基于關(guān)鍵性能指標(biāo)的數(shù)據(jù)驅(qū)動(dòng)故障檢測(cè)方法研究
發(fā)布時(shí)間：2019-06-21 00:02
【摘要】：過程監(jiān)控是保障系統(tǒng)安全性和可靠性的重要研究課題。在過去的幾十年中,得益于控制理論體系的不斷完善,基于解析模型的過程監(jiān)控方法獲得了長足的發(fā)展并產(chǎn)生出了大量的研究成果。然而,諸如化工、冶金、生物制藥等工業(yè)系統(tǒng),其內(nèi)部組成的復(fù)雜性和底層反應(yīng)機(jī)理的未知性使得建立其精準(zhǔn)的數(shù)學(xué)模型是非常困難甚至是不可能的。因此,基于解析模型的方法難以在此類系統(tǒng)中有效地推廣和應(yīng)用。值得注意的是,這類工業(yè)系統(tǒng)通常能夠產(chǎn)生出大量的離線記錄數(shù)據(jù)和在線測(cè)量數(shù)據(jù)。如何利用這些豐富的數(shù)據(jù)對(duì)系統(tǒng)進(jìn)行有效地監(jiān)測(cè)和控制引起了學(xué)術(shù)界和工業(yè)界的持續(xù)關(guān)注,這也促進(jìn)了數(shù)據(jù)驅(qū)動(dòng)過程監(jiān)控技術(shù)的快速發(fā)展。在過去的二十年中,數(shù)據(jù)驅(qū)動(dòng)過程監(jiān)控方法的主要任務(wù)是快速準(zhǔn)確地檢測(cè)出工業(yè)過程中發(fā)生的故障,并對(duì)故障進(jìn)行辨識(shí)、隔離以及恢復(fù)來確保系統(tǒng)的穩(wěn)定運(yùn)行。然而,近年來的研究成果和工業(yè)實(shí)踐的反饋信息表明并不是所有的過程故障都會(huì)影響到系統(tǒng)最終的產(chǎn)品質(zhì)量,反而忽略此類故障的報(bào)警可以顯著減少不必要的停產(chǎn)和檢修時(shí)間,從而極大地提高系統(tǒng)的生產(chǎn)效率同時(shí)降低維護(hù)成本。出于這一動(dòng)機(jī),基于關(guān)鍵性能指標(biāo)(KPI,Key Performance Indicator)的故障檢測(cè)方法成為工業(yè)界的迫切需求,同時(shí)也成為近五年來學(xué)術(shù)界研究的熱門課題。鑒于此,針對(duì)線性和非線性靜態(tài)系統(tǒng),本文將采用多元統(tǒng)計(jì)分析等數(shù)據(jù)驅(qū)動(dòng)技術(shù),深入開展基于KPI的故障檢測(cè)方法研究。第一,總結(jié)數(shù)據(jù)驅(qū)動(dòng)故障檢測(cè)方法的發(fā)展歷程和研究現(xiàn)狀,給出基于KPI的故障檢測(cè)問題的數(shù)學(xué)描述,并指出在基于KPI的故障檢測(cè)領(lǐng)域已有的研究成果的不足之處:1)目前針對(duì)線性系統(tǒng)提出的方法大多數(shù)是在偏最小二乘(PLS,Partial Least Squares)的基礎(chǔ)上通過后處理方式實(shí)現(xiàn)的,然而PLS對(duì)建模數(shù)據(jù)中的離群點(diǎn)和丟失點(diǎn)等異常數(shù)據(jù)非常敏感,導(dǎo)致少量異常數(shù)據(jù)即可嚴(yán)重影響PLS后處理方法的KPI預(yù)測(cè)性能,另外,已有的此類方法在故障判定邏輯方面依然比較復(fù)雜;2)受限于PLS的分解特性,PLS后處理方法的性能通常不穩(wěn)定,當(dāng)故障強(qiáng)度增大時(shí)這些方法的故障誤報(bào)率會(huì)顯著升高;3)目前針對(duì)非線性系統(tǒng)提出的方法在故障檢測(cè)性能和故障判定邏輯等方面都存在明顯缺陷;4)目前已有的線性和非線性方法在算法設(shè)計(jì)上都是獨(dú)立進(jìn)行的,具有一致分解結(jié)構(gòu)的綜合設(shè)計(jì)方法尚未引起注意,而這類方法對(duì)于簡(jiǎn)化基于KPI的故障檢測(cè)系統(tǒng)的設(shè)計(jì)步驟是非常重要的。針對(duì)這些問題,本文將逐一提出相應(yīng)的解決方案。第二,針對(duì)已有的PLS后處理方法對(duì)異常數(shù)據(jù)敏感以及故障判定邏輯復(fù)雜的問題,本文通過引入魯棒PLS算法和期望最大化算法分別降低建模數(shù)據(jù)中的離群點(diǎn)和丟失點(diǎn)等異常數(shù)據(jù)對(duì)PLS模型的影響,然后利用奇異值分解(SVD,Singular Value Decomposition)將過程變量空間正交分解為與KPI相關(guān)的子空間和與KPI無關(guān)的子空間,進(jìn)而提出一種魯棒KPI預(yù)測(cè)和基于KPI的線性故障檢測(cè)方法。仿真結(jié)果表明,所提出的方法在KPI預(yù)測(cè)方面明顯優(yōu)于已有的PLS后處理方法,并且在故障檢測(cè)性能和故障判定邏輯等方面都有明顯的提升。第三,針對(duì)已有的PLS后處理方法當(dāng)故障強(qiáng)度增大時(shí)故障誤報(bào)率升高的問題,本文通過引入數(shù)據(jù)預(yù)處理的思想,提出一類基于數(shù)據(jù)預(yù)處理和PLS后處理相結(jié)合的增強(qiáng)型的基于KPI的線性故障檢測(cè)方法。該類方法首先通過數(shù)據(jù)預(yù)處理去除過程變量空間中與KPI無關(guān)的成分,然后再利用PLS后處理將剩余過程變量空間正交分解為與KPI相關(guān)的子空間和與KPI無關(guān)的子空間,從而實(shí)現(xiàn)過程變量空間的徹底分解。仿真結(jié)果表明,所提出的方法明顯改善了PLS后處理方法性能不穩(wěn)定的問題,在故障強(qiáng)度非常大時(shí)依然可以保持極低的故障誤報(bào)率。第四,針對(duì)已有的基于KPI的非線性故障檢測(cè)方法在故障檢測(cè)性能和故障判定邏輯等方面存在的缺陷,本文提出兩種不同實(shí)現(xiàn)方式的新方法。首先,本文利用核偏最小二乘(KPLS,Kernel Partial Least Squares)對(duì)非線性過程建模,在此基礎(chǔ)上構(gòu)建核空間和KPI之間的線性關(guān)系,并通過SVD將核空間正交分解為與KPI相關(guān)的子空間和與KPI無關(guān)的子空間,進(jìn)而提出一種基于KPI的非線性故障檢測(cè)方法。另外,本文充分借鑒非線性模型逼近領(lǐng)域的研究成果,利用統(tǒng)計(jì)學(xué)習(xí)方法將非線性過程等效為若干局部線性模型,并通過在局部模型設(shè)計(jì)基于KPI的線性故障檢測(cè)方法進(jìn)而實(shí)現(xiàn)全局的基于KPI的非線性故障檢測(cè)方法。仿真結(jié)果表明,所提出的兩種非線性方法在故障檢測(cè)性能和故障判定邏輯等方面都明顯優(yōu)于已有的方法。第五,針對(duì)基于KPI的線性和非線性故障檢測(cè)方法的綜合設(shè)計(jì)問題,本文提出一種新穎的解決方案。首先,本文在主成分分析(PCA,Principle Component Analysis)的基礎(chǔ)上,利用主成分回歸(PCR,Principle Component Regression)的建模思想提出一種能夠?qū)⑦^程變量空間分解為與KPI相關(guān)的子空間和與KPI無關(guān)的子空間的算法,進(jìn)而提出一種新的基于KPI的線性故障檢測(cè)方法;依據(jù)完全相同的分解結(jié)構(gòu),本文通過建立核主成分分析(KPCA,Kernel Principle Component Analysis)模型,并利用核主成分回歸(KPCR,Kernel Principle Component Regression)的建模思想提出一種能夠?qū)⑻卣骺臻g分解為與KPI相關(guān)的子空間和與KPI無關(guān)的子空間的算法,進(jìn)而提出一種新的基于KPI的非線性故障檢測(cè)方法。仿真結(jié)果表明所提出的線性方法在故障檢測(cè)性能以及故障判定邏輯等方面都明顯優(yōu)于前面提出的線性方法和已有的PLS后處理方法;而所提出的非線性方法在故障檢測(cè)性能和故障判定邏輯方面和前面提出的非線性方法基本相同,但明顯優(yōu)于已有的非線性方法。更重要的是,一致的分解結(jié)構(gòu)極大地簡(jiǎn)化了基于KPI的故障檢測(cè)系統(tǒng)的設(shè)計(jì)步驟,同時(shí)也便于工程應(yīng)用人員對(duì)算法的理解,因此更加有利于所提出的方法在實(shí)際系統(tǒng)中的推廣和應(yīng)用。
[Abstract]:Process monitoring is an important research subject for the safety and reliability of the system. In the past few decades, thanks to the continuous improvement of the control theory system, the process monitoring method based on the analytical model has made great development and has produced a great deal of research results. However, industrial systems such as chemical, metallurgical, biopharmaceutical and the like, the complexity of its internal composition and the unknown nature of the underlying reaction mechanism make it very difficult or even impossible to establish its precise mathematical model. Therefore, the method based on the analytical model is difficult to be effectively promoted and applied in such systems. It is to be noted that such industrial systems are generally capable of producing a large amount of off-line recording data and on-line measurement data. How to use these abundant data to effectively monitor and control the system is the continuous concern of the academic and industry, which also promotes the rapid development of the data-driven process monitoring technology. In the past two decades, the main task of the data-driven process monitoring method is to quickly and accurately detect the faults occurring in the industrial process and to identify, isolate and recover the faults to ensure the stable operation of the system. However, the research results in recent years and the feedback information of industrial practice indicate that not all process failures will affect the final product quality of the system, but the alarm that ignores such failures can significantly reduce the unnecessary shutdown and maintenance time, So that the production efficiency of the system is greatly improved, and the maintenance cost is reduced. For this motivation, the failure detection method based on KPI and Key Performance Indicator becomes the urgent need of industry, and has also become a hot topic for academic research in the past five years. In view of the linear and non-linear static system, a multi-element statistical analysis and other data driving technology will be used in this paper to carry out the research on the method of fault detection based on KPI. First, the development history and the research status of the data-driven fault detection method are summarized, the mathematical description of the fault detection problem based on the KPI is given, and the shortcomings of the research results in the field of fault detection based on the KPI are pointed out: 1) Most of the methods currently proposed for linear systems are implemented by post-processing on the basis of partial least squares (PLS, Partial Least Squares), but the PLS is very sensitive to abnormal data such as outliers and missing points in the modeling data, leading to a small amount of abnormal data can seriously affect the KPI prediction performance of the PLS post-processing method, and in addition, the existing method is still more complex in the fault determination logic;2) is limited by the decomposition characteristic of the PLS, and the performance of the PLS post-processing method is generally not stable, when the failure intensity is increased, the fault error rate of the methods can be obviously increased;3) the method proposed by the non-linear system has obvious defects in the aspects of fault detection performance and fault judgment logic, and the like; 4) The existing linear and non-linear method is independently carried out in the design of the algorithm, and the integrated design method with the consistent decomposition structure has not yet attracted attention, and the method is very important for simplifying the design steps of the KPI-based fault detection system. In view of these problems, the corresponding solutions will be presented one by one. Secondly, according to the problem that the existing PLS post-processing method is sensitive to the abnormal data and the fault decision logic is complex, the influence of the outliers and the missing points in the modeling data on the PLS model is reduced by introducing the robust PLS algorithm and the expectation maximization algorithm, respectively. Then, singular value decomposition (SVD) is used to decompose the process variable space into sub-space related to the KPI and sub-space independent of the KPI, and then a robust KPI prediction and a KPI-based linear fault detection method is proposed. The simulation results show that the proposed method is better than the existing PLS after-processing method in the KPI prediction, and has obvious improvement in fault detection performance and fault decision logic. Thirdly, according to the existing PLS post-processing method, when the failure intensity is increased, the problem of the increase of the fault is raised. In this paper, by introducing the idea of data pre-processing, this paper puts forward a class of enhanced KPI-based linear fault detection method based on data pre-processing and PLS post-processing. The method comprises the following steps of: firstly, the component irrelevant to the KPI in the process variable space is removed through the data pretreatment, and then the residual process variable space is decomposed into the sub-space related to the KPI and the sub-space irrelevant to the KPI by using the PLS after-processing, so that the complete decomposition of the process variable space is realized. The simulation results show that the proposed method can obviously improve the performance of the PLS after-treatment method, and can still maintain a very low fault error when the fault strength is very large. Fourth, in view of the existing defects in the fault detection performance and fault determination logic of the existing KPI-based non-linear fault detection method, two new methods are proposed in this paper. Firstly, the linear relationship between the kernel space and the KPI is built on the basis of the kernel partial least square (KPLS) and the kernel partial least square (KPLS), and the kernel space is decomposed into sub-space related to the KPI and the sub-space irrelevant to the KPI by the SVD. And then a non-linear fault detection method based on the KPI is proposed. In addition, this paper fully uses the research results in the nonlinear model approximation, and uses the statistical learning method to convert the non-linear process into a number of local linear models. And a global KPI-based non-linear fault detection method is realized by designing a KPI-based linear fault detection method in a local model. The simulation results show that the two nonlinear methods are superior to the existing methods in the aspects of fault detection performance and fault decision logic. Fifth, in view of the comprehensive design of the linear and non-linear fault detection method based on the KPI, this paper presents a novel solution. First, on the basis of principal component analysis (PCA) and Principal Component Analysis (PCA), a method of using principal component regression (PCR) to decompose process variable space into sub-space related to KPI and sub-space independent of KPI is proposed. In this paper, a new linear fault detection method based on KPI is proposed. According to the exact same decomposition structure, the kernel principal component analysis (KPCA, Kernel Principal Component Analysis) model is established, and the kernel principal component regression (KPCR) is used. Kernel Principal Component Regression proposed a new method of non-linear fault detection based on KPI, which can decompose the feature space into sub-space related to the KPI and sub-space independent of the KPI. The simulation results show that the proposed linear method is superior to the linear method and the existing PLS after-processing method in the aspects of fault detection performance and fault determination logic. The proposed non-linear method is basically the same as the non-linear method proposed in the fault detection performance and fault decision logic, but it is better than the existing non-linear method. More importantly, the consistent decomposition structure greatly simplifies the design steps of the KPI-based fault detection system, and is also convenient for engineering application personnel to understand the algorithm, so that the proposed method is more beneficial to the popularization and application of the proposed method in the actual system.
【學(xué)位授予單位】：哈爾濱工業(yè)大學(xué)
【學(xué)位級(jí)別】：博士
【學(xué)位授予年份】：2016
【分類號(hào)】：TP277
本文編號(hào)：2503626
[Abstract]:Process monitoring is an important research subject for the safety and reliability of the system. In the past few decades, thanks to the continuous improvement of the control theory system, the process monitoring method based on the analytical model has made great development and has produced a great deal of research results. However, industrial systems such as chemical, metallurgical, biopharmaceutical and the like, the complexity of its internal composition and the unknown nature of the underlying reaction mechanism make it very difficult or even impossible to establish its precise mathematical model. Therefore, the method based on the analytical model is difficult to be effectively promoted and applied in such systems. It is to be noted that such industrial systems are generally capable of producing a large amount of off-line recording data and on-line measurement data. How to use these abundant data to effectively monitor and control the system is the continuous concern of the academic and industry, which also promotes the rapid development of the data-driven process monitoring technology. In the past two decades, the main task of the data-driven process monitoring method is to quickly and accurately detect the faults occurring in the industrial process and to identify, isolate and recover the faults to ensure the stable operation of the system. However, the research results in recent years and the feedback information of industrial practice indicate that not all process failures will affect the final product quality of the system, but the alarm that ignores such failures can significantly reduce the unnecessary shutdown and maintenance time, So that the production efficiency of the system is greatly improved, and the maintenance cost is reduced. For this motivation, the failure detection method based on KPI and Key Performance Indicator becomes the urgent need of industry, and has also become a hot topic for academic research in the past five years. In view of the linear and non-linear static system, a multi-element statistical analysis and other data driving technology will be used in this paper to carry out the research on the method of fault detection based on KPI. First, the development history and the research status of the data-driven fault detection method are summarized, the mathematical description of the fault detection problem based on the KPI is given, and the shortcomings of the research results in the field of fault detection based on the KPI are pointed out: 1) Most of the methods currently proposed for linear systems are implemented by post-processing on the basis of partial least squares (PLS, Partial Least Squares), but the PLS is very sensitive to abnormal data such as outliers and missing points in the modeling data, leading to a small amount of abnormal data can seriously affect the KPI prediction performance of the PLS post-processing method, and in addition, the existing method is still more complex in the fault determination logic;2) is limited by the decomposition characteristic of the PLS, and the performance of the PLS post-processing method is generally not stable, when the failure intensity is increased, the fault error rate of the methods can be obviously increased;3) the method proposed by the non-linear system has obvious defects in the aspects of fault detection performance and fault judgment logic, and the like; 4) The existing linear and non-linear method is independently carried out in the design of the algorithm, and the integrated design method with the consistent decomposition structure has not yet attracted attention, and the method is very important for simplifying the design steps of the KPI-based fault detection system. In view of these problems, the corresponding solutions will be presented one by one. Secondly, according to the problem that the existing PLS post-processing method is sensitive to the abnormal data and the fault decision logic is complex, the influence of the outliers and the missing points in the modeling data on the PLS model is reduced by introducing the robust PLS algorithm and the expectation maximization algorithm, respectively. Then, singular value decomposition (SVD) is used to decompose the process variable space into sub-space related to the KPI and sub-space independent of the KPI, and then a robust KPI prediction and a KPI-based linear fault detection method is proposed. The simulation results show that the proposed method is better than the existing PLS after-processing method in the KPI prediction, and has obvious improvement in fault detection performance and fault decision logic. Thirdly, according to the existing PLS post-processing method, when the failure intensity is increased, the problem of the increase of the fault is raised. In this paper, by introducing the idea of data pre-processing, this paper puts forward a class of enhanced KPI-based linear fault detection method based on data pre-processing and PLS post-processing. The method comprises the following steps of: firstly, the component irrelevant to the KPI in the process variable space is removed through the data pretreatment, and then the residual process variable space is decomposed into the sub-space related to the KPI and the sub-space irrelevant to the KPI by using the PLS after-processing, so that the complete decomposition of the process variable space is realized. The simulation results show that the proposed method can obviously improve the performance of the PLS after-treatment method, and can still maintain a very low fault error when the fault strength is very large. Fourth, in view of the existing defects in the fault detection performance and fault determination logic of the existing KPI-based non-linear fault detection method, two new methods are proposed in this paper. Firstly, the linear relationship between the kernel space and the KPI is built on the basis of the kernel partial least square (KPLS) and the kernel partial least square (KPLS), and the kernel space is decomposed into sub-space related to the KPI and the sub-space irrelevant to the KPI by the SVD. And then a non-linear fault detection method based on the KPI is proposed. In addition, this paper fully uses the research results in the nonlinear model approximation, and uses the statistical learning method to convert the non-linear process into a number of local linear models. And a global KPI-based non-linear fault detection method is realized by designing a KPI-based linear fault detection method in a local model. The simulation results show that the two nonlinear methods are superior to the existing methods in the aspects of fault detection performance and fault decision logic. Fifth, in view of the comprehensive design of the linear and non-linear fault detection method based on the KPI, this paper presents a novel solution. First, on the basis of principal component analysis (PCA) and Principal Component Analysis (PCA), a method of using principal component regression (PCR) to decompose process variable space into sub-space related to KPI and sub-space independent of KPI is proposed. In this paper, a new linear fault detection method based on KPI is proposed. According to the exact same decomposition structure, the kernel principal component analysis (KPCA, Kernel Principal Component Analysis) model is established, and the kernel principal component regression (KPCR) is used. Kernel Principal Component Regression proposed a new method of non-linear fault detection based on KPI, which can decompose the feature space into sub-space related to the KPI and sub-space independent of the KPI. The simulation results show that the proposed linear method is superior to the linear method and the existing PLS after-processing method in the aspects of fault detection performance and fault determination logic. The proposed non-linear method is basically the same as the non-linear method proposed in the fault detection performance and fault decision logic, but it is better than the existing non-linear method. More importantly, the consistent decomposition structure greatly simplifies the design steps of the KPI-based fault detection system, and is also convenient for engineering application personnel to understand the algorithm, so that the proposed method is more beneficial to the popularization and application of the proposed method in the actual system.
【學(xué)位授予單位】：哈爾濱工業(yè)大學(xué)
【學(xué)位級(jí)別】：博士
【學(xué)位授予年份】：2016
【分類號(hào)】：TP277
【參考文獻(xiàn)】
相關(guān)期刊論文 前1條
1 王麗;侍洪波;;采用改進(jìn)核偏最小二乘法的非線性化工過程故障檢測(cè)(英文)[J];Chinese Journal of Chemical Engineering;2014年06期
，本文編號(hào)：2503626
本文鏈接：http://sikaile.net/shoufeilunwen/xxkjbs/2503626.html
最近更新
教材專著
