本文選題：非高斯 + 最大方差展開　； 參考：《華東理工大學(xué)》2015年碩士論文

【摘要】：隨著國民經(jīng)濟(jì)的快速發(fā)展以及人民生活水平的顯著提高,整個社會對流程工業(yè)的生產(chǎn)制造提出越來越高的要求,其安全與穩(wěn)定不容小覷。保證生產(chǎn)安全和提高產(chǎn)品質(zhì)量是流程工業(yè)亟待解決的問題,過程監(jiān)控技術(shù)的合理運(yùn)用是解決這些問題的有效途徑。由于近年來計(jì)算機(jī)控制系統(tǒng)和智能儀表在生產(chǎn)中的應(yīng)用,可以獲取大量數(shù)據(jù)。通過對過程數(shù)據(jù)的統(tǒng)計(jì)分析進(jìn)而對系統(tǒng)的運(yùn)行狀態(tài)進(jìn)行監(jiān)控,已然成為近年來的熱門研究領(lǐng)域。多變量統(tǒng)計(jì)過程監(jiān)控(Multivariate Statistical Process Monitoring, MSPM)方法作為一種重要的基于數(shù)據(jù)驅(qū)動的監(jiān)控方法,受到了學(xué)術(shù)界和工業(yè)界的普遍關(guān)注。 但是,傳統(tǒng)MSPM方法受到過程中的很多條件限制,例如過程數(shù)據(jù)應(yīng)盡量滿足線性關(guān)系、高斯分布。然而實(shí)際工業(yè)由于種種因素的影響,數(shù)據(jù)變量間呈現(xiàn)強(qiáng)非線性以及非高斯分布等關(guān)系。因此,在前人研究的基礎(chǔ)上,對實(shí)際工業(yè)中存在的問題進(jìn)行了分析,進(jìn)行了如下工作： 1.針對傳統(tǒng)監(jiān)控方法在處理數(shù)據(jù)進(jìn)行建模時(shí)破壞非線性結(jié)構(gòu),監(jiān)控效率不高的情況,提出了一種基于否定選擇算法(Negative Selection Algorithm, NSA)的過程監(jiān)控方法。該方法首先采用最大方差展開(Maximum Variance Unfolding, MVU)方法從原始數(shù)據(jù)中提取低維流形,再利用NSA對低維流形進(jìn)行建模得到“超球體群”模型,從而實(shí)現(xiàn)對過程的監(jiān)控。TE平臺仿真表明提出的方法較其他方法具有更好的檢測能力。 2.針對支持向量數(shù)據(jù)描述(Support Vector Data Description, SVDD)方法在處理大樣本時(shí)遇到的“維數(shù)災(zāi)難”的問題,同時(shí)利用其在處理小樣本數(shù)據(jù)獨(dú)有的優(yōu)勢,提出了一種基于LTSA-Greedy-SVDD的過程監(jiān)控方法。該方法首先引入局部切空間排列(Local Tangent Space Alignment, LTSA)算法提取低維流形,之后引入Greedy方法提取特征建模樣本,從而大大地減少了運(yùn)算時(shí)間。TE平臺仿真以及應(yīng)用仿真表明了該方法的有效性。 3.針對過程數(shù)據(jù)是高斯分布和非高斯分布的混合體等問題,提出了一種基于加權(quán)聯(lián)合指標(biāo)的過程監(jiān)控方法。該方法利用非高斯-高斯兩步策略提取過程數(shù)據(jù)的有用信息建立統(tǒng)計(jì)模型,之后采用加權(quán)策略對兩個統(tǒng)計(jì)量進(jìn)行加權(quán)得到新的統(tǒng)計(jì)指標(biāo)�；诩訖�(quán)聯(lián)合指標(biāo)的監(jiān)控方法的有效性在數(shù)值系統(tǒng)仿真中得到了驗(yàn)證。TE過程仿真和工業(yè)應(yīng)用也都表明了提出的方法的有效性。
[Abstract]:With the rapid development of the national economy and the remarkable improvement of the people's living standard, the whole society has put forward more and more high requirements for the production and manufacture of the process industry, and its safety and stability should not be underestimated.Ensuring production safety and improving product quality are the urgent problems to be solved in process industry, and the rational application of process monitoring technology is an effective way to solve these problems.Because of the application of computer control system and intelligent instrument in production in recent years, a large amount of data can be obtained.It has become a hot research field in recent years to monitor the running state of the system through the statistical analysis of the process data.As an important data-driven monitoring method, multivariate Statistical Process monitoring (MSPMM) has attracted much attention from academia and industry.However, the traditional MSPM method is restricted by many conditions in the process, for example, the process data should satisfy the linear relation as far as possible, Gao Si distribution.However, due to the influence of various factors, the data variables are strongly nonlinear and non-Gao Si distribution.Therefore, on the basis of previous studies, the problems existing in the actual industry are analyzed, and the following work is done:1.A process monitoring method based on negative selection algorithm (NSAs) is proposed to solve the problem that the traditional monitoring method destroys the nonlinear structure and the monitoring efficiency is not high when the data is modeled.In this method, the maximum Variance unfolding (MVU) method is used to extract the low-dimensional manifold from the original data, and then the "hypersphere group" model is obtained by using NSA to model the low-dimensional manifold.The simulation results show that the proposed method has better detection capability than other methods.2.Aiming at the problem of "dimension disaster" encountered by support vector data description Vector Data description (SVDDD) method in dealing with large samples, and taking advantage of its unique advantages in dealing with small sample data, a process monitoring method based on LTSA-Greedy-SVDD is proposed.In this method, the local tangent space arrangement Local Tangent Space alignment (LTSA) algorithm is introduced to extract the low-dimensional manifold, and then the Greedy method is introduced to extract the feature modeling samples.Thus, the computation time is greatly reduced. Te platform simulation and application simulation show the effectiveness of the method.3.Aiming at the problem that the process data is a mixture of Gao Si distribution and non-#china_person1# distribution, a process monitoring method based on weighted joint index is proposed.The statistical model is established by using the useful information of process data extracted by non-Gaussian two-step strategy, and the new statistical index is obtained by weighting the two statistics by weighted strategy.The effectiveness of the monitoring method based on weighted joint index is verified by numerical system simulation. Te process simulation and industrial application also show the effectiveness of the proposed method.
【學(xué)位授予單位】：華東理工大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2015
【分類號】：TQ015.9

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 張少捷;王振雷;錢鋒;;基于LTSA的ICA方法及其在化工過程監(jiān)控中的應(yīng)用[J];化工進(jìn)展;2010年10期

2 謝磊;王樹青;;遞歸核PCA及其在非線性過程自適應(yīng)監(jiān)控中的應(yīng)用[J];化工學(xué)報(bào);2007年07期

3 鄧曉剛;田學(xué)民;;基于DMVU-OCSVM的故障診斷方法[J];化工學(xué)報(bào);2011年08期

4 王華忠,張雪申,俞金壽;基于支持向量機(jī)的故障診斷方法[J];華東理工大學(xué)學(xué)報(bào);2004年02期

5 張穎偉;劉強(qiáng);張楊;;基于DKPLS的非線性過程故障檢測[J];華中科技大學(xué)學(xué)報(bào)(自然科學(xué)版);2009年S1期

6 曾憲華;羅四維;;全局保持的流形學(xué)習(xí)算法對比研究[J];計(jì)算機(jī)工程與應(yīng)用;2010年15期

7 楊金寶;張昌宏;陳平;;基于改進(jìn)BP神經(jīng)網(wǎng)絡(luò)的網(wǎng)絡(luò)故障診斷研究[J];計(jì)算機(jī)與數(shù)字工程;2012年02期

8 石懷濤;劉建昌;丁曉迪;譚帥;王雪梅;;基于混合動態(tài)主元分析的故障檢測方法[J];控制工程;2012年01期

9 謝磊;劉雪芹;張建明;王樹青;;基于NGPP-SVDD的非高斯過程監(jiān)控及其應(yīng)用研究[J];自動化學(xué)報(bào);2009年01期

10 周東華;胡艷艷;;動態(tài)系統(tǒng)的故障診斷技術(shù)[J];自動化學(xué)報(bào);2009年06期

相關(guān)博士學(xué)位論文 前2條

1 邵紀(jì)東;非線性過程監(jiān)測中的數(shù)據(jù)降維及相關(guān)問題研究[D];浙江大學(xué);2010年

2 葛志強(qiáng);復(fù)雜工況過程統(tǒng)計(jì)監(jiān)測方法研究[D];浙江大學(xué);2009年

，

本文編號：1732389