【摘要】：旋轉(zhuǎn)機械是機械裝備的重要組成部分,一旦出現(xiàn)故障,會導(dǎo)致整個設(shè)備或生產(chǎn)過程停止運行,甚至造成嚴(yán)重的安全事故和重大經(jīng)濟損失。因此,機械設(shè)備故障預(yù)測受到人們的關(guān)注和研究。傳統(tǒng)頻譜分析方法僅依賴單通道振動信息,丟失了信息的完整性,而全矢譜技術(shù)采用同源雙通道信息融合的思想,保證頻譜包含完整、全面的振動信息;現(xiàn)代設(shè)備監(jiān)測系統(tǒng)通常采集大量監(jiān)測信號,但在設(shè)備預(yù)測過程中,并不能充分利用歷史監(jiān)測信息,導(dǎo)致中長期預(yù)測可信度低,時間序列聚類方法能把近似狀態(tài)的時刻聚類,將大量歷史監(jiān)測信息簡化,使得預(yù)測過程中利用更多歷史信息;為克服全矢-ARIMA(FV-ARIMA)和全矢-SVR(FV-SVR)預(yù)測模型的缺陷,提出改進的全矢-SVR預(yù)測模型。本文以設(shè)備監(jiān)測大數(shù)據(jù)為研究對象,全矢譜技術(shù)和時間序列聚類為理論支撐,結(jié)合改進的全矢-SVR預(yù)測模型,對設(shè)備故障預(yù)測進行研究。主要研究工作如下:(1)詳細(xì)研究了全矢譜技術(shù)的理論和算法,給出Hilbert-全矢譜的算法步驟,并將其應(yīng)用于滾動軸承的退化分析中,驗證了Hilbert-全矢譜具有良好的包絡(luò)解調(diào)效果,所求得的特征主振矢能夠表征振動強度,區(qū)分故障類型。(2)研究設(shè)備監(jiān)測數(shù)據(jù)的特點,并給出設(shè)備監(jiān)測大數(shù)據(jù)的概念;研究數(shù)據(jù)的平滑處理方法和時間序列聚類分析方法,并將其應(yīng)用到真實的時序序列中,獲得良好的平滑處理效果和聚類效果。(3)研究ARIMA模型和SVR預(yù)測的基本理論和算法;給出全矢預(yù)測模型的基本流程;通過對滾動軸承的狀態(tài)預(yù)測,分析并總結(jié)全矢-ARIMA和全矢-SVR預(yù)測模型的優(yōu)點和缺點。(4)針對全矢預(yù)測模型的缺點,提出改進的全矢-SVR預(yù)測模型;結(jié)合時間序列聚類分析和改進的全矢預(yù)測模型,構(gòu)建基于大數(shù)據(jù)的中長期設(shè)備故障全矢預(yù)測模型;采用滾動軸承運行過程中的全部歷史數(shù)據(jù),分別對改進的全矢-SVR預(yù)測模型和基于大數(shù)據(jù)的中長期設(shè)備故障全矢預(yù)測模型進行實驗驗證,結(jié)果顯示,兩種預(yù)測方法均取得良好的預(yù)測效果。
[Abstract]:Rotating machinery is an important part of machinery and equipment, once it fails, it will cause the whole equipment or production process to stop running, and even cause serious safety accidents and major economic losses. Therefore, mechanical equipment fault prediction has attracted people's attention and research. The traditional spectrum analysis method only relies on the single channel vibration information and loses the integrity of the information, while the whole vector spectrum technology adopts the idea of homologous and dual channel information fusion to ensure that the spectrum contains complete and comprehensive vibration information. Modern equipment monitoring system usually collects a large number of monitoring signals, but in the process of equipment prediction, the historical monitoring information can not be fully utilized, which leads to the low credibility of the medium and long term prediction, and the time series clustering method can cluster the approximate state of time. Simplifying a large number of historical monitoring information to make use of more historical information in the prediction process; In order to overcome the defects of total vector ARIMA (FV-ARIMA) and total vector SVR (FV-SVR) prediction models, an improved total vector SVR prediction model is proposed. This paper takes big data as the research object, total vector spectrum technology and time series clustering as the theoretical support, combined with the improved full-vector SVR prediction model, to study the equipment fault prediction. The main research work is as follows: (1) the theory and algorithm of total vector spectrum technology are studied in detail, and the steps of Hilbert- complete vector spectrum algorithm are given, and applied to the degradation analysis of rolling bearings. It is verified that Hilbert- full-vector spectrum has a good envelope demodulation effect, and the characteristic principal vibration vector can characterize vibration intensity and distinguish fault types. (2) the characteristics of equipment monitoring data are studied, and the concept of equipment monitoring big data is given. The data smoothing method and time series clustering analysis method are studied and applied to real time series to obtain good smoothing effect and clustering effect. (3) the basic theory and algorithm of ARIMA model and SVR prediction are studied. The basic flow chart of the full-vector prediction model is given. The advantages and disadvantages of full-vector ARIMA and full-vector SVR prediction models are analyzed and summarized through the state prediction of rolling bearings. (4) aiming at the shortcomings of the full-vector prediction model, an improved full-vector SVR prediction model is proposed. Combined with time series clustering analysis and improved full-vector prediction model, the full-vector prediction model of medium- and long-term equipment fault based on big data is constructed. Using all the historical data of rolling bearing operation, the improved full-vector SVR prediction model and the full-vector prediction model of medium-long term equipment fault based on big data are tested, and the results show that, The two prediction methods have achieved good prediction results.
【學(xué)位授予單位】：鄭州大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2017
【分類號】：TH17

【參考文獻】

相關(guān)期刊論文 前10條

1 李凌均;陳超;韓捷;陳宏;;全矢支持向量回歸頻譜預(yù)測方法[J];鄭州大學(xué)學(xué)報(工學(xué)版);2016年03期

2 韓昕鋒;任立坤;;基于神經(jīng)網(wǎng)絡(luò)的軸承故障預(yù)測模型[J];海軍航空工程學(xué)院學(xué)報;2015年03期

3 王杭州;朱劍鋒;趙勁松;邱彤;陳丙珍;;卡爾曼濾波與灰色預(yù)測用于異常工況趨勢預(yù)測的方法[J];計算機與應(yīng)用化學(xué);2015年03期

4 習(xí)偉;李鵬;郭曉斌;許愛東;蔣愈勇;張利強;吳玉生;;多維時間序列關(guān)聯(lián)分析方法在電力設(shè)備故障預(yù)測中的應(yīng)用[J];電網(wǎng)與清潔能源;2014年12期

5 杜占龍;李小民;鄭宗貴;毛瓊;;強跟蹤平方根容積卡爾曼濾波和自回歸模型融合的故障預(yù)測[J];控制理論與應(yīng)用;2014年08期

6 程知;;數(shù)據(jù)挖掘的預(yù)處理技術(shù)研究[J];計算機光盤軟件與應(yīng)用;2014年06期

7 徐輝;吳家勝;張瀚文;;ELM神經(jīng)網(wǎng)絡(luò)及其在機械故障預(yù)測中的應(yīng)用[J];中國煤炭;2014年01期

8 邱宏軍;韓偉實;;旋轉(zhuǎn)機械的故障預(yù)測方法綜述[J];科技創(chuàng)新與應(yīng)用;2013年19期

9 孫銀銀;劉振祥;胡歙眉;洪宇;;基于改進的MGM(1,n)模型的旋轉(zhuǎn)機械故障預(yù)測方法研究[J];汽輪機技術(shù);2012年05期

10 陸寶春;程相亮;樊帆;張登峰;;機械設(shè)備運行故障預(yù)測方法綜述[J];機械制造與自動化;2012年05期

相關(guān)博士學(xué)位論文 前2條

1 陳向民;基于形態(tài)分量分析和線調(diào)頻小波路徑追蹤的機械故障診斷方法研究[D];湖南大學(xué);2013年

2 祝志博;融合聚類分析的故障檢測和分類研究[D];浙江大學(xué);2012年

相關(guān)碩士學(xué)位論文 前9條

1 孫建;滾動軸承振動故障特征提取與壽命預(yù)測研究[D];大連理工大學(xué);2015年

2 曹立立;基于HMM的TE過程在線故障診斷與多步故障預(yù)報[D];華中科技大學(xué);2015年

3 侯曉凱;基于神經(jīng)網(wǎng)絡(luò)的多狀態(tài)網(wǎng)絡(luò)設(shè)備故障預(yù)測的研究[D];山東大學(xué);2014年

4 曾平;基于Hilbert-Huang變換的微車主減速器品質(zhì)評價方法的應(yīng)用研究[D];武漢理工大學(xué);2013年

5 薛奰舒;基于數(shù)據(jù)挖掘的旋轉(zhuǎn)設(shè)備振動故障診斷應(yīng)用[D];吉林大學(xué);2013年

6 張國坤;基于聚類分析的汽輪發(fā)電機組早期故障識別系統(tǒng)研究[D];華北電力大學(xué);2013年

7 朱文婕;模糊聚類有效性指標(biāo)研究[D];合肥工業(yè)大學(xué);2009年

8 李紅英;支持向量分類機的核函數(shù)研究[D];重慶大學(xué);2009年

9 張海濤;旋轉(zhuǎn)機械全矢譜分析系統(tǒng)的構(gòu)建與應(yīng)用[D];鄭州大學(xué);2007年

，

本文編號：2388904