本文關(guān)鍵詞：數(shù)據(jù)驅(qū)動(dòng)的過(guò)渡過(guò)程建模與監(jiān)測(cè)　出處：《浙江大學(xué)》2017年博士論文　論文類型：學(xué)位論文

  更多相關(guān)文章： 過(guò)渡過(guò)程識(shí)別與故障檢測(cè) 非線性特性 非高斯特性 動(dòng)態(tài)特性

【摘要】：由于工況輸入點(diǎn)改變、原料變化、季節(jié)因素以及設(shè)備老化等原因,工業(yè)過(guò)程運(yùn)行狀態(tài)會(huì)發(fā)生不同程度的改變。在多工況過(guò)程建模和故障檢測(cè)中,需要對(duì)這些變化加以識(shí)別以便實(shí)現(xiàn)不同階段的故障檢測(cè)。傳統(tǒng)的多工況過(guò)程監(jiān)測(cè)通常著眼于穩(wěn)態(tài)工況而忽略了過(guò)渡過(guò)程的存在。在過(guò)渡過(guò)程中,數(shù)據(jù)特性的劇烈波動(dòng)會(huì)對(duì)過(guò)程的平穩(wěn)運(yùn)行產(chǎn)生一定程度的影響。因此,對(duì)過(guò)渡過(guò)程的建模和在線監(jiān)測(cè)是工業(yè)過(guò)程監(jiān)測(cè)領(lǐng)域中一個(gè)重要的研究課題。本文通過(guò)對(duì)過(guò)渡過(guò)程中的不同數(shù)據(jù)特性,包括非線性特性、非高斯特性及動(dòng)態(tài)特性進(jìn)行建模分析,著重研究了過(guò)渡過(guò)程的識(shí)別和在線故障檢測(cè)方法。全文的主要研究?jī)?nèi)容如下:首先,考慮過(guò)渡過(guò)程數(shù)據(jù)中的非線性特性的影響,將一個(gè)過(guò)渡過(guò)程視為多個(gè)子階段,提出了一種多投影模型迭代更新的數(shù)據(jù)分類方法,并綜合多次數(shù)據(jù)分類情況得到最終多工況數(shù)據(jù)的分類結(jié)果。同時(shí)設(shè)置過(guò)渡過(guò)程判別規(guī)則來(lái)判斷分類結(jié)果中過(guò)渡過(guò)程各子階段和各穩(wěn)態(tài)工況的分布,從而達(dá)到離線識(shí)別過(guò)渡過(guò)程的目的。之后,提出了一種基于KPLS模型序列的過(guò)渡過(guò)程在線識(shí)別和故障檢測(cè)方法,通過(guò)模型的在線更新完成過(guò)渡過(guò)程的在線識(shí)別和故障檢測(cè)的任務(wù)。其次,考慮過(guò)渡過(guò)程數(shù)據(jù)中的非高斯特性的影響,提出了一種基于獨(dú)立元交互信息差異度的過(guò)程故障檢測(cè)方法。針對(duì)過(guò)渡過(guò)程的時(shí)變特性,引入即時(shí)學(xué)習(xí)的思想,通過(guò)求取在線數(shù)據(jù)和歷史數(shù)據(jù)之間的交互信息,選取相似歷史數(shù)據(jù)作為在線訓(xùn)練集。同時(shí)運(yùn)用核密度估計(jì)方法,并結(jié)合獨(dú)立元交互信息差異度分析方法對(duì)統(tǒng)計(jì)限進(jìn)行在線更新。之后,通過(guò)比較在線數(shù)據(jù)和在線訓(xùn)練集之間的獨(dú)立元交互信息差異度,實(shí)現(xiàn)過(guò)渡過(guò)程的故障檢測(cè)。再次,考慮過(guò)渡過(guò)程數(shù)據(jù)中的自相關(guān)特性的影響,提出了一種基于動(dòng)態(tài)交互信息的方法用以提取過(guò)程的動(dòng)態(tài)信息,并通過(guò)度量多工況過(guò)程中不同階段之間動(dòng)態(tài)特性的相似度,完成過(guò)渡過(guò)程的離線識(shí)別工作。同時(shí),為兼顧算法快速性和高效性,提出了基于兩步移動(dòng)窗策略的多工況過(guò)程識(shí)別方法。隨后,提出了基于DPLS模型序列的過(guò)渡過(guò)程在線識(shí)別和故障檢測(cè)方法,通過(guò)模型的在線更新完成過(guò)渡過(guò)程在線識(shí)別和故障檢測(cè)的工作。最后,對(duì)本文所做工作進(jìn)行了總結(jié),并對(duì)相關(guān)領(lǐng)域的未來(lái)研究工作進(jìn)行了簡(jiǎn)要分析和展望。
[Abstract]:Due to the change of input point, material change, seasonal factors and aging of equipment, the operating state of industrial process will change to some extent. These changes need to be identified in order to achieve different stages of fault detection. Traditional multi-condition process monitoring usually focuses on steady state conditions and neglects the existence of transition process. The violent fluctuation of data characteristics will have a certain degree of impact on the smooth operation of the process. Modeling and on-line monitoring of transition process is an important research topic in the field of industrial process monitoring. Non-#china_person0# characteristics and dynamic characteristics of modeling analysis, focusing on the transition process identification and on-line fault detection methods. The main contents of this paper are as follows: first. Considering the influence of nonlinear characteristics in transition process data, a new data classification method based on iterative updating of multi-projection models is proposed, in which a transition process is regarded as multiple sub-stages. Finally, the classification results of the final multi-condition data are obtained by synthesizing the classification of multiple data. At the same time, the transitional process discriminant rules are set to judge the distribution of each sub-stage and each steady state of the transition process in the classification results. In order to achieve the purpose of off-line identification of transition process, a method of on-line identification and fault detection of transition process based on KPLS model sequence is proposed. The task of on-line identification and fault detection of transition process is completed by online updating of the model. Secondly, the influence of non-Gaussian characteristics in transition process data is considered. In this paper, a process fault detection method based on the difference degree of independent element interactive information is proposed. According to the time-varying characteristics of transition process, the idea of real-time learning is introduced, and the interactive information between online data and historical data is obtained. The similar historical data is selected as the online training set and the statistical limit is updated online by using the kernel density estimation method and the independent element interactive information difference analysis method. By comparing the information difference between online data and online training set, the fault detection of transition process is realized. Thirdly, the influence of autocorrelation in transition process data is considered. A method based on dynamic interactive information is proposed to extract the dynamic information of the process and measure the similarity of the dynamic characteristics between different stages in the multi-condition process. At the same time, in order to give consideration to the fast and high efficiency of the algorithm, a multi-condition process recognition method based on two-step moving window strategy is proposed. A method of on-line identification and fault detection of transition process based on DPLS model sequence is proposed. The on-line identification and fault detection of transition process are completed by on-line updating of the model. Finally. The work done in this paper is summarized, and the future research work in related fields is briefly analyzed and prospected.
【學(xué)位授予單位】：浙江大學(xué)
【學(xué)位級(jí)別】：博士
【學(xué)位授予年份】：2017
【分類號(hào)】：TP274

【參考文獻(xiàn)】

相關(guān)期刊論文 前1條

1 賀正楚;潘紅玉;;德國(guó)“工業(yè)4.0”與“中國(guó)制造2025”[J];長(zhǎng)沙理工大學(xué)學(xué)報(bào)(社會(huì)科學(xué)版);2015年03期

，

本文編號(hào)：1417541