【摘要】：隨著信息科學(xué)技術(shù)的快速發(fā)展,計(jì)算機(jī)技術(shù)與各種智能儀表在機(jī)械裝備的監(jiān)測(cè)中獲得了廣泛應(yīng)用,反映系統(tǒng)運(yùn)行狀態(tài)的海量過(guò)程數(shù)據(jù)被采集并存儲(chǔ)下來(lái),但是存在著“數(shù)據(jù)豐富,但信息匱乏”的缺陷。利用這些離、在線運(yùn)行數(shù)據(jù),采用智能數(shù)據(jù)分析算法,建立起一種能夠科學(xué)描述機(jī)械裝備運(yùn)行狀態(tài)的量化特征模式,實(shí)現(xiàn)對(duì)機(jī)械裝備信息化技術(shù)發(fā)展中機(jī)器故障的智能自動(dòng)辨識(shí),具有非常積極地奠定作用。 為此,本文從反映機(jī)械裝備信息特點(diǎn)的量化特征模式構(gòu)造出發(fā),基于數(shù)據(jù)挖掘的知識(shí)發(fā)現(xiàn)原理,圍繞著利用智能數(shù)據(jù)分析工具,開展基于數(shù)據(jù)驅(qū)動(dòng)的故障監(jiān)測(cè)診斷方法的研究工作。通過(guò)采用數(shù)據(jù)驅(qū)動(dòng)故障診斷的常用算法,重點(diǎn)對(duì)反映機(jī)械裝備信息特點(diǎn)的量化特征模式構(gòu)造及不均衡故障數(shù)據(jù)集的分類方法進(jìn)行探討,為量化描述機(jī)組運(yùn)行狀況,實(shí)現(xiàn)對(duì)故障模式的在線診斷提供依據(jù)。本文主要研究工作包括以下幾個(gè)方面的內(nèi)容： (1)介紹多域特征的提取方法,對(duì)KPCA-SVM的故障數(shù)據(jù)分類方法進(jìn)行研究,并對(duì)該方法在轉(zhuǎn)子系統(tǒng)故障診斷中的應(yīng)用情況進(jìn)行探討。 (2)針對(duì)故障信息的量化特征描述問(wèn)題,提出了一種特征選擇與特征信息融合的加權(quán)KPCA方法。首先對(duì)單個(gè)通道的振動(dòng)信號(hào)提取時(shí)域、頻域和時(shí)頻域的多域特征參量,通過(guò)特征選擇方法篩選出利于故障模式辨識(shí)的敏感特征；其次融合多通道的敏感特征,得到融合特征向量；然后采用加權(quán)KPCA方法提取出融合特征向量的核主成分。通過(guò)SVM分類器的實(shí)驗(yàn)驗(yàn)證情況表明,該算法可有效辨識(shí)出不同故障類型。 (3)針對(duì)不均衡故障數(shù)據(jù)分類精度低,辨識(shí)效率不高的問(wèn)題,提出了一種基于滑動(dòng)窗口相似性因子分析方法。該方法引入滑動(dòng)窗口技術(shù),通過(guò)分析目標(biāo)數(shù)據(jù)與歷史數(shù)據(jù)的PCA相似性因子,從舊的過(guò)程數(shù)據(jù)中篩選出與診斷目標(biāo)相似的數(shù)據(jù),構(gòu)成待選數(shù)據(jù)池；然后采用距離相似性因子,從待選數(shù)據(jù)池中選擇出與目標(biāo)數(shù)據(jù)最相似的數(shù)據(jù)用于輔助訓(xùn)練。將該方法用于轉(zhuǎn)子故障的不均衡數(shù)據(jù)分類中,在不同偏斜率下采用KPCA-SVM方法進(jìn)行故障分類。結(jié)果表明,該方法可有效地改善分類決策邊界,降低由樣本不均衡而引起的誤診斷率。 (4)基于測(cè)試測(cè)量?jī)x器發(fā)展中“虛擬化”、“控件化”的發(fā)展方向,對(duì)智能控件化虛擬儀器儀表的系統(tǒng)軟件構(gòu)架及其應(yīng)用開展研究。在C#軟件平臺(tái)下,提出了轉(zhuǎn)子系統(tǒng)故障數(shù)據(jù)采集的實(shí)驗(yàn)系統(tǒng)方案,嘗試對(duì)以下模塊開展設(shè)計(jì)：波形顯示模塊、電機(jī)控制模塊、數(shù)據(jù)存儲(chǔ)模塊。
[Abstract]:With the rapid development of information science and technology, computer technology and various intelligent instruments have been widely used in the monitoring of mechanical equipment. The massive process data reflecting the running state of the system has been collected and stored. However, there are the defects of "rich data, but lack of information". Based on these off-line operation data and intelligent data analysis algorithm, a quantitative feature model which can scientifically describe the running state of mechanical equipment is established. The realization of intelligent automatic identification of machine faults in the development of mechanical equipment information technology plays a very active role. Therefore, starting from the construction of quantitative feature pattern reflecting the characteristics of mechanical equipment information, and based on the principle of knowledge discovery in data mining, this paper revolves around the use of intelligent data analysis tools. The research work of fault monitoring and diagnosis method based on data drive is carried out. By using the common algorithm of data-driven fault diagnosis, the construction of quantitative feature mode reflecting the characteristics of mechanical equipment information and the classification method of unbalanced fault data set are discussed in order to quantitatively describe the operation status of the unit. The online diagnosis of fault mode is realized. The main research work of this paper includes the following aspects: (1) the extraction method of multi-domain features is introduced, and the fault data classification method of KPCA-SVM is studied. The application of this method in rotor system fault diagnosis is also discussed. (2) aiming at the problem of quantitative feature description of fault information, a weighted KPCA method for feature selection and feature information fusion is proposed. Firstly, the multi-domain feature parameters of time domain, frequency domain and time-frequency domain are extracted from the vibration signal of a single channel, and the sensitive features conducive to fault pattern identification are screened out by feature selection method. Secondly, the fusion feature vector is obtained by fusion of the sensitive features of multi-channel, and then the kernel principal components of the fusion feature vector are extracted by weighted KPCA method. The experimental results of SVM classifiers show that the algorithm can effectively identify different fault types. (3) in order to solve the problems of low classification accuracy and low identification efficiency of unbalanced fault data, a similarity factor analysis method based on sliding window is proposed. In this method, the sliding window technology is introduced, and the PCA similarity factor between the target data and the historical data is analyzed, and the data similar to the diagnostic target is screened out from the old process data to form the data pool to be selected. Then the distance similarity factor is used to select the data most similar to the target data from the data pool to be selected for auxiliary training. This method is applied to the unbalanced data classification of rotor faults, and the KPCA-SVM method is used for fault classification under different slope. The results show that this method can effectively improve the boundary of classification decision and reduce the misdiagnosis rate caused by the imbalance of samples. (4) based on the development direction of "virtualization" and "control" in the development of test and measurement instruments, the system software architecture and application of intelligent control virtual instruments are studied. Under the platform of C # software, the experimental system scheme of rotor system fault data acquisition is put forward, and the following modules are designed: waveform display module, motor control module, data storage module.
【學(xué)位授予單位】：蘭州理工大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2013
【分類號(hào)】：TH165.3

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 張敬芬,趙德有;基于模糊神經(jīng)網(wǎng)絡(luò)和數(shù)據(jù)融合的結(jié)構(gòu)裂紋故障診斷[J];船舶力學(xué);2004年02期

2 謝春麗,夏虹,劉永闊;多傳感器數(shù)據(jù)融合技術(shù)在故障診斷中的應(yīng)用[J];傳感器技術(shù);2004年04期

3 李兵;張培林;任國(guó)全;劉東升;米雙山;;基于互信息的滾動(dòng)軸承故障特征選擇方法[J];測(cè)試技術(shù)學(xué)報(bào);2009年02期

4 李潔;高新波;焦李成;;基于特征加權(quán)的模糊聚類新算法[J];電子學(xué)報(bào);2006年01期

5 張萬(wàn)斌;;時(shí)頻域特征因子診斷滾動(dòng)軸承故障的試驗(yàn)研究[J];鞍鋼技術(shù);1993年10期

6 李巍華,廖廣蘭,史鐵林,楊叔子;基于核函數(shù)主元分析的機(jī)械設(shè)備狀態(tài)識(shí)別[J];華中科技大學(xué)學(xué)報(bào)(自然科學(xué)版);2002年12期

7 蔣玉嬌;王曉丹;王文軍;畢凱;;一種基于PCA和ReliefF的特征選擇方法[J];計(jì)算機(jī)工程與應(yīng)用;2010年26期

8 肖健華;吳今培;;樣本數(shù)目不對(duì)稱時(shí)的SVM模型[J];計(jì)算機(jī)科學(xué);2003年02期

9 劉天羽;李國(guó)正;;滾動(dòng)軸承故障診斷中數(shù)據(jù)不均衡問(wèn)題的研究[J];計(jì)算機(jī)工程與科學(xué);2010年05期

10 隋文濤;路長(zhǎng)厚;張丹;;基于加權(quán)FCM算法的軸承故障診斷[J];武漢理工大學(xué)學(xué)報(bào)(交通科學(xué)與工程版);2010年01期

相關(guān)博士學(xué)位論文 前7條

1 曾慶虎;機(jī)械傳動(dòng)系統(tǒng)關(guān)鍵零部件故障預(yù)測(cè)技術(shù)研究[D];國(guó)防科學(xué)技術(shù)大學(xué);2010年

2 胡友強(qiáng);數(shù)據(jù)驅(qū)動(dòng)的多元統(tǒng)計(jì)故障診斷及應(yīng)用[D];重慶大學(xué);2010年

3 雷亞國(guó);混合智能技術(shù)及其在故障診斷中的應(yīng)用研究[D];西安交通大學(xué);2007年

4 吳勝?gòu)?qiáng);核主元分析及證據(jù)理論的多域特征故障診斷新方法研究[D];燕山大學(xué);2011年

5 張麗新;高維數(shù)據(jù)的特征選擇及基于特征選擇的集成學(xué)習(xí)研究[D];清華大學(xué);2004年

6 彭兵;基于改進(jìn)支持向量機(jī)和特征信息融合的水電機(jī)組故障診斷[D];華中科技大學(xué);2008年

7 楊智明;面向不平衡數(shù)據(jù)的支持向量機(jī)分類方法研究[D];哈爾濱工業(yè)大學(xué);2009年

相關(guān)碩士學(xué)位論文 前6條

1 童憶瑩;基于增量聚類和ReliefF的特征選擇方法[D];西南大學(xué);2011年

2 霍天龍;基于支持向量機(jī)的轉(zhuǎn)子系統(tǒng)故障診斷方法研究[D];蘭州理工大學(xué);2011年

3 范先念;數(shù)據(jù)不平衡分類問(wèn)題研究[D];中國(guó)科學(xué)技術(shù)大學(xué);2011年

4 楊慧斌;滾動(dòng)軸承故障診斷中的特征提取與選擇方法[D];湖南工業(yè)大學(xué);2011年

5 向陽(yáng)輝;基于信息融合技術(shù)的旋轉(zhuǎn)機(jī)械故障診斷研究[D];中南大學(xué);2007年

6 馬再超;轉(zhuǎn)子故障數(shù)據(jù)分類方法研究與實(shí)驗(yàn)臺(tái)測(cè)試信息系統(tǒng)開發(fā)[D];蘭州理工大學(xué);2012年

，

本文編號(hào)：2494884