本文選題：希爾伯特-黃變換 + 核方法�。� 參考：《中國礦業(yè)大學》2013年博士論文

【摘要】：機械設備在線監(jiān)測是企業(yè)安全生產(chǎn)、產(chǎn)品質(zhì)量保證的關(guān)鍵。一方面機械設備結(jié)構(gòu)、運行狀態(tài)復雜難以建立準確的數(shù)學模型，另一方面設備運行狀態(tài)數(shù)據(jù)量大，非線性度高、噪聲干擾強、不確定等特性使得故障診斷比較困難。本論文借鑒機器學習、故障診斷、人工智能等理論和應用成果，對復雜機械設備的智能故障檢測、診斷進行了深入研究，主要內(nèi)容有： (1)復雜非線性、動態(tài)信號處理以及故障統(tǒng)計量構(gòu)造研究。該方法使用希爾伯特-黃變換（Hilbert-Huang Transform，HHT）振動信號分解到感興趣的子頻帶；然后使用HHT把子頻帶信號分解為多個內(nèi)蘊模式函數(shù)(Intrinsic Mode Function, IMF)，根據(jù)IMF系數(shù)的鄰域相關(guān)性去噪，基于信號能量準則消除虛假IMF；提出基于數(shù)據(jù)依賴KICA（Data Dependent Kernel Component Analysisn, DDKICA）獲取描述過程特征的內(nèi)蘊信息，，給出經(jīng)驗特征空間的DDKICA模型選擇準則；最后根據(jù)抽取的時頻域特征分布使用支持向量描述(Support Vector Data Description, SVDD)構(gòu)造新的統(tǒng)計量、確定置信度進行故障監(jiān)控。研究表明該方法能夠及時發(fā)現(xiàn)異常情況。 (2)基于多尺度理論的振動信號去噪和故障特征提取。分析了形態(tài)梯度小波的多尺度特性及其特點，使用形態(tài)梯度小波對振動信號進行多尺度分解，對各層的細節(jié)系數(shù)進行軟閾值降噪處理，然后進行信號重構(gòu)；對降噪后的信號采用S-變換進行多分辨率時頻分析，從S變換譜圖中提取故障特征。仿真和實例證明該方法能有效提取故障特征，適合在線監(jiān)測和診斷。 (3)先進機器學習理論在提升機故障監(jiān)控研究和應用。針對具有冗余、異構(gòu)（heterogenous）和多尺度特性的高維數(shù)據(jù)集，本文提出多核正交局部鑒別分析和全局保持（Multiple Kernel Orthogonal Locality Discriminative Analysis with GlobalityPreserving, MKOLDAGP）維數(shù)約簡算法。該方法不僅保證了低維特征空間與原始數(shù)據(jù)空間具有相似的幾何結(jié)構(gòu)，具有更好的鑒別特性，而且使得數(shù)據(jù)局部聚類概率密度近似服從高斯分布。最后給出基于GMM的故障監(jiān)測和故障統(tǒng)計量，較好地克服了現(xiàn)有因非線性、非高斯特性而導致高斯混合模型（Gaussian Mixture Model,GMM）的故障監(jiān)測性能下降問題。仿真實驗表明了本算法可以有效抽取數(shù)據(jù)特征，有較強的故障檢測能力。 (4)不平衡數(shù)據(jù)集的v-NSVDD多分類研究。分析了多類支持向量數(shù)據(jù)描述(support vector data description,SVDD)算法存在的問題，提出一種新的不平衡數(shù)據(jù)v-NSVDD多分類算法。該方法基于不同類別樣本間隔最大原理，較好地克服噪聲和在野點的影響，提高了分類模型的泛化性能；通過樣本加權(quán)的方法解決了不平衡類別樣本預測精度低的問題，并在理論上給出了根據(jù)類別樣本數(shù)量設置樣本加權(quán)系數(shù)的方法。為實現(xiàn)多分類器拒判，防止因每個分類器的核函數(shù)參數(shù)不同而影響判決結(jié)果的準確性和可靠性，本文給出基于相對距離和K-NN規(guī)則相結(jié)合的多分類方法。使用Benchmark數(shù)據(jù)集。進行仿真實驗，結(jié)果表明本算法能夠獲得較低的分類誤差，能夠有效處理樣本不平衡問題。
[Abstract]:The on - line monitoring of mechanical equipment is the key to enterprise safety production and product quality assurance . On the one hand , it is difficult to establish an accurate mathematical model on the structure of mechanical equipment and operation state . On the other hand , it is difficult to establish an accurate mathematical model on the other hand , such as machine learning , fault diagnosis , artificial intelligence and so on .

( 1 ) The structure of complex nonlinear , dynamic signal processing and fault statistics is studied . Hilbert - Huang Transform ( HHT ) vibration signal is used to decompose the Hilbert - Huang Transform ( HHT ) vibration signal to the sub - band of interest ;
then using the HHT to decompose the subband signals into a plurality of intrinsic mode functions ( IMF ) , de - noising based on the neighborhood correlation of the IMF coefficients , and eliminating the false IMF based on the signal energy criterion ;
The data dependent Kernel Component ( DDKICA ) is proposed to obtain the intrinsic information describing the process characteristics , and the DDKICA model selection criterion of the empirical feature space is given .
Finally , based on the extracted time - domain feature distribution , a new statistic is constructed using Support Vector Data Description ( SVDD ) , and the confidence is determined to be fault - monitored . The research shows that the method can detect the abnormal condition in time .

( 2 ) The vibration signal de - noising and fault feature extraction based on the multi - scale theory are analyzed . The multi - scale characteristics and characteristics of the morphological gradient wavelet are analyzed , the multi - scale decomposition of the vibration signals is carried out by using the morphological gradient wavelet , the detail coefficients of each layer are soft - threshold denoising and then the signal reconstruction is carried out ;
The multi - resolution time - frequency analysis of the signal after noise reduction is carried out by using S - transform . The fault feature is extracted from the S - transform spectrum diagram . Simulation and examples show that the method can effectively extract fault features and is suitable for on - line monitoring and diagnosis .

( 3 ) The research and application of advanced machine learning theory in the fault monitoring of hoist . Aiming at the high - dimensional data set with redundant , heterogeneous and multi - scale characteristics , this paper puts forward multi - core orthogonal partial differential analysis and global preserving ( Multiple Kernel Orthogonal Locality Analysis with Globality Analysis , MKOLDAGP ) dimension reduction algorithm .

( 4 ) v - nSVDD multi - classification research of unbalanced data set . The problem of support vector data description ( SVDD ) algorithm is analyzed . A new multi - classification algorithm for unbalanced data v - NSVDD is presented .
In this paper , the problem of low prediction accuracy of unbalanced class samples is solved by means of sample weighted method , and the method of setting sample weighting coefficients according to the number of class samples is given . In order to realize multi - classifier rejection , it is possible to prevent the accuracy and reliability of the decision result due to different kernel function parameters of each classifier . The paper gives a multi - classification method based on relative distance and K - NN rule . The simulation experiment is carried out using Benchmark data set . The results show that the algorithm can obtain lower classification error and can effectively deal with the problem of sample imbalance .

【學位授予單位】：中國礦業(yè)大學
【學位級別】：博士
【學位授予年份】：2013
【分類號】：TH165.3

【參考文獻】

相關(guān)期刊論文 前10條

1 胡海峰;安茂春;秦國軍;胡蔦慶;;基于隱半Markov模型的故障診斷和故障預測方法研究[J];兵工學報;2009年01期

2 劉毅華;王媛媛;宋執(zhí)環(huán);;基于平穩(wěn)小波包分解和希爾伯特變換的故障特征自適應提取[J];電工技術(shù)學報;2009年02期

3 馬宏忠;姚華陽;黎華敏;;基于Hilbert模量頻譜分析的異步電機轉(zhuǎn)子斷條故障研究[J];電機與控制學報;2009年03期

4 韓璞,張君,董澤,潘笑;汽輪機振動信號的最優(yōu)小波包基消噪與檢測[J];動力工程;2005年01期

5 陳峗,張中杰,田小波;基于加窗Hilbert變換的復偏振分析方法及其應用[J];地球物理學報;2005年04期

6 朱孝開;楊德貴;;基于推廣能力測度的多類SVDD模式識別方法[J];電子學報;2009年03期

7 何正嘉;孫海亮;訾艷陽;;自適應多小波基函數(shù)構(gòu)造與機械故障診斷應用研究[J];中國工程科學;2011年10期

8 劉小平;許桂云;任世錦;楊茂云;;形態(tài)梯度小波降噪與S變換的齒輪故障特征抽取算法[J];電子設計工程;2012年22期

9 王曉建;王玲;彭啟琮;;部分HHT和ICA的混合語音增強算法[J];電子科技大學學報;2008年S1期

10 許仙珍;謝磊;王樹青;;基于PCA混合模型的多工況過程監(jiān)控[J];化工學報;2011年03期

相關(guān)博士學位論文 前7條

1 王廣斌;基于流形學習的旋轉(zhuǎn)機械故障診斷方法研究[D];中南大學;2010年

2 胡蔦慶;轉(zhuǎn)子碰摩非線性行為與故障辨識的研究[D];國防科學技術(shù)大學;2001年

3 余紅英;機械系統(tǒng)故障信號特征提取技術(shù)研究[D];中北大學;2005年

4 李加文;盲信號理論及在機械設備故障檢測與分析中的應用研究[D];上海交通大學;2006年

5 李岳;機械動力傳動系統(tǒng)核基故障識別與狀態(tài)預測技術(shù)研究[D];國防科學技術(shù)大學;2007年

6 安學利;水力發(fā)電機組軸系振動特性及其故障診斷策略[D];華中科技大學;2009年

7 竇唯;旋轉(zhuǎn)機械振動故障診斷的圖形識別方法研究[D];哈爾濱工業(yè)大學;2009年

本文編號：1784614