本文選題：特征選擇 + 智能診斷��； 參考：《蘭州理工大學(xué)》2013年碩士論文

【摘要】：旋轉(zhuǎn)機(jī)械是電力、化工等行業(yè)生產(chǎn)中的關(guān)鍵設(shè)備,對(duì)旋轉(zhuǎn)機(jī)械設(shè)備進(jìn)行狀態(tài)監(jiān)測(cè)和故障診斷以保證設(shè)備的安全、可靠運(yùn)行具有重要的經(jīng)濟(jì)價(jià)值。隨著信息技術(shù)、現(xiàn)代控制理論和人工智能的發(fā)展,自動(dòng)化和智能化逐漸成為故障診斷系統(tǒng)的發(fā)展方向。然而故障診斷技術(shù)發(fā)展到現(xiàn)在,仍然面臨著支撐理論存在局限性、規(guī)則獲取困難、診斷模型難以實(shí)際應(yīng)用等各種問(wèn)題。 本研究針對(duì)在轉(zhuǎn)子故障診斷中,特征的選擇缺乏可靠的依據(jù)、多通道信息融合造成的特征冗余問(wèn)題以及故障識(shí)別精度不高的問(wèn)題,研究了基于K-W檢驗(yàn)特征選擇與CRFS識(shí)別的故障診斷模型在轉(zhuǎn)子故障診斷中的應(yīng)用,開(kāi)辟了轉(zhuǎn)子故障診斷的新途徑。本文的主要工作和研究結(jié)論如下： 1)針對(duì)常用的故障特征種類繁多,對(duì)其選擇缺乏可靠依據(jù)和針對(duì)性不強(qiáng)的問(wèn)題,通過(guò)對(duì)不同故障類型樣本同一特征的數(shù)據(jù)區(qū)間進(jìn)行分析,篩選出了數(shù)據(jù)區(qū)間重疊較小的具備較強(qiáng)表征轉(zhuǎn)子不同運(yùn)行狀態(tài)能力的特征。以此為依據(jù),建立了轉(zhuǎn)子原始故障特征數(shù)據(jù)集。 2)針對(duì)多通道監(jiān)測(cè)、數(shù)據(jù)采集能夠更加全面的反映轉(zhuǎn)子運(yùn)行狀態(tài),但對(duì)故障特征集的建立造成了維數(shù)過(guò)高、不同類別子集間可分性差的問(wèn)題,研究了K-W檢驗(yàn)特征選擇方法,簡(jiǎn)化了算法并與主成分分析(PCA)進(jìn)行對(duì)比分析,實(shí)驗(yàn)驗(yàn)的證結(jié)果表明,K-W檢驗(yàn)特征選擇的結(jié)果空間聚類緊致,降維效果和算法復(fù)雜度均優(yōu)于主成分分析法。 3)將條件隨機(jī)場(chǎng)模型(CRFS)引入到轉(zhuǎn)子故障診斷中,并將經(jīng)過(guò)特征優(yōu)化后的數(shù)據(jù)輸入CRFS進(jìn)行參數(shù)學(xué)習(xí)和樣本訓(xùn)練,實(shí)驗(yàn)結(jié)果表明條件隨機(jī)場(chǎng)穩(wěn)定性好且識(shí)別準(zhǔn)確率高,大量特征疊加對(duì)識(shí)別精度的影響并不大。通過(guò)與HMM模型對(duì)比分析表明,在條件復(fù)雜、故障種類較多以及特征相似時(shí)HMM模型診斷率會(huì)明顯下降且訓(xùn)練較慢,而CRFS所有特征可以進(jìn)行全局歸一化,能夠求得全局的最優(yōu)解,在多故障診斷中表現(xiàn)出了優(yōu)良的性能。 4)利用虛擬儀器技術(shù)開(kāi)發(fā)了一套集實(shí)時(shí)狀態(tài)監(jiān)測(cè)、預(yù)警、振動(dòng)信號(hào)分析、振動(dòng)數(shù)據(jù)和特征數(shù)據(jù)存儲(chǔ)、報(bào)表自動(dòng)生成及遠(yuǎn)程網(wǎng)絡(luò)訪問(wèn)等功能于一體的機(jī)械振動(dòng)自動(dòng)測(cè)試分析信息系統(tǒng)。在實(shí)驗(yàn)研究以及工程應(yīng)用中均取得了較好的效果。 研究表明,通過(guò)特征降維、特征選擇能夠獲得具備較好的類別可分性的故障特征向量,故如何在智能故障診斷算法研究中獲得新突破,及如何將智能診斷算法合理地嵌入于自動(dòng)化測(cè)控系統(tǒng),將是故障診斷領(lǐng)域開(kāi)展研究工作的重要方向。
[Abstract]:Rotating machinery is the key equipment in the production of electric power and chemical industry. It is of great economic value to monitor and diagnose the status of rotating machinery and equipment to ensure the safety and reliable operation of the equipment. With the development of information technology, modern control theory and artificial intelligence, automation and intelligence are becoming the developing direction of fault diagnosis system. However, with the development of fault diagnosis technology, it still faces many problems, such as the limitation of supporting theory, the difficulty of obtaining rules, the difficulty of practical application of diagnostic model, and so on. This study aims at the lack of reliable basis for feature selection in rotor fault diagnosis, the problem of feature redundancy caused by multi-channel information fusion and the problem of low fault identification accuracy. The application of fault diagnosis model based on K-W test feature selection and CRFS identification in rotor fault diagnosis is studied, which opens a new way for rotor fault diagnosis. The main work and conclusions of this paper are as follows: 1) aiming at the problems of the variety of common fault features, the lack of reliable basis for their selection and the lack of pertinence, the data interval of the same feature of different fault types is analyzed. The characteristics of the rotor with little overlap in the data interval are selected, which can represent the different running states of the rotor. Based on this, the original fault feature data set of rotor is established. 2) in view of multi-channel monitoring, data acquisition can reflect rotor running state more comprehensively, but the establishment of fault feature set leads to the problems of high dimension and poor separability among different subsets, so the K-W test feature selection method is studied. The algorithm is simplified and compared with the principal component analysis (PCA). The experimental results show that the result space of the feature selection of K-W test is compact, the dimension reduction effect and the complexity of the algorithm are better than that of the principal component analysis. 3) the conditional random field model (CRFs) is introduced into rotor fault diagnosis, and the data after feature optimization is input into CRFS for parameter learning and sample training. The experimental results show that the conditional random field has good stability and high recognition accuracy. The superposition of a large number of features has little effect on the recognition accuracy. Compared with HMM model, it is shown that the diagnostic rate of HMM model decreases obviously and the training is slower when the conditions are complex, there are many kinds of faults and the characteristics are similar, while all the features of CRFS can be normalized globally and the global optimal solution can be obtained. It shows excellent performance in multi-fault diagnosis. 4) A set of real-time state monitoring, early warning, vibration signal analysis, vibration data and feature data storage are developed by using virtual instrument technology. Automatic test and analysis information system for mechanical vibration with automatic report generation and remote network access. Good results have been obtained in both experimental research and engineering application. The research shows that feature selection can obtain fault feature vector with better classification by feature reduction, so how to make a breakthrough in intelligent fault diagnosis algorithm. And how to embed the intelligent diagnosis algorithm into the automatic measurement and control system reasonably will be an important research direction in the field of fault diagnosis.
【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 胡海峰;安茂春;秦國(guó)軍;胡蔦慶;;基于隱半Markov模型的故障診斷和故障預(yù)測(cè)方法研究[J];兵工學(xué)報(bào);2009年01期

2 黃德根;李澤中;萬(wàn)如;;基于SVM和CRF的雙層模型中文機(jī)構(gòu)名識(shí)別[J];大連理工大學(xué)學(xué)報(bào);2010年05期

3 周俊生;戴新宇;尹存燕;陳家駿;;基于層疊條件隨機(jī)場(chǎng)模型的中文機(jī)構(gòu)名自動(dòng)識(shí)別[J];電子學(xué)報(bào);2006年05期

4 付勝;張亞彬;;基于模糊理論的水泵監(jiān)測(cè)及故障診斷系統(tǒng)開(kāi)發(fā)[J];北京工業(yè)大學(xué)學(xué)報(bào);2012年07期

5 蔡秀紅;;轉(zhuǎn)子不對(duì)中的分析和處理[J];化工機(jī)械;2010年03期

6 羅榮華;閔華清;;用于移動(dòng)機(jī)器人多目標(biāo)跟蹤的混合條件隨機(jī)場(chǎng)[J];華南理工大學(xué)學(xué)報(bào)(自然科學(xué)版);2011年05期

7 朱文球;劉強(qiáng);;基于條件隨機(jī)域的上下文人類動(dòng)作識(shí)別[J];計(jì)算機(jī)工程與應(yīng)用;2008年28期

8 張勇;陳莉;;聚類與PCA融合的特征提取方法研究[J];計(jì)算機(jī)工程與應(yīng)用;2010年11期

9 吳曉鋒;宗成慶;;一種基于LDA的CRF自動(dòng)文摘方法[J];中文信息學(xué)報(bào);2009年06期

10 任海軍;賀利樂(lè);;機(jī)械設(shè)備轉(zhuǎn)子不平衡的診斷與平衡[J];煤礦機(jī)械;2007年07期

相關(guān)博士學(xué)位論文 前5條

1 何學(xué)文;基于支持向量機(jī)的故障智能診斷理論與方法研究[D];中南大學(xué);2004年

2 許雪琦;分布式智能化狀態(tài)監(jiān)測(cè)與故障診斷系統(tǒng)的設(shè)計(jì)與研究[D];天津大學(xué);2004年

3 吳敬東;轉(zhuǎn)子系統(tǒng)碰摩的若干非線性動(dòng)力學(xué)問(wèn)題研究[D];東北大學(xué);2006年

4 y囈黃，

本文編號(hào)：1841413