基于统计理论的工业过程性能监控与故障诊断研究
|
摘要
如何确保生产的安全、提高产品的质量以及整体的经济效益是现代工业生产过程中非常关键的问题,一种有效解决该问题的技术手段是有效的过程性能监控和故障诊断的应用。现代计算机及信息技术的迅猛发展使得工业生产过程中越来越多的变量能够得到测量、处理和监控。统计性能监控方法因为仅仅依赖容易得到的过程数据,而不是依赖精确的数学模型,逐渐受到了广泛的关注。
本文在对传统统计过程监控方法的研究基础之上,提出了几种不同程度上的改进措施。进一步一些新的基于统计过程的监控方法被提出并运用。本文的主要内容如下:
1.提出基于小波包去噪主元分析方法的过程监控与故障诊断技术。该方法首先利用小波包变换技术,将测量噪声和干扰因素在过程数据中消除;其次利用主元分析法的特点,使过程数据得到降维,从而可建立主元监控模型;再次通过分析各变量对主元的贡献图,进行故障诊断。TE过程的仿真结果表明该方法在过程性能监控和故障诊断的有效性。
2.提出基于核主元分析方法的过程监控与故障诊断技术。该方法同样先利用小波包变换消除测量噪声和干扰。不同的是它采用核主元分析算法对故障进行在线检测。进一步运用核函数梯度算法对检测得到的故障实现在线故障诊断,从而可根据每个监控变量对相关统计量的不同贡献程度,绘制出贡献图,在贡献图的基础上实现故障分离。最后引入特征向量选择方法,使得监控过程中的核矩阵计算困难问题得到较好解决。通过对TE过程的仿真研究,并与主元分析法相比,实验结果表明该方法能有效实现故障检测和诊断,更高的过程监控能力得到突显。
3.利用核主元分析非线性过程监控的优势,结合多重核学习支持向量机在故障诊断方面的准确性,提出了基于核主元分析和多重核学习支持向量机的非线性过程监控和故障诊断方法。运用核主元法对数据进行处理,在特征空间构建监控变量和控制置信限,实现故障检测,若有故障发生,则计算样本的非线性主元得分向量,将其作为多重核学习支持向量机的输入值,通过其分类进行故障类型识别。将上述方法用于TE化工过程,仿真结果表明该方法能够准确快速地检测并诊断故障。
4.为了进一步提高故障诊断的速度和准确度,提出了基于核主元分析和无约束优化的稀疏型支持向量机的过程监控与故障诊断方法,首先利用核主元分析方法来检测故障,再利用Cholesky分解更新无约束优化中的Hessian矩阵构建稀疏型支持向量机,对TE过程的故障进行识别。仿真结果表明该方法能够准确快速地检测并诊断故障。
5.在分析复杂工业过程特点基础之上,充分利用核主元分析方法具有处理非线性数据的优势,以及独立成分分析方法具有较强提取高维特征空间信息能力的特点,提出基于核独立成分分析方法和支持向量机的非线性性能监控和故障诊断方法。该方法关键的步骤是先对数据作空间映射变换到高维特征空间;其次在高维特征空间中运用独立主元方法进行相关分析和计算。该方法借助在高维特征空间建立监控统计量和控制置信限的办法实现工业过程的监控。在实现过程监控的基础上,引入支持向量机,利用支持向量机优良的数据分类能力,实现故障诊断。TE过程仿真研究验证了该方法的有效性。
6.提出基于核独立成分分析和核Fisher判别分析的过程监控与故障诊断方法。该方法充分运用核学习理论,把核方法与线性Fisher判别分析方法有机地结合起来:通过利用核独立成分分析建立正常工况模型,得到检测故障信息。在发生故障的情况下,利用Fisher判别分析方法在高维的特征空间的特点和优势,可将满足最大分离程度的核Fisher判别向量和特征向量求出。从而根据当前故障的判别向量和历史故障数据集中所含故障的最优核Fisher判别向量的相似度进行故障诊断。通过对TE过程的仿真研究,验证了所提方法的有效性。
How to ensure safety, enhance the quality of products and the overall economic benefit are the critical problem in the process of modern industrial. An effective of technical method to solve the problem is the application of effective process performance monitoring and fault diagnosis. The rapid development of the computer and information technology made that a large number of process data of industrial have been sampled and collected. Since the methods of statistical performance monitoring rely only on readily available process data and do not assume accurate mathematical model, they have been paid more attention.
In this paper, some improvements of traditional methods have been made which based on the research of traditional statistical process monitoring method, and furthermore some new statistical monitoring methods are proposed too. The dissertation includes following main contents:
1. A new method combined wavelet packet transform (WPT) with principal component analysis (PCA) for process monitoring is proposed. Firstly, the method use WPT technology to restrain the noise and disturbance that contained in the process data effectively. And then the PCA technology is used to reduce the dimension of the process data and establish principal component (PC) model for monitoring. The contribution plots which represent the contribution of each monitoring variable to the PC are used for fault diagnosis. The monitoring results of the application to the Tennessee Eastman (TE) chemical process confirm its effectiveness.
2. A new fault detection and diagnosis method based on kernel principal component analysis (KPCA) is described. Firstly, it removes the noise from data set using WPT. The difference is that the new method here using KPCA to detect fault. And furthermore kernel function gradient algorithm is used to diagnosis fault. KPCA contribution plots are protracted which represent the contribution of each monitoring variable to the statistics. During the monitoring process, the feature vector selection method scheme is given to reduce the computation complexity of kernel matrix. The proposed method is applied to the simulation of Tennessee Eastman (TE) chemical process. The monitoring results confirm that the proposed method can effectively detect faults and diagnoses faults.
3. Using the advantage of KPCA for nonlinear monitoring and introducing the accuracy of multiple kernel learning support vector machines (MKL-SVM) for fault diagnosis, a new method for nonlinear process monitoring based on KPCA and MKL-SVM is proposed. The data is analyzed using KPCA. In the feature space, through constructing the statistical index and control limit, performance monitoring is implemented. T2 and SPE are constructed in the future space. If statistical index exceed the predefined control limit, a fault may have occurred .Then the nonlinear score vectors are calculated and fed into the MKL-SVM to identify the faults. The proposed method is applied to the simulation of Tennessee Eastman(TE)chemical process .The simulation results show that the proposed method can identify various types of faults accurately and rapidly.
4. To further improve the diagnosis speed and accuracy, a new method for nonlinear process monitoring based on KPCA and sparse SVM is proposed. The data is analyzed using KPCA. Through constructing the statistical index and control limit in the feature space, performance monitoring is implemented. If statistical index exceed the predefined control limit, a fault may have occurred. Then the nonlinear score vectors are calculated and fed into the sparse SVM to identify the faults. The proposed method is applied to the simulation of Tennessee Eastman(TE)chemical process. The simulation results show that the proposed method can identify various types of faults accurately and rapidly.
5. On the analysis of the characteristics of complex industrial processes basis, making full use of advantage of kernel principal component analysis method which could dealing with nonlinear data and the ability of kernel independent component analysis (KICA) to extraction high-dimensional feature space information, a new nonlinear performance monitoring and fault diagnosis method based on kernel independent component analysis (KICA) and SVM is proposed. The key of this method is map the data into high-dimensional feature subspace. And then analysis and computation can be done using the KICA algorithm. In the feature space, with the help of constructing the statistical index and control limit, the performance monitoring is implemented. SVM with the capacity of data classification are used to diagnosis the process fault. The effectiveness of this new method is confirmed by the application to the Tennessee Eastman (TE) chemical process.
6. A new statistical process monitoring and fault diagnosis method having the character of nonlinear which based on KICA and kernel FDA (KFDA) is proposed. Kernel learning theory is introduced into linear fisher discriminant analysis (FDA). KICA is used to establish the normal operating conditions and detect the fault. If a fault occurs, the nuclear fisher discriminant vector and feature vector F of the process data are extracted from the Fisher subspace. Thus, the batch normal or not can be detected by comparing distance with the predefined threshold. Comparing the present discriminant vector and the optimal discriminant vector of fault in historical data set, the similar degree can be detected. According to the similar degree, the perform fault can be diagnosed. The results of simulating TE process demonstrate that the proposed method can efficient in detecting and diagnosing the malfunctions,with more accurate result.
本文在对传统统计过程监控方法的研究基础之上,提出了几种不同程度上的改进措施。进一步一些新的基于统计过程的监控方法被提出并运用。本文的主要内容如下:
1.提出基于小波包去噪主元分析方法的过程监控与故障诊断技术。该方法首先利用小波包变换技术,将测量噪声和干扰因素在过程数据中消除;其次利用主元分析法的特点,使过程数据得到降维,从而可建立主元监控模型;再次通过分析各变量对主元的贡献图,进行故障诊断。TE过程的仿真结果表明该方法在过程性能监控和故障诊断的有效性。
2.提出基于核主元分析方法的过程监控与故障诊断技术。该方法同样先利用小波包变换消除测量噪声和干扰。不同的是它采用核主元分析算法对故障进行在线检测。进一步运用核函数梯度算法对检测得到的故障实现在线故障诊断,从而可根据每个监控变量对相关统计量的不同贡献程度,绘制出贡献图,在贡献图的基础上实现故障分离。最后引入特征向量选择方法,使得监控过程中的核矩阵计算困难问题得到较好解决。通过对TE过程的仿真研究,并与主元分析法相比,实验结果表明该方法能有效实现故障检测和诊断,更高的过程监控能力得到突显。
3.利用核主元分析非线性过程监控的优势,结合多重核学习支持向量机在故障诊断方面的准确性,提出了基于核主元分析和多重核学习支持向量机的非线性过程监控和故障诊断方法。运用核主元法对数据进行处理,在特征空间构建监控变量和控制置信限,实现故障检测,若有故障发生,则计算样本的非线性主元得分向量,将其作为多重核学习支持向量机的输入值,通过其分类进行故障类型识别。将上述方法用于TE化工过程,仿真结果表明该方法能够准确快速地检测并诊断故障。
4.为了进一步提高故障诊断的速度和准确度,提出了基于核主元分析和无约束优化的稀疏型支持向量机的过程监控与故障诊断方法,首先利用核主元分析方法来检测故障,再利用Cholesky分解更新无约束优化中的Hessian矩阵构建稀疏型支持向量机,对TE过程的故障进行识别。仿真结果表明该方法能够准确快速地检测并诊断故障。
5.在分析复杂工业过程特点基础之上,充分利用核主元分析方法具有处理非线性数据的优势,以及独立成分分析方法具有较强提取高维特征空间信息能力的特点,提出基于核独立成分分析方法和支持向量机的非线性性能监控和故障诊断方法。该方法关键的步骤是先对数据作空间映射变换到高维特征空间;其次在高维特征空间中运用独立主元方法进行相关分析和计算。该方法借助在高维特征空间建立监控统计量和控制置信限的办法实现工业过程的监控。在实现过程监控的基础上,引入支持向量机,利用支持向量机优良的数据分类能力,实现故障诊断。TE过程仿真研究验证了该方法的有效性。
6.提出基于核独立成分分析和核Fisher判别分析的过程监控与故障诊断方法。该方法充分运用核学习理论,把核方法与线性Fisher判别分析方法有机地结合起来:通过利用核独立成分分析建立正常工况模型,得到检测故障信息。在发生故障的情况下,利用Fisher判别分析方法在高维的特征空间的特点和优势,可将满足最大分离程度的核Fisher判别向量和特征向量求出。从而根据当前故障的判别向量和历史故障数据集中所含故障的最优核Fisher判别向量的相似度进行故障诊断。通过对TE过程的仿真研究,验证了所提方法的有效性。
How to ensure safety, enhance the quality of products and the overall economic benefit are the critical problem in the process of modern industrial. An effective of technical method to solve the problem is the application of effective process performance monitoring and fault diagnosis. The rapid development of the computer and information technology made that a large number of process data of industrial have been sampled and collected. Since the methods of statistical performance monitoring rely only on readily available process data and do not assume accurate mathematical model, they have been paid more attention.
In this paper, some improvements of traditional methods have been made which based on the research of traditional statistical process monitoring method, and furthermore some new statistical monitoring methods are proposed too. The dissertation includes following main contents:
1. A new method combined wavelet packet transform (WPT) with principal component analysis (PCA) for process monitoring is proposed. Firstly, the method use WPT technology to restrain the noise and disturbance that contained in the process data effectively. And then the PCA technology is used to reduce the dimension of the process data and establish principal component (PC) model for monitoring. The contribution plots which represent the contribution of each monitoring variable to the PC are used for fault diagnosis. The monitoring results of the application to the Tennessee Eastman (TE) chemical process confirm its effectiveness.
2. A new fault detection and diagnosis method based on kernel principal component analysis (KPCA) is described. Firstly, it removes the noise from data set using WPT. The difference is that the new method here using KPCA to detect fault. And furthermore kernel function gradient algorithm is used to diagnosis fault. KPCA contribution plots are protracted which represent the contribution of each monitoring variable to the statistics. During the monitoring process, the feature vector selection method scheme is given to reduce the computation complexity of kernel matrix. The proposed method is applied to the simulation of Tennessee Eastman (TE) chemical process. The monitoring results confirm that the proposed method can effectively detect faults and diagnoses faults.
3. Using the advantage of KPCA for nonlinear monitoring and introducing the accuracy of multiple kernel learning support vector machines (MKL-SVM) for fault diagnosis, a new method for nonlinear process monitoring based on KPCA and MKL-SVM is proposed. The data is analyzed using KPCA. In the feature space, through constructing the statistical index and control limit, performance monitoring is implemented. T2 and SPE are constructed in the future space. If statistical index exceed the predefined control limit, a fault may have occurred .Then the nonlinear score vectors are calculated and fed into the MKL-SVM to identify the faults. The proposed method is applied to the simulation of Tennessee Eastman(TE)chemical process .The simulation results show that the proposed method can identify various types of faults accurately and rapidly.
4. To further improve the diagnosis speed and accuracy, a new method for nonlinear process monitoring based on KPCA and sparse SVM is proposed. The data is analyzed using KPCA. Through constructing the statistical index and control limit in the feature space, performance monitoring is implemented. If statistical index exceed the predefined control limit, a fault may have occurred. Then the nonlinear score vectors are calculated and fed into the sparse SVM to identify the faults. The proposed method is applied to the simulation of Tennessee Eastman(TE)chemical process. The simulation results show that the proposed method can identify various types of faults accurately and rapidly.
5. On the analysis of the characteristics of complex industrial processes basis, making full use of advantage of kernel principal component analysis method which could dealing with nonlinear data and the ability of kernel independent component analysis (KICA) to extraction high-dimensional feature space information, a new nonlinear performance monitoring and fault diagnosis method based on kernel independent component analysis (KICA) and SVM is proposed. The key of this method is map the data into high-dimensional feature subspace. And then analysis and computation can be done using the KICA algorithm. In the feature space, with the help of constructing the statistical index and control limit, the performance monitoring is implemented. SVM with the capacity of data classification are used to diagnosis the process fault. The effectiveness of this new method is confirmed by the application to the Tennessee Eastman (TE) chemical process.
6. A new statistical process monitoring and fault diagnosis method having the character of nonlinear which based on KICA and kernel FDA (KFDA) is proposed. Kernel learning theory is introduced into linear fisher discriminant analysis (FDA). KICA is used to establish the normal operating conditions and detect the fault. If a fault occurs, the nuclear fisher discriminant vector and feature vector F of the process data are extracted from the Fisher subspace. Thus, the batch normal or not can be detected by comparing distance with the predefined threshold. Comparing the present discriminant vector and the optimal discriminant vector of fault in historical data set, the similar degree can be detected. According to the similar degree, the perform fault can be diagnosed. The results of simulating TE process demonstrate that the proposed method can efficient in detecting and diagnosing the malfunctions,with more accurate result.
引文
[1] Nigerian Aeeident InvestigationBureau. Aeeident Investigation Report .2009. http://aib.gov.ng.
[2]安全文化网.化工事故统计. 2009. http://www.anquan.com.cn/.
[3] Calandranis, J, Stephanopoulos, G, Nunokawa S. Online performance monitoring and diagnosis. Chemical Engineering Progress, 1990, Vo1. 86(1): 60-68.
[4]周韶圆.基于HMM的统计过程监控研究[博士学位论文].杭州:浙江大学, 2005.
[5] Beard R V. Failure accommodation in linear systems though self-reorganization [Ph.D. Thesis]. MIT, Cambridge, MA, 1971.
[6] Mehra R K, Peschon J. An innovation approach to fault detection and diagnosis in Dynamics. Automatica, 1971, 7.
[7] Willsky A S. A suvrey of design methods for failure detection in dynamic systems. Automatica, 1976, 12.
[8] Himmelblua D M. Fault detection and diagnosis in chemical and Petrochemical Process. Amsterdam: Elsevier Press, 1978.
[9]叶银忠,潘日芳,蒋慰孙.动态系统的故障检测与诊断方法.信息与控制. 1985, Vo1.15 (6):27-34.
[10]周东华,孙优贤.控制系统故障检测与诊断技术.北京:清华大学出版社, 1994.
[11] Frank P M. Fault diagnosis in dynamic systems using analytical and knowledge-based redundancy --- A survey and some new results. Automatica, 1990, Vo1.26 (3): 459-474.
[12] Jiang B, Staroswiecki, Marcel. Robust observer based fault diagnosis for a class of nonlinear systems with uncertainty. Proceedings of the IEEE Conference onDecision and Control, 2001, l: 161-166.
[13] Jiang B, Staroswiecki, Marcel. Fault diagnosis for nonlinear uncertain systems using robust/ sliding mode observers. Control and Intelligent Systems, 2005, Vo1. 33 (3): 151-157.
[14] Wu J D, Huang C W, Huang R W. An application of a recursive Kalman filtering algorithm in rotating machinery fault diagnosis. NDT and E International, 2004, 375:411-419.
[15]赵旭.基于统计学方法的过程监控与质量控制研究[博士学位论文].上海:上海交通大学, 2006.
[16] Chiang L H, Russell E L, Braatz R D, Fault detection and diagnosis in industrial systems. Springer-Verlag, London, 2001.
[17] Shewhart W A. Statistical method from the viewpoint of quality control. New York: Dover,1986.
[18] Page E S. Continuous inspection schemes. Biometrika, 1954, 41:100-114.
[19] Roberts S W. Control chart tests based on geometric moving average. Technometrics, 1959, 1: 239-250.
[20] Page E S. Cumulative sum control charts. Technometrics, 1961, 3:1-9.
[21] Thompson J R, Koronacki J. Statistical process control for quality improvement. New York: Chapman and Hall, 1993.
[22] Bissel D. Statistical methods for SPC and TQM. London: Chapman and Hall, 1994.
[23] Jackson J E, and G S Mudholkar. Control Procedures for residuals associated with principal component analysis. Technometrics, 1979, 21:341-349.
[24] MacGregor J F, Marlin T E, Kresta J, etal. Multivariate statistical methods in process analysis and control. Proceedings of the Fourth International Conference on Chemical Process Control. Amsterdam: Elsevier, 1991, 79-99.
[25] Kresta J, MacGregor J F, Marlin T E. Multivariate statistical monitoring of process operating performance. The Canadian Journal of Chemical Engineering, 1991(69): 35-47.
[26] Nomikos P, MacGregor J F. Multivariate SPC charts for monitoring batch processes. Technometrics, 1995, Vol. 37(1): 41-59.
[27] Nomikos P, MacGregor J F. Monitoring batch processes using multiway principal component analysis. American Institute of Chemical Engineers Journal, 1994, Vol.40 (8):1361-1375.
[28]蒋丽英.基于FDA-DPLS方法的流程工业故障诊断研究[博士学位论文].杭州:浙江大学, 2005.
[29] Sch?lkopf B, Smola A J, Muller K.Nonlinear component analysis as a kernel eigenvalue problem. Neural Computation, 1998, 10: 1299-1319.
[30] Jade A m, Srikanth B, Jayaraman V k, etc. Feature extraction and denoising using kernel PCA. Chemical Engineering Science, 2003(58):4441-4448.
[31] Choi S W, Lee C, Lee J M, Jin H P, Lee I B. Fault detection and identification of nonlinear processes based on kernel PCA. Chemometrics and Intelligent Laboratory Systems, 2005(75): 55-67.
[32]王华忠,俞金寿.基于核函数PCA的非线性过程实时监控方法.华东理工大学学报(自然科学版), 2005, 31(6): 783-787.
[33]樊立萍,徐阳.基于KPCA的污水处理过程监视.仪器仪表学报, 2005, 26(8): 157-158.
[34] Michael E T. Sparse kernel principal component analysis. Advances in Neural Information Processing Systems, 2000: 633-639.
[35] Lima A, Zen H, Nankaku Y, etc. Applying sparse KPCA for feature extraction in speech recognition .IEICE Transactions on Information and Systems, 2005, E88-D (3): 401-409.
[36]徐勇,杨静宇,陆建峰.提升KPCA方法特征抽取效率的算法设计.中国工程科学, 2005, 7(10): 38-42.
[37]解立春,王海清,李平. PKPCA:融合先验类别信息的非线性主元分析算法.电路与系统学报, 2003, 8(6): 95-100.
[38]王新峰,邱静,刘冠军.基于有监督核函数主元分析的故障状态识别.测试技术学报, 2005, 19(2): 200-203.
[39] Geladi P, Kowalski B R. Partial least-squares regression: A tutorial. Analytica Chimica Acta, 1986, 185: l-17.
[40] Duda R O, Hart P E. Pattern classification and scene analysis. John Wiley &Sons, NewYork, 1973.
[41] Sarnrnon J W. An optimal discriminant plane. IEEE Trans on Computers, 1970, 19(9):826-829.
[42] Foley D H, Sarnrnon J W. An optimal set of discriminant vectors. IEEE Trans on Computers, 1975, 24(3):281-289.
[43] Tian Q, Fainman Y, Lee S H. Comparison of statistical pattern-recognition algorithms for hybrid processingⅡ: eigenvector-based algorithm. J. Opt. Soc. Am. A 5, 1988, 5(10): 1670-1682.
[44] Hong Z Q, Yang J Y. Optimal discriminant plane for a small number of samples and design method of classifier on the plane. Pattern Recognition, 1991, 24(4): 317-324.
[45] Cheng Y Q, Zhuang Y M, Yang J Y. Optimal Fisher discriminant analysis using the rank decomposition. Pattern Recognition, 1992, 25(1):101-111.
[46]程永清,庄永明,杨静宁.一种改进的Fisher判别准则.计算机研究与发展. 1991, 28(6): 43-48.
[47] Liu K, Cheng Y Q, Yang J Y. An efficient algorithm for Foley-Sammon optimal set of discriminant vectors by algebraic method.International Journal of Pattern Recognition and Artificial Intelligence, 1992, 6(5): 817-829.
[48] Chiang L H, Russell E L, Braatz R D. Fault diagnosis in chemical processes using Fisher discriminant analysis, discriminant partial least squares, and principal component analysis. Chemometrics and Intelligent Laboratory Systems, 2000, 50: 243-252.
[49] Russell E L, Braat R D. Fault isolation in industrial processes using Fisher discriminant analysis. Foundations of Computer-aided Process Operations, Pekny J F and Blau G E, eds, AICHE, New York, 1998.
[50] Hyv?rinen A. Survey on independent component analysis. Neural Computing Surveys, 1999,2:94-128.
[51] Kano M, Tanaka S, Hasebe S, etal. Monitoring independent components for fault detection. AICHE J, 2003, 49(4):969-976.
[52] Kano M, Tanaka S, Ohno H, etal. The use of independent component analysis for multivariate statistical process control. Proc. of Int. Symp.on Advanced Control of Ind. Pro. , Kumamoto, Japan, 2002, 423-428.
[53] Lee J M, Yoo C, Lee I B. Statistical process monitoring with independent component analysis. Journal of Process Control, 2004, 14(5):467-485.
[54]陈国金,梁军,钱积新.独立元分析方法及其在化工过程监控和故障诊断中的应用.化工学报, 2003, 54(10): 1474-1477.
[55]卢娟,刘飞.基于规范变量分析的动态多变量过程故障诊断.计算机测量与控制, 2007, 15(8):984-986.
[56]郭明.基于数据驱动的流程工业性能监控与故障诊断研究[博士学位论文].杭州:浙江大学, 2004.
[57]何宁.基于ICA-PCA方法的流程工业过程监控与故障诊断研究[博士学位论文].杭州:浙江大学, 2004.
[58] Kosanovich K A, Piovoso M J. PCA of wavelet transformed process data for monitoring. Intelligent data analysis, 1997, 1(1):85-99.
[59]胡昌华,张军波,夏军,等.基于MATLAB的系统分析与设计:小波分析.西安:西安电子科技大学出版社, 1999.12.
[60]赵成燕.小波包主元分析方法在故障诊断中的应用研究[硕士学位论文].上海:华东理工大学, 2005.
[61] Macgregor J F, Kourti T. Statistical process control of multivariate process. Control Engineering Practice, 1995, 3(3): 403-414.
[62] Mamzic C L. Guidelines for the application of statistical process control in the continuous process industries. Measurement and Control, 1995, 28(April).
[63] Kosanovich K A, Piovoso M J. Multivariate statistical methods applied to process monitoring. Presented at EPSRC IMI Sponsored Meeting on Multivariate Statistical Process Control and Plant Performance Monitoring, December 19, 1995, Newcastle, U.K.
[64] Martin E B, Morris A J. An overview of multivariate statistical process control in continuous and batch process performance monitoring. Trans. Inst. MC, 1996, 18(2): 51-60.
[65] Zhang J, Martin E B, Morris A J. Fault detection and diagnosis using multivariate statistical techniques. Trans Ichem, 1996, 71 (1, Part A).
[66] Raich A, Cinar A. Statistical process monitoring and disturbance diagnosis in multivariable continuous processes. AIChE Journal, 1996, 42(4): 995-1009.
[67] Chen J, Bandoni A, Romagnoli J A. Robust statistical process monitoring. Computers & Chemical. Engineering, 1996, 20(s1): s495-s502.
[68] Chen J, Bandoni A, Romagnoli J A. Robust PCA and normal region in multivariate statistical process monitoring. AIChE Journal, 1996: 3563-3566.
[69] Qin S J, Li W H. Recursive PCA for adaptive process monitoring. Proceedings of the 14th World Congress of IFCA, Beijing, China, 1999.
[70] Zhao L J, Cai T Y, Wang G. Double moving window MPCA for online adaptive batch monitoring. Chin. J. Chem. Eng., 2005, 13 (5): 649-655.
[71] Jia F, Martin E B, Morris A J. Nonlinear principal components analysis with application to process fault detection. International Journal of Systems Science, 2001, 31:1473– 1487.
[72] Lee D S, Park J M, Vanrolleghem P A. Adaptive multiscale principal component analysis for on-line monitoring of a sequencing batch reactor. Journal of Biotechnology, 2005, 116(2): 195-210.
[73] Dong D, McAvoy T J. Nonlinear principal component analysis based on principal curves and neural networks. Computers and Chemical Engineering, 1996, 20 (1): 65-78.
[74] Cho J H, Lee J M, Choi S W. Fault identification for process monitoring using kernel principal component analysis. Chemical Engineering Science, 2005, 60 (1): 279-288.
[75]薄翠梅,张广明,王执铨.基于KPCA-PNN的复杂工业过程集成故障辨识方法.信息与控制, 2009, 38(1):98-109.
[76] Vapnik V. An overview of statistical learning theory. IEEE Trans. Neural Network, 1999, 10(5): 988-999.
[77] Cristianini N, Shawe-Taylor J. An Introduction to Support Vector Machines and Other Kernel -based Learning Methods. UK: Cambridge University Press, 2000.
[78] Genton M G. Classes of Kernels for Machine Learning:a statistical perspective. Journal of Machine Learning Research, 2001, 2: 299-312.
[79]阎威武,常俊林,邵惠鹤.基于滚动时间窗的最小二乘支持向量机回归估计方法及仿真.上海交通大学学报, 2004, 38(4): 524-526,532.
[80]王华忠,俞金寿.基于混合核函数PCR方法的工业过程软测量建模.化工自动化及仪表, 2005, 32(2): 23-25.
[81] Baudat G, Anouar F. Kernel-based methods and function approximation. In Proceedings of international conference on neural networks, Washington, DC. 2001: 1244-1249
[82] Baudat G, Anouar F. Feature vector selection and projection using kernels. Neurocomputing, 2003, 55: 21-38.
[83] Peiling Cui, Junhong Li, Guizeng Wang .Improved kernel principal component analysis for fault detection. Expert Systems with Applications 2008, 34:1210-1219.
[84] Chen J H, Liao C M. Dynamic process fault monitoring based on neural network and PCA. Journal of Process Control, 2002, 12(2): 277-289.
[85]肖应旺,徐保国.基于ICA-MPCA的间歇过程检测方法.仪器仪表学报, 2009, 30(5): 990-996.
[86] Zhao Shijian, Zhang Jie, Xu Yongmao. Performance monitoring of process with multiple operating modes through multiple PLS models. Journal of process Control, 2006, 16(7):763~772.
[87] Mehranbod N, Soroush M, Panjapornpon C. A method of sensor fault detection and identification. Journal of Process Control, 2005, 15(3):321~339.
[88] Ge M, Du R, Zhang G C, etal. Fault diagnosis using support vector machine with an application in sheet metal stamping operations. Mechanical Systems & Signal Processing, 2004, Vol.18: 143~159.
[89]马笑潇,黄席樾,柴毅.基于SVM的二叉树多类分类算法及其在故障诊断中的应用.控制与决策, 2003, Vol.18 (3): 272~276.
[90]程军圣,于德介,杨宇.基于内禀模态奇异值分解和支持向量机的故障诊断方法.自动化学报, 2006, Vol.32 (3): 475~480.
[91]刘爱伦,袁小艳,俞金寿.基于KPCA-SVC的复杂过程故障诊断.仪器仪表学报, 2007, 28(5):868-872.
[92]蒋少华,桂卫华,阳春华,等.基于核主元分析与多支持向量机的监控诊断方法及其应用.系统工程理论与实践, 2009, 29(9):153-159.
[93] Lanckriet G R G, Cristianini N, Bartlett P, e.al. Learning the kernel matrix with semidefinite programming. Journal of Machine Learning Research, 2004, 5: 27~72.
[94] Anderson E D, Anderson A D. The MOSEK interior point optimizer for linear programming //High Performance Optimization Berlin: Springer, 2000: 197~232.
[95] Hsu C, Lin C J. A comparison of methods for mufti-class support vector machines. IEEE Trans. on Neural Networks, 2002,.13 (2): 415~425.
[96]张军峰,胡寿松.基于多重核学习支持向量机的歼击机故障诊断.东南大学学报(自然科学版). 2007, 37 Sup. (I): 1~5.
[97]于德介,陈淼峰,程军圣等.基于AR模型和支持向量机的转子系统故障诊断方法.系统工程理论与实践, 2007, 27(5):152-159.
[98]张军峰,胡寿松.基于无约束优化的非线性支持向量回归.控制与决策,2009, 24(1):125-128.
[99] Keerthi S S, Chapelle O, Decoste D. Building support vector machines with reduced classifier complexity. Journal of Machine Learning Research, 2006, Vo1.7: 1493~1515.
[100] Chapelle O. Training a support vector machine in the primal. Neural Computation, 2007, Vol.19: 1155~1178.
[101] Kano M, Nagao K, Hasebe S, etal. Comparision of multivariate statistical process monitoring methods with applications to the Eastman challenge problem [J].Computers and Chemical Engineering, 2002, 26:161-174.
[102] Chen Q, Wynne R J, Goulding P, etal. The application of principal component analysis and kernel density estimation to enhance process monitoring. Control Engineering Practice, 2000, 8:531-543.
[103] Ku W, Storer R H, Georgakis C. Disturbance detection and isolation by dynamic principal component analysis. Chemometrics and Intelligent Laboratory System, 1995, 30: 179-196.
[104]宋凯,王海清,李平. PLS质量监控及其在Tennessee Eastman过程中的应用.浙江大学学报:工学版, 2005,39(5):657-662.
[105] Martin E B, Morris A J. Non-parametric confidence bounds for process performance monitoring charts. Journal of Process Control, 1996, 6(6), 349-358.
[106] Hyv?rinen A, Oja E. Independent component analysis:algorithms and applications.Neural Networks, 2000, 13(4-5):411-430.
[107]杨竹青,李勇,胡德文.独立成分分析方法综述.自动化学报, 2002, 28(5):762-772.
[108] Liangun, Qian ji-xin. Multivariate Statiscal Process Monitoring and Control: Recent Developments and Application to Chemical Industry. Chinese J. Chem.Eng., 2003, 11(2): 191-203.
[109] Seungjin Choi, Andrzej Cichocki. Blind Source Separation and Independent Component Analysis: A Review. Neural Information Processing-Letters and Reviews, 2005, 16(1):1-57.
[110] Achmad Widodo, Bo-Suk Yang, Tian Han. Combination of Independent analysis and support vector machines for intelligent faults diagnosis of induction motors.Expert Systems with Applications. Neural Networks, 2000, 13, 411-430.
[111]陈国金,梁军,刘育明等.基于多元统计投影方法的过程监控技术研究.浙江大学学报:工学版, 2004, 38(12): 1561-1565.
[112] Cheung Y M, Xu L. Independent component ordering in ICA time series analysis. NeuroComputing, 2001, 41(1):145-152.
[113] Jutten, C, Herault, J. Independent component analysis.Proceedings of European Signal Processing Conference, 1988, 287-314.
[114] T Lee. Independent Component Analysis: Theory and Applications. Kluwer Academic Publishers, Boston, USA, 1998.
[115] Hyv?rinen A. New approximations of differential entropy for independent component analysis and projection pursuit, Adv. Neural Inform. Process. Syst. 10 (1998) 273–279.
[116] Bell A J, Sejnowski A J. An information-maximization approach to blind separation and blind deconvolution. Neural Computation, 1995, 7(6):1129-1159.
[117] Amari S L, Cichocki A, Yang H. A new learning algorithm for blind source separation. Advances in Neural Information Processing Systems, 1996, 8:757-763.
[118] Hyv?rinen A, Oja E. A fast fixed-point algorithm for independent component analysis.Neural Computation, 1997, 9(7):1483-1492.
[119] Hyv?rinen A. Fast and robust fixed-point algorithms for independent component analysis. IEEE Transactions on Neural Networks, 1999, 10(3):626-634.
[120] Hyv?rinen A, Karhunen J, Oja, E. Independent Component Analysis. John Wiley & Sons, Inc, New York, USA, 2001.
[121] Li R F, Wang X Z. Dimension reduction of process dynamic trends using independent component analysis, Comp. Chem. Eng. 2002,26: 467-473.
[122] Yang J, Gao X, Zhang D, et al. Kernel ICA: An alternative formulation and its application to face recognition.Pattern Recognition, 2005, 38(10): 1784-1787.
[123] Bach F R, Jordan M I. Kernel independent component analysis.Journal of Machine Learning, 2002, 3(1):1-48.
[124] Lee J M, Qin S J, Lee I B. Fault detection of non-linear processes using kernel independent component analysis. Canadian Journal of Chemical Engineering, 2007, 85(4): 526-536.
[125] Zhang Y, Qin S J. Fault detection of nonlinear processes using multiway kernel independent component analysis. Industrial&Engineering Chemistry Research, 46(23):7780-7787.
[126] Cardoso J F, Soulomica A. Blind beamforming for non- Gaussian signals. IEEE Proc. F 1993, 140 (6): 362–370.
[127] Lee J M, Lee I B. Nonlinear process monitoring using kernel principal component analysis. Chemical Engineering Science, 2004, 59(1): 223-234.
[128] Simoglou A, Martin E B, Morris A J. Statistical performance monitoring of dynamic multivariate processes using state space modeling. Computers and Chemical Engineering, 2002,26(6):909-920.
[129]张曦.基于统计理论的工业过程综合性能监控、诊断及质量预测方法研究[博士学位论文].上海:上海交通大学, 2008.
[130] Tracy N D, Young J C, Mason R L. Multivariate control charts for individual observations. Journal of Quality Technology, 1992, 24: 88-95.
[131] Silverman B W. Density Estimation for Statistics and Data Analysis. Chapman & Hall, UK, 1986.
[132] Wand M P, Jones M C.Kernel smoothing.UK: Chapman&Hall, 1995.
[133] Pierre M, Drezet L, Harrison R F. A new method for sparsity control in support vector classification and regression. Pattern recognition, 2001, 34(1):111-125.
[134]彭文季,罗兴锜.基于小波包分析和支持向量机的水电机组振动故障诊断研究.中国电机工程学报, 2006, 26(24) : 164-169.
[135]杨慧中,高岩,张素贞等.独立成分分析和支持向量机混合方法在过程监控中的应用.计算机与应用化学, 2007, 24(3) : 295-298.
[136] Sebald D J, Buchlew J A. Support vector machines and the multiple hypothesis test problem. IEEE Trans on Signal Processing, 2001, 49(11): 2865-2872.
[137]袁胜发,褚福磊.支持向量机及其在机械故障诊断中的应用.振动与冲击, 2007, 26(11): 29-37.
[138] Fisher R A. The utilization of multiple measurements in taxonomic problem. Annals of Eugenics, 1936, 7(2): 179-188.
[139] Chiang L H, Russell E L, Braatz R D. Fault Detection and Diagnosis in Industrial Systems. Hong Kong: Springer, 2001.
[140] Jackson J E. A User’s Guide to Principal Components. Wiley, New York, 1991.
[141] He Q P, Qin S J, Wang J. A new Fault diagnosis method using fault directions in Fisher discriminant analysis. AIChEJ, 2005, 51(2):555-571.
[142] Mika S, R?tsch G, Weston J. Fisher discriminant analysis with kernels. Nerual Networks for Signal Processing IX, 1999, 41-48.
[143]王树青等编著.先进控制技术及应用[M].北京:化学工业出版社, 2001.
[2]安全文化网.化工事故统计. 2009. http://www.anquan.com.cn/.
[3] Calandranis, J, Stephanopoulos, G, Nunokawa S. Online performance monitoring and diagnosis. Chemical Engineering Progress, 1990, Vo1. 86(1): 60-68.
[4]周韶圆.基于HMM的统计过程监控研究[博士学位论文].杭州:浙江大学, 2005.
[5] Beard R V. Failure accommodation in linear systems though self-reorganization [Ph.D. Thesis]. MIT, Cambridge, MA, 1971.
[6] Mehra R K, Peschon J. An innovation approach to fault detection and diagnosis in Dynamics. Automatica, 1971, 7.
[7] Willsky A S. A suvrey of design methods for failure detection in dynamic systems. Automatica, 1976, 12.
[8] Himmelblua D M. Fault detection and diagnosis in chemical and Petrochemical Process. Amsterdam: Elsevier Press, 1978.
[9]叶银忠,潘日芳,蒋慰孙.动态系统的故障检测与诊断方法.信息与控制. 1985, Vo1.15 (6):27-34.
[10]周东华,孙优贤.控制系统故障检测与诊断技术.北京:清华大学出版社, 1994.
[11] Frank P M. Fault diagnosis in dynamic systems using analytical and knowledge-based redundancy --- A survey and some new results. Automatica, 1990, Vo1.26 (3): 459-474.
[12] Jiang B, Staroswiecki, Marcel. Robust observer based fault diagnosis for a class of nonlinear systems with uncertainty. Proceedings of the IEEE Conference onDecision and Control, 2001, l: 161-166.
[13] Jiang B, Staroswiecki, Marcel. Fault diagnosis for nonlinear uncertain systems using robust/ sliding mode observers. Control and Intelligent Systems, 2005, Vo1. 33 (3): 151-157.
[14] Wu J D, Huang C W, Huang R W. An application of a recursive Kalman filtering algorithm in rotating machinery fault diagnosis. NDT and E International, 2004, 375:411-419.
[15]赵旭.基于统计学方法的过程监控与质量控制研究[博士学位论文].上海:上海交通大学, 2006.
[16] Chiang L H, Russell E L, Braatz R D, Fault detection and diagnosis in industrial systems. Springer-Verlag, London, 2001.
[17] Shewhart W A. Statistical method from the viewpoint of quality control. New York: Dover,1986.
[18] Page E S. Continuous inspection schemes. Biometrika, 1954, 41:100-114.
[19] Roberts S W. Control chart tests based on geometric moving average. Technometrics, 1959, 1: 239-250.
[20] Page E S. Cumulative sum control charts. Technometrics, 1961, 3:1-9.
[21] Thompson J R, Koronacki J. Statistical process control for quality improvement. New York: Chapman and Hall, 1993.
[22] Bissel D. Statistical methods for SPC and TQM. London: Chapman and Hall, 1994.
[23] Jackson J E, and G S Mudholkar. Control Procedures for residuals associated with principal component analysis. Technometrics, 1979, 21:341-349.
[24] MacGregor J F, Marlin T E, Kresta J, etal. Multivariate statistical methods in process analysis and control. Proceedings of the Fourth International Conference on Chemical Process Control. Amsterdam: Elsevier, 1991, 79-99.
[25] Kresta J, MacGregor J F, Marlin T E. Multivariate statistical monitoring of process operating performance. The Canadian Journal of Chemical Engineering, 1991(69): 35-47.
[26] Nomikos P, MacGregor J F. Multivariate SPC charts for monitoring batch processes. Technometrics, 1995, Vol. 37(1): 41-59.
[27] Nomikos P, MacGregor J F. Monitoring batch processes using multiway principal component analysis. American Institute of Chemical Engineers Journal, 1994, Vol.40 (8):1361-1375.
[28]蒋丽英.基于FDA-DPLS方法的流程工业故障诊断研究[博士学位论文].杭州:浙江大学, 2005.
[29] Sch?lkopf B, Smola A J, Muller K.Nonlinear component analysis as a kernel eigenvalue problem. Neural Computation, 1998, 10: 1299-1319.
[30] Jade A m, Srikanth B, Jayaraman V k, etc. Feature extraction and denoising using kernel PCA. Chemical Engineering Science, 2003(58):4441-4448.
[31] Choi S W, Lee C, Lee J M, Jin H P, Lee I B. Fault detection and identification of nonlinear processes based on kernel PCA. Chemometrics and Intelligent Laboratory Systems, 2005(75): 55-67.
[32]王华忠,俞金寿.基于核函数PCA的非线性过程实时监控方法.华东理工大学学报(自然科学版), 2005, 31(6): 783-787.
[33]樊立萍,徐阳.基于KPCA的污水处理过程监视.仪器仪表学报, 2005, 26(8): 157-158.
[34] Michael E T. Sparse kernel principal component analysis. Advances in Neural Information Processing Systems, 2000: 633-639.
[35] Lima A, Zen H, Nankaku Y, etc. Applying sparse KPCA for feature extraction in speech recognition .IEICE Transactions on Information and Systems, 2005, E88-D (3): 401-409.
[36]徐勇,杨静宇,陆建峰.提升KPCA方法特征抽取效率的算法设计.中国工程科学, 2005, 7(10): 38-42.
[37]解立春,王海清,李平. PKPCA:融合先验类别信息的非线性主元分析算法.电路与系统学报, 2003, 8(6): 95-100.
[38]王新峰,邱静,刘冠军.基于有监督核函数主元分析的故障状态识别.测试技术学报, 2005, 19(2): 200-203.
[39] Geladi P, Kowalski B R. Partial least-squares regression: A tutorial. Analytica Chimica Acta, 1986, 185: l-17.
[40] Duda R O, Hart P E. Pattern classification and scene analysis. John Wiley &Sons, NewYork, 1973.
[41] Sarnrnon J W. An optimal discriminant plane. IEEE Trans on Computers, 1970, 19(9):826-829.
[42] Foley D H, Sarnrnon J W. An optimal set of discriminant vectors. IEEE Trans on Computers, 1975, 24(3):281-289.
[43] Tian Q, Fainman Y, Lee S H. Comparison of statistical pattern-recognition algorithms for hybrid processingⅡ: eigenvector-based algorithm. J. Opt. Soc. Am. A 5, 1988, 5(10): 1670-1682.
[44] Hong Z Q, Yang J Y. Optimal discriminant plane for a small number of samples and design method of classifier on the plane. Pattern Recognition, 1991, 24(4): 317-324.
[45] Cheng Y Q, Zhuang Y M, Yang J Y. Optimal Fisher discriminant analysis using the rank decomposition. Pattern Recognition, 1992, 25(1):101-111.
[46]程永清,庄永明,杨静宁.一种改进的Fisher判别准则.计算机研究与发展. 1991, 28(6): 43-48.
[47] Liu K, Cheng Y Q, Yang J Y. An efficient algorithm for Foley-Sammon optimal set of discriminant vectors by algebraic method.International Journal of Pattern Recognition and Artificial Intelligence, 1992, 6(5): 817-829.
[48] Chiang L H, Russell E L, Braatz R D. Fault diagnosis in chemical processes using Fisher discriminant analysis, discriminant partial least squares, and principal component analysis. Chemometrics and Intelligent Laboratory Systems, 2000, 50: 243-252.
[49] Russell E L, Braat R D. Fault isolation in industrial processes using Fisher discriminant analysis. Foundations of Computer-aided Process Operations, Pekny J F and Blau G E, eds, AICHE, New York, 1998.
[50] Hyv?rinen A. Survey on independent component analysis. Neural Computing Surveys, 1999,2:94-128.
[51] Kano M, Tanaka S, Hasebe S, etal. Monitoring independent components for fault detection. AICHE J, 2003, 49(4):969-976.
[52] Kano M, Tanaka S, Ohno H, etal. The use of independent component analysis for multivariate statistical process control. Proc. of Int. Symp.on Advanced Control of Ind. Pro. , Kumamoto, Japan, 2002, 423-428.
[53] Lee J M, Yoo C, Lee I B. Statistical process monitoring with independent component analysis. Journal of Process Control, 2004, 14(5):467-485.
[54]陈国金,梁军,钱积新.独立元分析方法及其在化工过程监控和故障诊断中的应用.化工学报, 2003, 54(10): 1474-1477.
[55]卢娟,刘飞.基于规范变量分析的动态多变量过程故障诊断.计算机测量与控制, 2007, 15(8):984-986.
[56]郭明.基于数据驱动的流程工业性能监控与故障诊断研究[博士学位论文].杭州:浙江大学, 2004.
[57]何宁.基于ICA-PCA方法的流程工业过程监控与故障诊断研究[博士学位论文].杭州:浙江大学, 2004.
[58] Kosanovich K A, Piovoso M J. PCA of wavelet transformed process data for monitoring. Intelligent data analysis, 1997, 1(1):85-99.
[59]胡昌华,张军波,夏军,等.基于MATLAB的系统分析与设计:小波分析.西安:西安电子科技大学出版社, 1999.12.
[60]赵成燕.小波包主元分析方法在故障诊断中的应用研究[硕士学位论文].上海:华东理工大学, 2005.
[61] Macgregor J F, Kourti T. Statistical process control of multivariate process. Control Engineering Practice, 1995, 3(3): 403-414.
[62] Mamzic C L. Guidelines for the application of statistical process control in the continuous process industries. Measurement and Control, 1995, 28(April).
[63] Kosanovich K A, Piovoso M J. Multivariate statistical methods applied to process monitoring. Presented at EPSRC IMI Sponsored Meeting on Multivariate Statistical Process Control and Plant Performance Monitoring, December 19, 1995, Newcastle, U.K.
[64] Martin E B, Morris A J. An overview of multivariate statistical process control in continuous and batch process performance monitoring. Trans. Inst. MC, 1996, 18(2): 51-60.
[65] Zhang J, Martin E B, Morris A J. Fault detection and diagnosis using multivariate statistical techniques. Trans Ichem, 1996, 71 (1, Part A).
[66] Raich A, Cinar A. Statistical process monitoring and disturbance diagnosis in multivariable continuous processes. AIChE Journal, 1996, 42(4): 995-1009.
[67] Chen J, Bandoni A, Romagnoli J A. Robust statistical process monitoring. Computers & Chemical. Engineering, 1996, 20(s1): s495-s502.
[68] Chen J, Bandoni A, Romagnoli J A. Robust PCA and normal region in multivariate statistical process monitoring. AIChE Journal, 1996: 3563-3566.
[69] Qin S J, Li W H. Recursive PCA for adaptive process monitoring. Proceedings of the 14th World Congress of IFCA, Beijing, China, 1999.
[70] Zhao L J, Cai T Y, Wang G. Double moving window MPCA for online adaptive batch monitoring. Chin. J. Chem. Eng., 2005, 13 (5): 649-655.
[71] Jia F, Martin E B, Morris A J. Nonlinear principal components analysis with application to process fault detection. International Journal of Systems Science, 2001, 31:1473– 1487.
[72] Lee D S, Park J M, Vanrolleghem P A. Adaptive multiscale principal component analysis for on-line monitoring of a sequencing batch reactor. Journal of Biotechnology, 2005, 116(2): 195-210.
[73] Dong D, McAvoy T J. Nonlinear principal component analysis based on principal curves and neural networks. Computers and Chemical Engineering, 1996, 20 (1): 65-78.
[74] Cho J H, Lee J M, Choi S W. Fault identification for process monitoring using kernel principal component analysis. Chemical Engineering Science, 2005, 60 (1): 279-288.
[75]薄翠梅,张广明,王执铨.基于KPCA-PNN的复杂工业过程集成故障辨识方法.信息与控制, 2009, 38(1):98-109.
[76] Vapnik V. An overview of statistical learning theory. IEEE Trans. Neural Network, 1999, 10(5): 988-999.
[77] Cristianini N, Shawe-Taylor J. An Introduction to Support Vector Machines and Other Kernel -based Learning Methods. UK: Cambridge University Press, 2000.
[78] Genton M G. Classes of Kernels for Machine Learning:a statistical perspective. Journal of Machine Learning Research, 2001, 2: 299-312.
[79]阎威武,常俊林,邵惠鹤.基于滚动时间窗的最小二乘支持向量机回归估计方法及仿真.上海交通大学学报, 2004, 38(4): 524-526,532.
[80]王华忠,俞金寿.基于混合核函数PCR方法的工业过程软测量建模.化工自动化及仪表, 2005, 32(2): 23-25.
[81] Baudat G, Anouar F. Kernel-based methods and function approximation. In Proceedings of international conference on neural networks, Washington, DC. 2001: 1244-1249
[82] Baudat G, Anouar F. Feature vector selection and projection using kernels. Neurocomputing, 2003, 55: 21-38.
[83] Peiling Cui, Junhong Li, Guizeng Wang .Improved kernel principal component analysis for fault detection. Expert Systems with Applications 2008, 34:1210-1219.
[84] Chen J H, Liao C M. Dynamic process fault monitoring based on neural network and PCA. Journal of Process Control, 2002, 12(2): 277-289.
[85]肖应旺,徐保国.基于ICA-MPCA的间歇过程检测方法.仪器仪表学报, 2009, 30(5): 990-996.
[86] Zhao Shijian, Zhang Jie, Xu Yongmao. Performance monitoring of process with multiple operating modes through multiple PLS models. Journal of process Control, 2006, 16(7):763~772.
[87] Mehranbod N, Soroush M, Panjapornpon C. A method of sensor fault detection and identification. Journal of Process Control, 2005, 15(3):321~339.
[88] Ge M, Du R, Zhang G C, etal. Fault diagnosis using support vector machine with an application in sheet metal stamping operations. Mechanical Systems & Signal Processing, 2004, Vol.18: 143~159.
[89]马笑潇,黄席樾,柴毅.基于SVM的二叉树多类分类算法及其在故障诊断中的应用.控制与决策, 2003, Vol.18 (3): 272~276.
[90]程军圣,于德介,杨宇.基于内禀模态奇异值分解和支持向量机的故障诊断方法.自动化学报, 2006, Vol.32 (3): 475~480.
[91]刘爱伦,袁小艳,俞金寿.基于KPCA-SVC的复杂过程故障诊断.仪器仪表学报, 2007, 28(5):868-872.
[92]蒋少华,桂卫华,阳春华,等.基于核主元分析与多支持向量机的监控诊断方法及其应用.系统工程理论与实践, 2009, 29(9):153-159.
[93] Lanckriet G R G, Cristianini N, Bartlett P, e.al. Learning the kernel matrix with semidefinite programming. Journal of Machine Learning Research, 2004, 5: 27~72.
[94] Anderson E D, Anderson A D. The MOSEK interior point optimizer for linear programming //High Performance Optimization Berlin: Springer, 2000: 197~232.
[95] Hsu C, Lin C J. A comparison of methods for mufti-class support vector machines. IEEE Trans. on Neural Networks, 2002,.13 (2): 415~425.
[96]张军峰,胡寿松.基于多重核学习支持向量机的歼击机故障诊断.东南大学学报(自然科学版). 2007, 37 Sup. (I): 1~5.
[97]于德介,陈淼峰,程军圣等.基于AR模型和支持向量机的转子系统故障诊断方法.系统工程理论与实践, 2007, 27(5):152-159.
[98]张军峰,胡寿松.基于无约束优化的非线性支持向量回归.控制与决策,2009, 24(1):125-128.
[99] Keerthi S S, Chapelle O, Decoste D. Building support vector machines with reduced classifier complexity. Journal of Machine Learning Research, 2006, Vo1.7: 1493~1515.
[100] Chapelle O. Training a support vector machine in the primal. Neural Computation, 2007, Vol.19: 1155~1178.
[101] Kano M, Nagao K, Hasebe S, etal. Comparision of multivariate statistical process monitoring methods with applications to the Eastman challenge problem [J].Computers and Chemical Engineering, 2002, 26:161-174.
[102] Chen Q, Wynne R J, Goulding P, etal. The application of principal component analysis and kernel density estimation to enhance process monitoring. Control Engineering Practice, 2000, 8:531-543.
[103] Ku W, Storer R H, Georgakis C. Disturbance detection and isolation by dynamic principal component analysis. Chemometrics and Intelligent Laboratory System, 1995, 30: 179-196.
[104]宋凯,王海清,李平. PLS质量监控及其在Tennessee Eastman过程中的应用.浙江大学学报:工学版, 2005,39(5):657-662.
[105] Martin E B, Morris A J. Non-parametric confidence bounds for process performance monitoring charts. Journal of Process Control, 1996, 6(6), 349-358.
[106] Hyv?rinen A, Oja E. Independent component analysis:algorithms and applications.Neural Networks, 2000, 13(4-5):411-430.
[107]杨竹青,李勇,胡德文.独立成分分析方法综述.自动化学报, 2002, 28(5):762-772.
[108] Liangun, Qian ji-xin. Multivariate Statiscal Process Monitoring and Control: Recent Developments and Application to Chemical Industry. Chinese J. Chem.Eng., 2003, 11(2): 191-203.
[109] Seungjin Choi, Andrzej Cichocki. Blind Source Separation and Independent Component Analysis: A Review. Neural Information Processing-Letters and Reviews, 2005, 16(1):1-57.
[110] Achmad Widodo, Bo-Suk Yang, Tian Han. Combination of Independent analysis and support vector machines for intelligent faults diagnosis of induction motors.Expert Systems with Applications. Neural Networks, 2000, 13, 411-430.
[111]陈国金,梁军,刘育明等.基于多元统计投影方法的过程监控技术研究.浙江大学学报:工学版, 2004, 38(12): 1561-1565.
[112] Cheung Y M, Xu L. Independent component ordering in ICA time series analysis. NeuroComputing, 2001, 41(1):145-152.
[113] Jutten, C, Herault, J. Independent component analysis.Proceedings of European Signal Processing Conference, 1988, 287-314.
[114] T Lee. Independent Component Analysis: Theory and Applications. Kluwer Academic Publishers, Boston, USA, 1998.
[115] Hyv?rinen A. New approximations of differential entropy for independent component analysis and projection pursuit, Adv. Neural Inform. Process. Syst. 10 (1998) 273–279.
[116] Bell A J, Sejnowski A J. An information-maximization approach to blind separation and blind deconvolution. Neural Computation, 1995, 7(6):1129-1159.
[117] Amari S L, Cichocki A, Yang H. A new learning algorithm for blind source separation. Advances in Neural Information Processing Systems, 1996, 8:757-763.
[118] Hyv?rinen A, Oja E. A fast fixed-point algorithm for independent component analysis.Neural Computation, 1997, 9(7):1483-1492.
[119] Hyv?rinen A. Fast and robust fixed-point algorithms for independent component analysis. IEEE Transactions on Neural Networks, 1999, 10(3):626-634.
[120] Hyv?rinen A, Karhunen J, Oja, E. Independent Component Analysis. John Wiley & Sons, Inc, New York, USA, 2001.
[121] Li R F, Wang X Z. Dimension reduction of process dynamic trends using independent component analysis, Comp. Chem. Eng. 2002,26: 467-473.
[122] Yang J, Gao X, Zhang D, et al. Kernel ICA: An alternative formulation and its application to face recognition.Pattern Recognition, 2005, 38(10): 1784-1787.
[123] Bach F R, Jordan M I. Kernel independent component analysis.Journal of Machine Learning, 2002, 3(1):1-48.
[124] Lee J M, Qin S J, Lee I B. Fault detection of non-linear processes using kernel independent component analysis. Canadian Journal of Chemical Engineering, 2007, 85(4): 526-536.
[125] Zhang Y, Qin S J. Fault detection of nonlinear processes using multiway kernel independent component analysis. Industrial&Engineering Chemistry Research, 46(23):7780-7787.
[126] Cardoso J F, Soulomica A. Blind beamforming for non- Gaussian signals. IEEE Proc. F 1993, 140 (6): 362–370.
[127] Lee J M, Lee I B. Nonlinear process monitoring using kernel principal component analysis. Chemical Engineering Science, 2004, 59(1): 223-234.
[128] Simoglou A, Martin E B, Morris A J. Statistical performance monitoring of dynamic multivariate processes using state space modeling. Computers and Chemical Engineering, 2002,26(6):909-920.
[129]张曦.基于统计理论的工业过程综合性能监控、诊断及质量预测方法研究[博士学位论文].上海:上海交通大学, 2008.
[130] Tracy N D, Young J C, Mason R L. Multivariate control charts for individual observations. Journal of Quality Technology, 1992, 24: 88-95.
[131] Silverman B W. Density Estimation for Statistics and Data Analysis. Chapman & Hall, UK, 1986.
[132] Wand M P, Jones M C.Kernel smoothing.UK: Chapman&Hall, 1995.
[133] Pierre M, Drezet L, Harrison R F. A new method for sparsity control in support vector classification and regression. Pattern recognition, 2001, 34(1):111-125.
[134]彭文季,罗兴锜.基于小波包分析和支持向量机的水电机组振动故障诊断研究.中国电机工程学报, 2006, 26(24) : 164-169.
[135]杨慧中,高岩,张素贞等.独立成分分析和支持向量机混合方法在过程监控中的应用.计算机与应用化学, 2007, 24(3) : 295-298.
[136] Sebald D J, Buchlew J A. Support vector machines and the multiple hypothesis test problem. IEEE Trans on Signal Processing, 2001, 49(11): 2865-2872.
[137]袁胜发,褚福磊.支持向量机及其在机械故障诊断中的应用.振动与冲击, 2007, 26(11): 29-37.
[138] Fisher R A. The utilization of multiple measurements in taxonomic problem. Annals of Eugenics, 1936, 7(2): 179-188.
[139] Chiang L H, Russell E L, Braatz R D. Fault Detection and Diagnosis in Industrial Systems. Hong Kong: Springer, 2001.
[140] Jackson J E. A User’s Guide to Principal Components. Wiley, New York, 1991.
[141] He Q P, Qin S J, Wang J. A new Fault diagnosis method using fault directions in Fisher discriminant analysis. AIChEJ, 2005, 51(2):555-571.
[142] Mika S, R?tsch G, Weston J. Fisher discriminant analysis with kernels. Nerual Networks for Signal Processing IX, 1999, 41-48.
[143]王树青等编著.先进控制技术及应用[M].北京:化学工业出版社, 2001.