dòng)力學(xué)報(bào);2012年05期

5 胡愛(ài)軍;馬萬(wàn)里;唐貴基;;基于集成經(jīng)驗(yàn)?zāi)B(tài)分解和峭度準(zhǔn)則的滾動(dòng)軸承故障特征提取方法[J];中國(guó)電機(jī)工程學(xué)報(bào);2012年11期

6 肖文斌;陳進(jìn);周宇;王志陽(yáng);趙發(fā)剛;;小波包變換和隱馬爾可夫模型在軸承性能退化評(píng)估中的應(yīng)用[J];振動(dòng)與沖擊;2011年08期

7 孟光;尤明懿;;基于狀態(tài)監(jiān)測(cè)的設(shè)備壽命預(yù)測(cè)與預(yù)防維護(hù)規(guī)劃研究進(jìn)展[J];振動(dòng)與沖擊;2011年08期

8 劉穎;嚴(yán)軍;;基于時(shí)間序列ARMA模型的振動(dòng)故障預(yù)測(cè)[J];化工自動(dòng)化及儀表;2011年07期

9 趙元喜;胥永剛;高立新;崔玲麗;;基于諧波小波包和BP神經(jīng)網(wǎng)絡(luò)的滾動(dòng)軸承聲發(fā)射故障模式識(shí)別技術(shù)[J];振動(dòng)與沖擊;2010年10期

10 潘玉娜;陳進(jìn);李興林;;基于模糊c-均值的設(shè)備性能退化評(píng)估方法[J];上海交通大學(xué)學(xué)報(bào);2009年11期

，

本文編號(hào)：1925694