本文關(guān)鍵詞：基于變分模態(tài)分解與優(yōu)化多核支持向量機(jī)的旋轉(zhuǎn)機(jī)械早期故障診斷方法研究　出處：《重慶大學(xué)》2016年博士論文　論文類型：學(xué)位論文

  更多相關(guān)文章： 旋轉(zhuǎn)機(jī)械 早期故障診斷 變分模態(tài)分解 多核支持向量機(jī) 最大峭度相關(guān)反卷積

【摘要】：旋轉(zhuǎn)機(jī)械作為現(xiàn)代化工業(yè)生產(chǎn)中必不可少的工程設(shè)備,被廣泛應(yīng)用于化工、石油、冶金、電力等關(guān)系國(guó)計(jì)民生的重要領(lǐng)域。一旦旋轉(zhuǎn)機(jī)械設(shè)備發(fā)生故障輕則致使整個(gè)系統(tǒng)癱瘓?jiān)斐删薮蠼?jīng)濟(jì)損失,重則產(chǎn)生人員傷亡。研究表明旋轉(zhuǎn)機(jī)械早期故障階段具有較長(zhǎng)的潛伏期,如果能在旋轉(zhuǎn)機(jī)械設(shè)備故障萌芽即將出現(xiàn)、剛剛出現(xiàn)或故障程度比較輕微時(shí),準(zhǔn)確地預(yù)測(cè)故障可能發(fā)生的時(shí)間、部位以及故障類別,并據(jù)此指導(dǎo)旋轉(zhuǎn)機(jī)械設(shè)備的保養(yǎng)和維修工作,將有利于對(duì)旋轉(zhuǎn)機(jī)械設(shè)備故障發(fā)展進(jìn)行有效控制,并保障其安全可靠地運(yùn)行。旋轉(zhuǎn)機(jī)械早期振動(dòng)信號(hào)易受強(qiáng)背景噪聲干擾,同時(shí)受到傳輸路徑與信號(hào)衰減、傳播介質(zhì)與采集設(shè)備損耗等因素影響,進(jìn)一步弱化了振動(dòng)信號(hào)中包含的故障振動(dòng)信號(hào)信息;旋轉(zhuǎn)機(jī)械大多結(jié)構(gòu)復(fù)雜,故障源信號(hào)至測(cè)點(diǎn)位置為非線性傳播,同時(shí)運(yùn)行工況不穩(wěn)定、多部件耦合振動(dòng)、振動(dòng)干擾大等特點(diǎn),使得采集到的故障振動(dòng)信號(hào)具有強(qiáng)烈的非平穩(wěn)、非線性等特點(diǎn),導(dǎo)致故障振動(dòng)信號(hào)與設(shè)備狀態(tài)映射關(guān)系模糊,故障特征難以提取;旋轉(zhuǎn)機(jī)械早期故障樣本缺乏長(zhǎng)期性、系統(tǒng)性的收集,故障樣本稀缺且故障特征值和故障的類別無明確的映射關(guān)系,故障辨識(shí)難度大。論文針對(duì)旋轉(zhuǎn)機(jī)械微弱故障信號(hào)增強(qiáng)、非線性及非平穩(wěn)故障信號(hào)特征提取、小子樣故障診斷等問題,深入研究基于變分模態(tài)分解及優(yōu)化多核支持向量機(jī)的旋轉(zhuǎn)機(jī)械早期故障診斷方法,具體研究?jī)?nèi)容如下:(1)針對(duì)旋轉(zhuǎn)機(jī)械早期背景噪聲干擾大故障信息微弱的問題,提出自適應(yīng)最大相關(guān)峭度反卷積的微弱故障增強(qiáng)方法。以相關(guān)峭度作為評(píng)價(jià)指標(biāo),充分考慮早期故障振動(dòng)信號(hào)中所含沖擊成分的特性,通過迭代過程以實(shí)現(xiàn)解卷積運(yùn)算;利用小波Shannon熵作為目標(biāo)函數(shù),采用變步長(zhǎng)網(wǎng)格搜索法自動(dòng)搜尋最優(yōu)濾波器階數(shù)以及周期;使最大相關(guān)峭度反卷積方法在達(dá)到很好的效果的同時(shí)更具有自適應(yīng)性,從而有效地檢測(cè)出被噪聲淹沒的微弱故障;(2)針對(duì)旋轉(zhuǎn)機(jī)械故障信號(hào)非平穩(wěn)、非線性特征提取難的問題,提出自適應(yīng)變分模態(tài)分解的多頻帶多尺度樣本熵特征集構(gòu)建方法。利用不同頻帶上模態(tài)的多尺度樣本熵組成敏感特征向量集,表征旋轉(zhuǎn)機(jī)械早期故障狀態(tài)特征,進(jìn)而提高對(duì)旋轉(zhuǎn)機(jī)械早期故障狀態(tài)的辨識(shí)能力;(3)針對(duì)變分模態(tài)分解中一些關(guān)鍵參數(shù)選擇不確定的問題,提出自適應(yīng)變分模態(tài)分解方法;提出以VMD分解后各模態(tài)與原信號(hào)之間的相關(guān)性來保證分解的精度并指導(dǎo)最優(yōu)K值的確定;VMD分解中平衡約束參數(shù)越小,所得模態(tài)分量帶寬越大,易出現(xiàn)中心頻率重疊以及模態(tài)混疊的現(xiàn)象;通過仿真實(shí)驗(yàn)分析,提出在實(shí)際應(yīng)用中一般可取平衡約束參數(shù)為采樣頻率;研究分析了自適應(yīng)變分模態(tài)分解的性能:正交性能分析、能量保存度分析、等效濾波屬性分析;通過仿真實(shí)驗(yàn)分析得出:自適應(yīng)變分模態(tài)分解在正交性能、能量保存性能方面,均優(yōu)于EMD、EEMD、LMD方法;利用分?jǐn)?shù)高斯噪聲通過數(shù)值模擬實(shí)驗(yàn)對(duì)EMD、LMD、AVMD等效濾波屬性分析,相比于EMD和LMD,AVMD可以更接近于小波包分解,且是一種比EMD和LMD能提供更高的時(shí)頻分辨率的自適應(yīng)分解方法;對(duì)比研究了AVMD與EMD性能,發(fā)現(xiàn)當(dāng)有異常信息干擾時(shí),AVMD仍具有很好的效果;(4)針對(duì)旋轉(zhuǎn)機(jī)械早期故障樣本缺乏,提出基于免疫遺傳算法優(yōu)化多核支持向量機(jī)的旋轉(zhuǎn)機(jī)械小子樣故障診斷方法。通過引入權(quán)重因子將不同核函數(shù)組合學(xué)習(xí),基于全局核函數(shù)以及局部核函數(shù)構(gòu)造多核函數(shù),實(shí)現(xiàn)輸入特征向量到核函數(shù)空間的快速映射,算法泛化能力更好、模型解釋能力更強(qiáng);利用免疫遺傳算法獲取多核支持向量機(jī)最優(yōu)參數(shù),克服多核支持向量機(jī)參數(shù)選擇的不確定性,進(jìn)而提高多核支持向量機(jī)在旋轉(zhuǎn)機(jī)械小子樣振動(dòng)故障診斷中的穩(wěn)定性以及泛化推廣能力。文章最后對(duì)本文的工作進(jìn)行總結(jié),并展望下一步的研究方向。
[Abstract]:As the rotating machinery engineering equipment essential for modern industrial production, is widely used in chemical industry, petroleum, metallurgy, power and other important areas. Once the relationship beneficial to the people's livelihood rotating machinery fault light can lead to paralysis of the entire system caused huge economic losses and heavy casualties produced. The research showed that the early stage of failure of rotating machinery has a long incubation period if you can, in rotating machinery fault sprout will appear, or just appear relatively minor fault degree, accurate prediction of possible fault time, fault location and category, and then guide the rotating machinery equipment maintenance and repair work, will be conducive to the effective control of the equipment fault of rotating machinery development, and guarantee their safety reliable operation. The early vibration signal of rotating machinery is easily affected by strong background noise, at the same time by the transmission path and signal Effect of attenuation, propagation medium and acquisition equipment loss and other factors, further weakening the fault vibration signal information contained in the vibration signal of rotating machinery; most complicated structure, fault source signal to the measuring point for nonlinear propagation, and unstable running, multi components coupling vibration, vibration characteristics of high noise, the fault vibration signal the collected with strong non-stationary, non-linear characteristics, cause the fault vibration signal and device state mapping relation to fuzzy, fault feature extraction of rotating machinery early fault samples; lack of long-term, systematic collection, no explicit mappings between fault samples are scarce and fault characteristic value and fault type, fault identification difficult for weak fault signal of rotating machinery to enhance the extraction of nonlinear and nonstationary fault signal characteristics, fault diagnosis of small sample problems, in-depth research base In the early fault diagnosis of rotating machinery based on variational modal decomposition and optimization of multiple kernel support vector machine, the specific contents are as follows: (1) for rotating machinery early background noise interference problems of weak fault information, the fault adaptive maximum correlation kurtosis deconvolution enhancement method. Related to the kurtosis as the evaluation index, fully considering the characteristics of early fault vibration signal contained in the impact component, through the iterative process to achieve the deconvolution method; using wavelet Shannon entropy as the objective function, the automatic search for the optimal filter order and cycle using variable step grid search method; the maximum correlation kurtosis deconvolution method is more adaptive to achieve good results at the same time thus, effectively detect weak fault submerged by the noise; (2) according to the fault signal of rotating machinery non-stationary, nonlinear feature extraction problem,. The adaptive variational modal decomposition of multi band multiscale sample entropy feature construction method. Sensitive feature vector set using multi-scale sample entropy of different frequency modes, characterization of rotating machinery early fault characteristics, and improve the ability to identify early fault of rotating machinery condition; (3) according to the variation in mode decomposition the problem of determining the choice of some key parameters, an adaptive variational modal decomposition method; the correlation between VMD after the decomposition of the original signal mode and to ensure the accuracy of determining decomposition and guide the optimal K value; VMD decomposition equilibrium constraint parameter is smaller, the modal components more bandwidth, center frequency and prone to overlap the modal aliasing phenomenon; through simulation analysis, put forward in the practical application of general equilibrium constraint parameters for the sampling frequency; analysis of the adaptive variational modal decomposition Performance: the orthogonal performance analysis, energy saving analysis, analysis of equivalent filter attributes; through the simulation analysis results show that the adaptive variational modal decomposition in orthogonal performance, energy saving performance, are better than those of EMD, EEMD, LMD; through numerical simulation experiments on EMD, LMD using fractional Gauss noise analysis, AVMD equivalent filter properties compared to EMD, AVMD and LMD, can be more close to the wavelet packet decomposition, which is an adaptive than EMD and LMD can provide higher time-frequency resolution decomposition method; comparison of AVMD and EMD performance, found that when there are abnormal interference information, AVMD still has a very good effect; (4) according to the early fault of rotating machinery like lack of samples, proposed methods for fault diagnosis of rotating machines. The optimization of multi kernel support vector machine based on immune genetic algorithm. By introducing a weighting factor of different kernel function combination learning, global kernel function based on And the local kernel structure of multi kernel function, fast mapping input vectors to the kernel space, better generalization capability, the ability to explain the model by using immune genetic algorithm gets stronger; multi kernel support vector machine optimized parameters, parameter selection of support vector machines to overcome the uncertainty of multi kernel support, and improve the stability of the multi kernel support vector machine in the vibration fault diagnosis of rotating machinery in small sample and generalization ability. Finally, a summary of this paper, and the prospect of the next research direction.

【學(xué)位授予單位】：重慶大學(xué)
【學(xué)位級(jí)別】：博士
【學(xué)位授予年份】：2016
【分類號(hào)】：TH17

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 吳占濤;程軍圣;曾鳴;鄭近德;;基于分段多項(xiàng)式的局部特征尺度分解方法及應(yīng)用[J];振動(dòng)與沖擊;2016年04期

2 武英杰;甄成剛;劉長(zhǎng)良;;變分模態(tài)分解在風(fēng)電機(jī)組故障診斷中的應(yīng)用[J];機(jī)械傳動(dòng);2015年10期

3 陳立軍;張海勇;韓東;;基于VMD和HSA的水聲跳頻信號(hào)時(shí)頻分析方法[J];科學(xué)技術(shù)與工程;2015年28期

4 任學(xué)平;張玉皓;邢義通;王朝閣;;基于角域級(jí)聯(lián)最大相關(guān)峭度反褶積的滾動(dòng)軸承早期故障診斷[J];儀器儀表學(xué)報(bào);2015年09期

5 冷軍發(fā);郭松濤;荊雙喜;李新華;;基于最小熵解卷積的帶式輸送機(jī)傳動(dòng)滾筒軸承故障診斷[J];河南理工大學(xué)學(xué)報(bào)(自然科學(xué)版);2015年04期

6 鐘先友;趙春華;陳保家;田紅亮;;基于MCKD和包絡(luò)譜的旋轉(zhuǎn)機(jī)械故障診斷方法[J];機(jī)械傳動(dòng);2015年07期

7 唐貴基;王曉龍;;最大相關(guān)峭度解卷積結(jié)合1.5維譜的滾動(dòng)軸承早期故障特征提取方法[J];振動(dòng)與沖擊;2015年12期

8 唐貴基;王曉龍;;最大相關(guān)峭度解卷積結(jié)合稀疏編碼收縮的齒輪微弱故障特征提取[J];振動(dòng)工程學(xué)報(bào);2015年03期

9 唐貴基;王曉龍;;基于包絡(luò)譜稀疏度和最大相關(guān)峭度解卷積的滾動(dòng)軸承早期故障診斷方法[J];中國(guó)機(jī)械工程;2015年11期

10 隋文濤;張丹;Wilson Wang;;基于EMD和MKD的滾動(dòng)軸承故障診斷方法[J];振動(dòng)與沖擊;2015年09期

相關(guān)博士學(xué)位論文 前10條

1 蘇祖強(qiáng);基于泛化流形學(xué)習(xí)的風(fēng)電機(jī)組傳動(dòng)系統(tǒng)早期故障診斷方法研究[D];重慶大學(xué);2015年

2 鐘先友;旋轉(zhuǎn)機(jī)械故障診斷的時(shí)頻分析方法及其應(yīng)用研究[D];武漢科技大學(xué);2014年

3 楊賢昭;基于經(jīng)驗(yàn)?zāi)B(tài)分解的故障診斷方法研究[D];武漢科技大學(xué);2012年

4 陳仁祥;振動(dòng)譜表征空間滾動(dòng)軸承壽命狀態(tài)方法研究[D];重慶大學(xué);2012年

5 趙志宏;基于振動(dòng)信號(hào)的機(jī)械故障特征提取與診斷研究[D];北京交通大學(xué);2012年

6 李鋒;基于流形學(xué)習(xí)的風(fēng)電機(jī)組傳動(dòng)系統(tǒng)故障診斷方法研究[D];重慶大學(xué);2011年

7 鞠萍華;旋轉(zhuǎn)機(jī)械早期故障特征提取的時(shí)頻分析方法研究[D];重慶大學(xué);2010年

8 李寧;旋轉(zhuǎn)機(jī)械的測(cè)試信號(hào)分析及隱馬爾科夫模型應(yīng)用研究[D];重慶大學(xué);2010年

9 王衍學(xué);機(jī)械故障監(jiān)測(cè)診斷的若干新方法及其應(yīng)用研究[D];西安交通大學(xué);2009年

10 岳]Z;粗粒度并行遺傳算法的計(jì)算性能及其應(yīng)用研究[D];華中科技大學(xué);2008年

相關(guān)碩士學(xué)位論文 前10條

1 季艷;基于DEMD時(shí)頻分析的旋轉(zhuǎn)機(jī)械故障特征提取方法研究[D];燕山大學(xué);2015年

2 王亞超;基于局部均值分解的旋轉(zhuǎn)機(jī)械故障診斷技術(shù)研究[D];燕山大學(xué);2015年

3 趙沖;基于免疫遺傳算法的雙柱懸索拉線塔優(yōu)化分析[D];重慶大學(xué);2014年

4 練曉婷;旋轉(zhuǎn)機(jī)械故障早期識(shí)別方法研究與應(yīng)用[D];大連理工大學(xué);2013年

5 原平;基于EMD近似熵和LS-SVM的齒輪箱故障診斷研究[D];中北大學(xué);2013年

6 江瑞龍;基于最小熵解卷積的滾動(dòng)軸承故障診斷研究[D];上海交通大學(xué);2013年

7 徐繼剛;滾動(dòng)軸承振動(dòng)信號(hào)處理與故障辨識(shí)方法研究[D];蘭州理工大學(xué);2012年

8 楊怡;基于局部均值分解的齒輪故障診斷方法[D];湖南大學(xué);2012年

9 王健峰;基于改進(jìn)網(wǎng)格搜索法SVM參數(shù)優(yōu)化的說話人識(shí)別研究[D];哈爾濱工程大學(xué);2012年

10 王梅;一種改進(jìn)的核函數(shù)參數(shù)選擇方法[D];西安科技大學(xué);2011年

，

本文編號(hào)：1378973