基于灰色ELM的滾動軸承故障預(yù)測
發(fā)布時(shí)間：2018-11-18 07:42
【摘要】：隨著旋轉(zhuǎn)機(jī)械設(shè)備趨于大型化、高效化、集成化,這對旋轉(zhuǎn)機(jī)械安全可靠運(yùn)行的要求也相應(yīng)提高。滾動軸承是現(xiàn)代旋轉(zhuǎn)機(jī)械設(shè)備中最具關(guān)鍵作用的組成部件之一,它的工作狀態(tài)正常與否直接關(guān)系著機(jī)械設(shè)備乃至整個(gè)系統(tǒng)的運(yùn)行狀態(tài),但由于工作條件的惡劣造成其壽命參差性很大和容易損傷的缺點(diǎn),因此需要對滾動軸承實(shí)施有效的故障預(yù)測。本課題“基于灰色ELM的滾動軸承故障預(yù)測”對采用灰色理論方法和ELM神經(jīng)網(wǎng)絡(luò)進(jìn)行滾動軸承故障預(yù)測中所涉及的理論、方法和關(guān)鍵技術(shù)進(jìn)行了深入的研究,主要研究工作如下:通過系統(tǒng)分析滾動軸承故障預(yù)測主要方法及國內(nèi)外在該領(lǐng)域的研究現(xiàn)狀,指出快速、準(zhǔn)確的軸承故障預(yù)測技術(shù)已成為研究重點(diǎn)。在三大類故障預(yù)測技術(shù)中,重點(diǎn)分析介紹了了本文采用的基于數(shù)據(jù)的故障預(yù)測技術(shù)。針對滾動軸承振動信號具有非平穩(wěn)性和非線性的特點(diǎn)以及各種經(jīng)典方法的不足之處,運(yùn)用灰色理論來預(yù)測軸承故障發(fā)展。深入研究了灰色模型的建模機(jī)理和適用范圍。針對傳統(tǒng)灰色GM(1,1)模型的不足,探討了一系列改進(jìn)灰色模型。其中,灰色多變量預(yù)測模型MGM(1,n)模型從系統(tǒng)的角度對多個(gè)診斷指標(biāo)進(jìn)行統(tǒng)一描述,本文用滾動軸承實(shí)驗(yàn)予以驗(yàn)證。由于傳統(tǒng)的神經(jīng)網(wǎng)絡(luò)梯度學(xué)習(xí)算法存在著訓(xùn)練時(shí)間長、過度擬合訓(xùn)練樣本和易陷入局部最優(yōu)等問題。本課題引入了 ELM神經(jīng)網(wǎng)絡(luò),ELM(極限學(xué)習(xí)機(jī))具有學(xué)習(xí)時(shí)間短、算法簡單容易實(shí)現(xiàn)、良好的泛化性能和能避免陷入局部最優(yōu)等優(yōu)點(diǎn),已經(jīng)成功應(yīng)用于函數(shù)擬合和預(yù)測等應(yīng)用領(lǐng)域。介紹了極限學(xué)習(xí)機(jī)的相關(guān)基礎(chǔ)理論,對前饋神經(jīng)網(wǎng)絡(luò)學(xué)習(xí)算法和極限學(xué)習(xí)機(jī)算法進(jìn)行了研究。在實(shí)際環(huán)境中的滾動軸承的振動信號在的噪聲背景下不易提取,兼有非線性和非平穩(wěn)的特點(diǎn)。本文對滾動軸承的振動信號進(jìn)行經(jīng)驗(yàn)?zāi)B(tài)分解,經(jīng)過理論和仿真分析,發(fā)現(xiàn)在非線性信號處理方面EEMD分解較EMD分解有更好的抗混疊效果;自相關(guān)函數(shù)降噪性能優(yōu)越,在故障提取特征方面具有很大的優(yōu)勢。灰色模型能夠預(yù)測發(fā)展序列,ELM神經(jīng)網(wǎng)絡(luò)具有高度的非線性映射特性,本文提出一種新的組合權(quán)系數(shù)的計(jì)算方法,將二者有機(jī)結(jié)合,建立灰色ELM組合預(yù)測模型,能夠描述軸承兼具確定性和波動性的復(fù)雜趨勢。將組合模型用于軸承故障預(yù)測,充分利用信息以提高精度。對用EMD分解軸承振動數(shù)據(jù)后得到一系列IMF分量,將包含故障頻率的IMF的均方根值作為軸承的故障特征向量和預(yù)測模型輸入?yún)?shù)。得到的實(shí)驗(yàn)結(jié)果表明,其較單一模型有更高的預(yù)測精度。
[Abstract]:With the large scale, high efficiency and integration of rotating machinery, the requirement of safe and reliable operation of rotating machinery is raised accordingly. Rolling bearing is one of the most important components in modern rotating machinery. Its normal working condition is directly related to the running state of machinery and even the whole system. However, due to the poor working conditions, it is necessary to carry out effective fault prediction for rolling bearings due to the disadvantages of great variation of life and easy damage. In this paper, the theory, method and key technology of rolling bearing fault prediction based on grey ELM and ELM neural network are deeply studied. The main research work is as follows: through the systematic analysis of the main methods of rolling bearing fault prediction and the current research situation in this field at home and abroad, it is pointed out that the rapid and accurate bearing fault prediction technology has become the focus of research. In the three kinds of fault prediction technology, the data based fault prediction technology is analyzed and introduced in this paper. In view of the non-stationary and nonlinear characteristics of rolling bearing vibration signal and the shortcomings of various classical methods, the grey theory is used to predict the development of bearing fault. The modeling mechanism and application scope of grey model are studied in depth. Aiming at the deficiency of traditional grey GM (1K1) model, a series of improved grey models are discussed. Among them, the grey multivariable prediction model MGM (1n) model is used to describe several diagnostic indexes uniformly from the point of view of the system, which is verified by rolling bearing experiments in this paper. The traditional neural network gradient learning algorithm has many problems, such as long training time, over-fitting of training samples and easy to fall into local optimum. This paper introduces the ELM neural network, ELM (extreme learning machine), which has the advantages of short learning time, simple algorithm, good generalization performance and the ability to avoid falling into local optimum. It has been successfully applied in the fields of function fitting and prediction. This paper introduces the basic theory of extreme learning machine and studies the learning algorithm of feedforward neural network and ultimate learning machine. The vibration signal of rolling bearing in real environment is difficult to be extracted under the background of noise and has the characteristics of nonlinearity and nonstationarity. In this paper, the vibration signals of rolling bearings are decomposed by empirical mode decomposition. Through theoretical and simulation analysis, it is found that EEMD decomposition has better anti-aliasing effect than EMD decomposition in nonlinear signal processing. Autocorrelation function has excellent performance in noise reduction and has great advantages in fault feature extraction. Grey model can predict development sequence, ELM neural network has high nonlinear mapping characteristics. This paper presents a new calculation method of combined weight coefficient, combining the two methods organically, establishes the grey ELM combination prediction model. Can describe the bearing both certainty and volatility of the complex trend. The combined model is applied to the bearing fault prediction, and the information is fully utilized to improve the accuracy. A series of IMF components are obtained by using EMD to decompose the bearing vibration data. The root mean square (RMS) value of IMF which contains the fault frequency is taken as the bearing fault eigenvector and the input parameter of the prediction model. The experimental results show that the prediction accuracy of the model is higher than that of the single model.
【學(xué)位授予單位】：北京交通大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2017
【分類號】：TH133.33
[Abstract]:With the large scale, high efficiency and integration of rotating machinery, the requirement of safe and reliable operation of rotating machinery is raised accordingly. Rolling bearing is one of the most important components in modern rotating machinery. Its normal working condition is directly related to the running state of machinery and even the whole system. However, due to the poor working conditions, it is necessary to carry out effective fault prediction for rolling bearings due to the disadvantages of great variation of life and easy damage. In this paper, the theory, method and key technology of rolling bearing fault prediction based on grey ELM and ELM neural network are deeply studied. The main research work is as follows: through the systematic analysis of the main methods of rolling bearing fault prediction and the current research situation in this field at home and abroad, it is pointed out that the rapid and accurate bearing fault prediction technology has become the focus of research. In the three kinds of fault prediction technology, the data based fault prediction technology is analyzed and introduced in this paper. In view of the non-stationary and nonlinear characteristics of rolling bearing vibration signal and the shortcomings of various classical methods, the grey theory is used to predict the development of bearing fault. The modeling mechanism and application scope of grey model are studied in depth. Aiming at the deficiency of traditional grey GM (1K1) model, a series of improved grey models are discussed. Among them, the grey multivariable prediction model MGM (1n) model is used to describe several diagnostic indexes uniformly from the point of view of the system, which is verified by rolling bearing experiments in this paper. The traditional neural network gradient learning algorithm has many problems, such as long training time, over-fitting of training samples and easy to fall into local optimum. This paper introduces the ELM neural network, ELM (extreme learning machine), which has the advantages of short learning time, simple algorithm, good generalization performance and the ability to avoid falling into local optimum. It has been successfully applied in the fields of function fitting and prediction. This paper introduces the basic theory of extreme learning machine and studies the learning algorithm of feedforward neural network and ultimate learning machine. The vibration signal of rolling bearing in real environment is difficult to be extracted under the background of noise and has the characteristics of nonlinearity and nonstationarity. In this paper, the vibration signals of rolling bearings are decomposed by empirical mode decomposition. Through theoretical and simulation analysis, it is found that EEMD decomposition has better anti-aliasing effect than EMD decomposition in nonlinear signal processing. Autocorrelation function has excellent performance in noise reduction and has great advantages in fault feature extraction. Grey model can predict development sequence, ELM neural network has high nonlinear mapping characteristics. This paper presents a new calculation method of combined weight coefficient, combining the two methods organically, establishes the grey ELM combination prediction model. Can describe the bearing both certainty and volatility of the complex trend. The combined model is applied to the bearing fault prediction, and the information is fully utilized to improve the accuracy. A series of IMF components are obtained by using EMD to decompose the bearing vibration data. The root mean square (RMS) value of IMF which contains the fault frequency is taken as the bearing fault eigenvector and the input parameter of the prediction model. The experimental results show that the prediction accuracy of the model is higher than that of the single model.
【學(xué)位授予單位】：北京交通大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2017
【分類號】：TH133.33
【參考文獻(xiàn)】
相關(guān)期刊論文 前10條
1 朱鵬飛;夏陸岳;潘海天;;基于改進(jìn)Kalman濾波算法的多模型融合建模方法[J];化工學(xué)報(bào);2015年04期
2 劉國超;黃張?jiān)?徐秀杰;馮劍橋;;新陳代謝GM(1,1)模型在變形監(jiān)測數(shù)據(jù)處理中的應(yīng)用[J];勘察科學(xué)技術(shù);2014年01期
3 孫銀銀;劉振祥;胡歙眉;洪宇;;基于改進(jìn)的MGM(1,n)模型的旋轉(zhuǎn)機(jī)械故障預(yù)測方法研究[J];汽輪機(jī)技術(shù);2012年05期
4 陳良波;鄭亞青;;基于最小二乘法的曲線擬合研究[J];無錫職業(yè)技術(shù)學(xué)院學(xué)報(bào);2012年05期
5 張東娟;丁煜函;劉國海;梅從立;;基于改進(jìn)極限學(xué)習(xí)機(jī)的軟測量建模方法[J];計(jì)算機(jī)工程與應(yīng)用;2012年20期
6 陳宇;陳懷海;李贊澄;賀旭東;;時(shí)變AR模型的一種定階方法[J];振動與沖擊;2012年08期
7 李萬領(lǐng);孟晨;楊鎖昌;楊森;;基于改進(jìn)灰色模型的故障預(yù)測研究[J];中國測試;2012年02期
8 張光軼;蘇艷琴;許愛強(qiáng);;灰色模型在裝備故障預(yù)測中應(yīng)用分析[J];測控技術(shù);2012年02期
9 鞏林明;張振國;;基于灰色小波的網(wǎng)絡(luò)流量組合預(yù)測模型[J];計(jì)算機(jī)工程與設(shè)計(jì);2010年08期
10 曾波;劉思峰;方志耕;謝乃明;;灰色組合預(yù)測模型及其應(yīng)用[J];中國管理科學(xué);2009年05期
相關(guān)碩士學(xué)位論文 前4條
1 楊芬;離散灰色預(yù)測模型的拓展研究及應(yīng)用[D];南京航空航天大學(xué);2014年
2 段侯峰;基于遺傳算法優(yōu)化BP神經(jīng)網(wǎng)絡(luò)的變壓器故障診斷[D];北京交通大學(xué);2008年
3 劉源l，
本文編號：2339350
本文鏈接：http://sikaile.net/jixiegongchenglunwen/2339350.html
最近更新
教材專著
