本文關(guān)鍵詞： 滾動(dòng)軸承 故障診斷 經(jīng)驗(yàn)?zāi)B(tài)分解 小波分析 小波包分析 粗糙集 人工神經(jīng)網(wǎng)絡(luò)　出處：《西南交通大學(xué)》2012年碩士論文　論文類型：學(xué)位論文

【摘要】：隨著現(xiàn)代機(jī)械設(shè)備日趨大型化、精密化和自動(dòng)化,有效的機(jī)械故障診斷作為系統(tǒng)可靠和安全運(yùn)行的保障,具有非常重要的價(jià)值。滾動(dòng)軸承因摩擦力小、裝配方便等優(yōu)點(diǎn)成為機(jī)械設(shè)備中最常用的零部件,其穩(wěn)定性直接影響設(shè)備的性能。對(duì)滾動(dòng)軸承實(shí)施狀態(tài)監(jiān)測(cè)與故障診斷,對(duì)避免經(jīng)濟(jì)損失和重大事故發(fā)生有重大意義。 在滾動(dòng)軸承故障診斷中,振動(dòng)分析是最常用和有效的方法。掌握滾動(dòng)軸承振動(dòng)機(jī)理,確定振動(dòng)信號(hào)測(cè)定方式,模擬滾動(dòng)軸承內(nèi)圈、外圈故障后,構(gòu)建故障診斷實(shí)驗(yàn)系統(tǒng)。本文采集并處理振動(dòng)信號(hào),從時(shí)域、頻域和時(shí)頻域分析并提取反映滾動(dòng)軸承運(yùn)作狀態(tài)的特征向量。 其中,基于經(jīng)驗(yàn)的模態(tài)分解根據(jù)自身時(shí)間尺度特征分解信號(hào),具有高信噪比和自適應(yīng)性,在非線性、非平穩(wěn)信號(hào)的分析和處理上占有很大優(yōu)勢(shì)；小波分析采用變化的窗函數(shù)實(shí)現(xiàn)局部化的頻率分析,具有多分辨特性,廣泛應(yīng)用于信號(hào)的降噪和壓縮,從小波能量的角度出發(fā),可以挑選感興趣的分層進(jìn)行分析；小波包分析是小波分析的延伸與拓展,實(shí)現(xiàn)高頻和低頻的同步分解,提高時(shí)頻分辨率,更具應(yīng)用價(jià)值。 粗糙集理論是人工智能領(lǐng)域中處理不完備、不精確信息的軟計(jì)算方法,在知識(shí)挖掘、決策分析等領(lǐng)域有著廣泛的應(yīng)用。在滾動(dòng)軸承故障診斷中,保證診斷精度不變的情況下,粗糙集能有效地減少特征維數(shù),保留核屬性,減小計(jì)算量和不確定因素的影響,降低故障診斷系統(tǒng)的復(fù)雜度與規(guī)模。 人工神經(jīng)網(wǎng)絡(luò)模擬人腦結(jié)構(gòu)和功能,是強(qiáng)大的信息處理系統(tǒng),具有高度自適應(yīng)性、并行處理方式、自我學(xué)習(xí)和歸納的能力。通過(guò)學(xué)習(xí)和訓(xùn)練,神經(jīng)網(wǎng)絡(luò)由故障癥狀推斷故障產(chǎn)生原因,實(shí)現(xiàn)滾動(dòng)軸承故障診斷和模式識(shí)別。 本文采用三種方法對(duì)比實(shí)現(xiàn)軸承故障診斷。第一,將歸一化的特征向量導(dǎo)入訓(xùn)練好的神經(jīng)網(wǎng)絡(luò),實(shí)現(xiàn)滾動(dòng)軸承故障診斷;第二,建立粗糙集分類器,通過(guò)自學(xué)習(xí)實(shí)現(xiàn)滾動(dòng)軸承狀態(tài)分類；第三,將粗糙集作為前端數(shù)據(jù)預(yù)處理器,實(shí)現(xiàn)數(shù)據(jù)離散、屬性約簡(jiǎn)和決策規(guī)則的生成,優(yōu)化的特征參量作為神經(jīng)網(wǎng)絡(luò)的輸入。結(jié)果表明,粗糙集和神經(jīng)網(wǎng)絡(luò)相結(jié)合的故障診斷系統(tǒng)準(zhǔn)確率和效率明顯提高。 本文的重點(diǎn)是實(shí)現(xiàn)敏感特征向量的有效提取,靈活運(yùn)用粗糙集理論預(yù)處理特征,消除冗余信息,防止信息爆炸,結(jié)合神經(jīng)網(wǎng)絡(luò)容錯(cuò)和泛化能力強(qiáng)的優(yōu)勢(shì),有效地實(shí)現(xiàn)滾動(dòng)軸承故障診斷。同時(shí),粗糙集理論作為全新的特征降維技術(shù),在智能化故障診斷領(lǐng)域都有著廣泛的應(yīng)用和發(fā)展。
[Abstract]:With modern mechanical equipment becoming larger and larger, precision and automation, effective mechanical fault diagnosis as a guarantee of reliable and safe operation of the system, has a very important value. The advantages of convenient assembly have become the most commonly used parts in mechanical equipment, and its stability directly affects the performance of the equipment. It is of great significance to avoid economic losses and serious accidents to implement condition monitoring and fault diagnosis for rolling bearings. In the fault diagnosis of rolling bearing, vibration analysis is the most common and effective method. After mastering the vibration mechanism of rolling bearing, determining the measuring method of vibration signal, simulating the fault of inner ring and outer ring of rolling bearing, In this paper, the vibration signals are collected and processed, and the characteristic vectors reflecting the operation state of rolling bearings are analyzed and extracted from time domain, frequency domain and time frequency domain. Among them, the empirical mode decomposition decomposes the signal according to its own time scale characteristic, has the high signal-to-noise ratio and the adaptability, and has the very big superiority in the non-linear, the non-stationary signal analysis and the processing; Wavelet analysis uses the variable window function to realize localized frequency analysis, which has multi-resolution characteristic, and is widely used in signal denoising and compression. From the angle of wave energy, we can select the layers of interest for analysis. Wavelet packet analysis is an extension and extension of wavelet analysis. It can realize synchronous decomposition of high frequency and low frequency and improve time-frequency resolution. Rough set theory is a soft computing method for dealing with incomplete and imprecise information in the field of artificial intelligence. It is widely used in the fields of knowledge mining, decision analysis and so on. Rough set can effectively reduce the feature dimension, preserve kernel attributes, reduce the influence of computation and uncertainty, and reduce the complexity and scale of fault diagnosis system. Artificial neural network simulates the structure and function of human brain. It is a powerful information processing system with high adaptability, parallel processing, self-learning and inductive ability. Neural network infer the cause of fault from the fault symptom, and realize fault diagnosis and pattern recognition of rolling bearing. This paper uses three methods to realize bearing fault diagnosis. First, the normalized eigenvector is introduced into the trained neural network to realize the rolling bearing fault diagnosis; second, the rough set classifier is established. The status classification of rolling bearing is realized by self-learning. Thirdly, rough set is used as front-end data preprocessor to realize data discretization, attribute reduction and decision rule generation, and optimized characteristic parameters are used as input of neural network. The accuracy and efficiency of the fault diagnosis system based on rough set and neural network are improved obviously. The emphasis of this paper is to realize the effective extraction of sensitive feature vectors, to flexibly use rough set theory to preprocess features, to eliminate redundant information, to prevent information explosion, and to combine the advantages of neural network with strong fault tolerance and generalization ability. At the same time, as a new feature dimension reduction technology, rough set theory has been widely used and developed in the field of intelligent fault diagnosis.
【學(xué)位授予單位】：西南交通大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2012
【分類號(hào)】：TH133.33;TH165.3

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 王曉青;夏水華;;滾動(dòng)軸承失效影響因素與影響機(jī)制[J];軸承;2010年11期

2 郝麗娜,王偉,吳光宇,王宛山;粗糙集-神經(jīng)網(wǎng)絡(luò)故障診斷方法研究[J];東北大學(xué)學(xué)報(bào);2003年03期

3 林瑞霖;周平;;基于EMD和神經(jīng)網(wǎng)絡(luò)的氣閥機(jī)構(gòu)故障診斷研究[J];海軍工程大學(xué)學(xué)報(bào);2008年02期

4 李振興;;基于經(jīng)驗(yàn)?zāi)B(tài)分解的Wigner-Ville分布交叉項(xiàng)抑制方法[J];航空兵器;2010年06期

5 趙培洪;平殿發(fā);鄧兵;;抑制Winger-Ville分布交叉項(xiàng)的新方法[J];計(jì)算機(jī)應(yīng)用;2010年08期

6 郭小薈;馬小平;;基于粗糙集-神經(jīng)網(wǎng)絡(luò)集成的故障診斷[J];控制工程;2007年01期

7 李元萍;李元良;;粗糙集約簡(jiǎn)算法的研究與實(shí)現(xiàn)[J];礦業(yè)研究與開(kāi)發(fā);2008年04期

8 桂普江,林建中;滾動(dòng)軸承故障診斷的神經(jīng)網(wǎng)絡(luò)方法[J];機(jī)械;2004年10期

9 李興林;張仰平;曹茂來(lái);張燕遼;陸水根;李建平;;滾動(dòng)軸承故障監(jiān)測(cè)診斷技術(shù)應(yīng)用進(jìn)展[J];工程與試驗(yàn);2009年04期

10 徐襲;劉玉波;范學(xué)鑫;;基于模糊工具箱和ROSETTA的粗糙集數(shù)據(jù)挖掘[J];微計(jì)算機(jī)信息;2007年18期

相關(guān)博士學(xué)位論文 前1條

1 竇唯;旋轉(zhuǎn)機(jī)械振動(dòng)故障診斷的圖形識(shí)別方法研究[D];哈爾濱工業(yè)大學(xué);2009年

相關(guān)碩士學(xué)位論文 前5條

1 孔亞林;基于振動(dòng)信號(hào)的滾動(dòng)軸承故障診斷方法研究[D];大連理工大學(xué);2006年

2 張華君;基于HHT的機(jī)電系統(tǒng)的滾動(dòng)軸承故障診斷[D];太原理工大學(xué);2006年

3 馮曉光;近似熵在往復(fù)式壓縮機(jī)故障診斷中的研究應(yīng)用[D];大連理工大學(xué);2006年

4 劉華勝;基于EMD的滾動(dòng)軸承故障診斷方法研究[D];大連理工大學(xué);2007年

5 陳波;基于粗糙集—概率神經(jīng)網(wǎng)絡(luò)結(jié)合的變壓器故障診斷研究[D];廣西大學(xué);2008年

，

本文編號(hào)：1548137