摘要
复杂工业过程一旦发生事故,不仅会影响生产的可靠运行还可能会造成人员和财产的巨大损失。随着对生产过程的安全性和可靠性要求的提高,故障诊断及故障预测技术受到人们的关注,己成为国内外过程控制领域的的热点研究方向之一。近年来,随着现代社会对多品种、多规格和高质量产品更迫切的市场需求,工业生产更加倚重于生产小批量、高附加值产品的间歇过程。间歇生产的安全可靠运行以及产品的高质量追求已成为人们关注的焦点。基于数据的多元统计分析技术因其在处理高维、高度耦合数据时具有独特的优势,越来越受到研究人员和现场工程师的青睐。间歇过程的统计建模、在线监测、故障诊断及预测已成为广泛的研究课题。
本文以间歇过程为研究背景,在深入研究主成分分析(PCA)方法和Fisher判别分析(FDA)方法的基础上,提出了一系列具有实际应用价值的间歇过程故障诊断及故障预测方法：
1.在深入研究间歇过程时段特性的基础上,利用主成分个数以及负载矩阵变异方向的不同,提出了一种基于多向主成分分析(MPCA)的间歇过程时段识别及故障诊断方法。该方法能够实现间歇过程稳定时段和过渡时段的自动识别,并针对稳定时段和过渡时段不同的数据特征建立统计模型,实现在线监测及故障诊断。
2.针对MPCA方法故障诊断的弱点,研究了利用正常数据及故障数据共同建模的FDA方法对间歇过程的故障诊断。首先针对故障数据不充分的情况,提出了基于Bootstrap的子时段递推多向Fisher判别分析(RMFDA)故障诊断方法,弥补了数据不足带来的弊端,取得了良好的故障诊断效果。针对非线性较强的间歇过程,提出了递推核Fisher判别分析(RKFDA)的故障诊断方法,有效的实现了非线性过程的故障诊断。
3.针对间歇过程缓变故障的预测问题,提出了基于Fisher特征向量差异度的缓变故障预测方法。通过建立Fisher特征向量差异度统计量的时序模型,预测未来批次的统计量值,并将其与控制限对比,有效的实现了间歇过程的缓变故障的预测。
4.结合前面提出的故障诊断及预测方法,提出了故障诊断系统的总体结构框架及主要功能,设计并开发了基于PCA方法和FDA方法的注塑成型故障诊断平台,用于各种故障诊断算法的验证、完善与实施。
上述算法在间歇过程实验系统及仿真研究中验证了其有效性与可靠性,从而丰富了间歇过程统计建模、在线监测、故障诊断及故障预测的研究成果。开发的平台不仅可以应用于注塑成型过程,也可在其他复杂工业生产过程中推广应用,具有重要的实际意义。
Incidents in complex industrial processes can not only seriously affect the operations of the processes, but also result in tremendous loss of personnel and wealth. With the increasing requirements on safety and reliability of manufacturing processes, fault diagnosis and prediction attracts more and more attention and has become a hot research topic in the process control. Recently, with the urging requirement in the market of multi-type and high-quality products, the manufacturing of high-value-added products produced mostly through batch processes has become increasingly important in many industries. Consequently, the safety in batch processes has also become a critical issue. In relevant approaches, data-based multivariate statistical analysis techniques show particular advantages in dealing with the high-dimensional and coupling data, which makes them specially and increasingly attractive. Multivariate statistical modeling, online monitoring, fault diagnosis and fault prediction have been under wide investigation for batch processes.
Based on Principal Component Analysis (PCA) and Fisher Discriminant Analysis (FDA), this dissertation develops a series of fault diagnosis and fault prediction methods for solving problems in batch processes:
1. According to the multi-phase characteristics of batch processes, a phase identification and fault diagnosis method is proposed in this dissertation. The proposed method makes use of the changes of principal component number and loading matrixes to identify stable phases and transition phases automatically. Consequently, focusing on their different data nature, different statistical models are respectively developed as well as the corresponding online monitoring strategy.
2. To overcome the weakness of MPCA fault diagnosis, FDA method is studied which takes into account both normal and fault data for modeling. For the cases with insufficient fault data, a diagnosis strategy is developed based on Bootstrap and phase-based Recursive Multi-way Fisher Discriminant Analysis (RMFDA) to improve the diagnosis precision. For nonlinear processes, a Recursive Kernel Fisher Discriminant Analysis (RKFDA) strategy is proposed for the nonlinear fault diagnosis.
3. According to the gradually-changing property of faults over batches, a fault prediction method is developed based on Fisher Eigenvector Difference. In the proposed method, the statistical values of the next batch are estimated by the autoregressive models built using Fisher Eigenvector Difference. By comparing the estimated values with the control limits, the gradually-changing faults can be predicted.
4. By combining the proposed fault diagnosis and prediction methods, a fault diagnosis framework is set up with its primary functions specified. A fault diagnosis platform is also implemented for injection modeling based on PCA and FDA to verify and illustrate the proposed statistical methods.
The successful simulations, experiments and applications of the proposed approaches to batch process systems demonstrate the effectiveness of the present methods, which, thus, enrich the achievement of statistical modeling, online monitoring, fault diagnosis and prediction for batch processes.The successful development of the platform also has practical significance, since it can be used not only for injection modeling process but also for other complex industrial processes.
引文
[1].杨志才.化工生产中的间歇过程——原理、工艺及设备[M].北京：化学工业出版社,2001.
[2].刘世成.面向间歇发酵过程的多元统计监测方法研究[D].杭州：浙江大学,2008.
[3].蒋丽英.基于FDA/DPLS方法的流程工业故障诊断研究[D).杭州：浙江大学,2005.
[4].陈勇.基于多元统计分析的生产过程故障诊断研究[J],2003.
[5].潘波.基于Petri网的间歇工业过程故障诊断[D].北京：北京化工大学,2006.
[6].李强.机械设备早期故障预示中的微弱信号检测技术研究[D).天津：天津大学,2008.
[7].王树青.工业过程控制工程[M].北京：化学工业出版社,2003.
[8]. C. Zhao, F. Wang, Gao, F., N. Lu, Jia, M. Adaptive monitoring method for batch processes based on phase dissimilarity updating with limited modeling data[J], Industrial & Engineering Chemistry Research,2007,46(14):4943 -4953.
[9]. C. Zhao, F. Wang, Z. Mao, N. Lu, and Jia, Mingxing. Adaptive monitoring based on independent component analysis for multiphase batch processes with limited modeling data[J], Industrial & Engineering Chemistry Research,2008,47(9):3104-3113.
[10].赵春晖.多时段间歇过程统计建模、在线监测及质量预测[D).沈阳：东北大学,2009.
[11].陆宁云.间歇工业过程的统计建模、在线监测、故障诊断及质量预测[D].沈阳：东北大学,2004.
[12]. Westerhuis J A, Kourti T, MacGregor J F. Comparing alternative approaches for multivariate statistical analysis of batch process data[J], J Chemometrics,1999,13(3-4): 397-413.
[13]. Nomikos P, MacGregor J F. Monitoring batch processes using multiway principal component analysis[J], AIChE J,1994,40(8):1361-1375.
[14]. Wold, Svante, Kettaneh, Nouna, Friden, Hakan, Holmberg, Andrea. Modelling and diagnostics of batch processes and analogous kinetic experiments[J], Chemometrics and Intelligent Laboratory Systems,1998,44(1-2):331-340.
[15]. Gurden, Stephen P., Westerhuis, Johan A., Bijlsma, Sabina, Smilde, Age K. Modelling of spectroscopic batch process data using grey models to incorporate external information[J], Journal of Chemometrics,2001,15(2):101-121.
[16]. Louwerse, D. J., Smilde, A. K. Multivariate statistical process control of batch processes based on three-way models[J], Chemical Engineering Science,2000,55(7): 1225-1235.
[17]. van Sprang, Eric N. M., Ramaker, Henk-Jan, Westerhuis, Johan A., Gurden, Stephen P., Smilde, Age K. Critical evaluation of approaches for on-line batch process monitoring[J], Chemical Engineering Science,2002,57(18):3979-3991.
[18]. Lee, Jong-Min, Yoo, Chang Kyoo, Lee, In-Beum. Enhanced process monitoring of fed-batch penicillin cultivation using time-varying and multivariate statistical analysis[J], Journal of Biotechnology,2004,110(2):119-136.
[19]. Albazzaz H, Wang X Z. Statistical process control charts for batch operations based on independent component analysis[J], Industrial & Engineering Chemistry Research, 2004,43(21):6731-6741.
[20]. Lee, Jong-Min, Yoo, Changkyoo, Lee, In-Beum. On-line Batch Process Monitoring Using Different Unfolding Method and Independent Component Analysis[J], JOURNAL OF CHEMICAL ENGINEERING OF JAPAN,2003,36(11):1384-1396.
[21]. Dong D, McAvoy T J. Multistage batch process monitoring[A]. The Proceedings of American control conference[C], Seattle, WA,1995,1857-1861.
[22]. Kosanovich K A, Piovoso M J, Dahl K S. Multi-way PCA applied to an industrial batch process[A]. The Proceedings of American Control Conference[C], Baltimore MD, 1994,1294-1298.
[23]. 桑海峰.诺西肽发酵过程生物参数软测量方法的研究[D).沈阳：东北大学,2006.
[24]. Isermann R., Balle P. Trends in the application of model based fault detection and diagnosis of technical processes[A]. Proc. Of IFAC World Congress[C], San Francisco, USA,1997,1-12.
[25]. P.M., Frank, Koppen-Seliger. New developments using AI in fault diagnosis[J],1996: 1-12.
[26]. Frank, Paul M. Fault diagnosis in dynamic systems using analytical and knowledge-based redundancy:A survey and some new results[J], Automatica,1990, 26(3):459-474.
[27]. 周东华.孙优贤.控制系统的故障检测与诊断技术[M].北京：清华大学出版社,1994.
[28]. Jiang, Liying, Xie, Lei, Wang, Shuqing. Fault Diagnosis for Batch Processes by Improved Multi-model Fisher Discriminant Analysis[J], Chinese Journal of Chemical Engineering,2006,14(3):343-348.
[29]. 李厦.基于Petri网的故障诊断技术研究及其在液压系统中的应用[J],2006.
[30]. 胡学发.水压试验机故障诊断与故障预测方法研究(D).沈阳：东北大学,2008.
[31]. Lee, Jong-Min, Yoo, ChangKyoo, Lee, In-Beum. On-line batch process monitoring using a consecutively updated multiway principal component analysis model [J], Computers & Chemical Engineering,2003,27(12):1903-1912.
[32]. 刘玥,张贝克,吴重光.基于模糊推理的SDG故障诊断新方法[J],计算机应用,2005,25(11)：2661-2664.
[33]. 许欣.原油蒸馏装置SDG故障诊断应用研究[D].北京：北京化工大学,2008.
[34]. 李传坤.基于SDG的化工过程故障诊断系统研究(D].青岛：青岛科技大学,2009.
[35]. 王磊.SDG故障诊断试验平台的研究与开发[D].北京：北京化工大学,2005.
[36]. 赵静一,上官倩芡,马保海.10MN水压机液压系统故障树分析[J],液压与气动,1999,(03)：36-38.
[37]. 甘传付,曹宏炳黄允华蔡金燕.基于fmeca、Fta的故障诊断和故障预测[J],系统工程与电子技术,2002,(11).
[38]. 杜江,任滢.故障智能诊断专家系统模型研究[J],光电技术应用,2009,(04).
[39]. 何彪,刘顺波.基于遗传模糊c-均值聚类算法的除湿机故障诊断[J],制冷空调与电力机械,2009,(04).
[40]. 周家驹,许志宏,石乐明,张跃敏,蔡松筠.人工神经网络方法在材料性能预测及化工过程故障诊断中的应用[J],过程工程学报,1993,(01).
[41]. D. Fuessel, R. Isermann. Hierarchical motor diagnosis utilising structural knowledge and a self-learning neuro-fuzzy scheme [J], IEEE Transactions on Industrial Electronics, 2000,47(5):1070-1077.
[42]. Frank, Paul M., Koppen-Seliger, Birgit. Fuzzy logic and neural network applications to fault diagnosis[J], International Journal of Approximate Reasoning,1997,16(1): 67-88.
[43]. 牛征.基于多元统计分析的火电厂控制系统故障诊断研究[D],
[44]. 冯雄峰。多元统计过程控制研究及在炼油生产过程中的应用博士[D]清华大学,1999。华北电力大学,2006.4.
[45]. Kano, Manabu, Hasebe, Shinji, Hashimoto, Iori, Ohno, Hiromu. A new multivariate statistical process monitoring method using principal component analysis[J], Computers & Chemical Engineering,2001,25(7-8):1103-1113.
[46]. 付克昌,吴铁军.基于特征子空间的kpca及其在故障检测与诊断中的应用[J],化工学报,2006,(11).
[47]. 朱奇,侍洪波.基于pca多变量统计的故障检测与诊断[J],控制工程,2006,(S1).
[48]. 朱大奇,易健雄,袁芳.基于小波灰色预测理论的旋转机械故障预测分析仪[J],仪器仪表学报,2008,(06).
[49]. 许丽佳,龙兵,王厚军.基于lssvm-Hmm的发射机故障预测研究[J],仪器仪表学报,2008,(01).
[50]. 孙才新,毕为民 周湶 廖瑞金 陈伟根.灰色预测参数模型新模式及其在电气绝缘故障预测中的应用[J],控制理论与应用,2003,(05).
[51]. 周东华.一种非线性系统的传感器故障检测与诊断新方法[J],自动化学报,1995,(03).
[52]. 冯恩波,肖德云,方崇智.一种基于时序预测神经网络的故障预测方法及其应用[J],自动化学报,1995,(03).
[53]. 胡寿松,张正道.基于神经网络的非线性时间序列故障预测[J],自动化学报,2007,(07).
[54]. Bowerman, Bruce L., O'Connell, Richard T. Forecasting and Time Series:An applied approach[M].北京：机械工业出版社,2003.
[55]. S., LU K., R., Sakes. Failure Prediction for an On-Line Maintenance System in a Poisson Shock Environment[J], Systems, Man and Cybernetics, IEEE Transactions on, 1979,9(6):356-362.
[56]. Milne, R., Bain, E., Drummond, M. Predicting faults with real-time diagnosis[J], Proceedings of the 30th Conference on decision and control [C], Brighton, England,1991, 3:2598-2603.
[57]. Khoshgoftaar, T. M., Pandya, A. S., More, H. B. A neural network approach for predicting software development faults [A]. Software Reliability Engineering,1992. Proceedings., Third International Symposium on,1992,83-89.
[58]. Gadzheva, E. D., Raykovska, L. H. Nullator-norator approach for diagnosis and fault prediction in analog circuits[A]. IEEE International Symposium on Circuits and Systems (ISCAS'94)[C], Arizona, USA,1994,53-56.
[59]. J.Dimopoulos, Nikitas, Watkins, Andrew, Neville, Stephen, F.Li., Kin. An Expert Network Analyzer: fault diagnosis and Prediction[J], Canadian conference on electrical and computer engineering,1993,2:1213-1216.
[60]. Lennox, B., Rutherford, P., Montague, G. A., Haughin, C. A novel fault prediction technique using model degradation analysis[A]. American Control Conference,1995. Proceedings of the[C], Washington,1995,3274-3278.
[61]. Vijay Devabhaktuni, Mustapha C.E.Yagoub, Qi-Jun Zhang. A robust algorithm for automatic development of neural network models for microwave applications[A]. IEEE MTT International Microwave Symp.[C], Digest,2001,2087-2090.
[62]. Vijay Devabhaktuni, Mustapha C.E.Yagoub, Qi-Jun Zhang. A robust algorithm for automatic development of neural network models for microwave applications[J], IEEE Trans. Microwave Theory and Tech.,2001,49(12):2282-2291.
[63]. Tai-cong, Chen, Da-jian, Han, Au, F. T. K., Tham, L. G. Acceleration of Levenberg-Marquardt training of neural networks with variable decay rate [A]. Neural Networks,2003. Proceedings of the International Joint Conference on[C], Portland, OR, United States,2003,1873-1878.
[64]. Mie Mie Thet Thwin, Tong-Seng Quah. Application of neural network for predicting software development faults using object-oriented design metrics[A]. Proceedings of the 9th International conference on neural information processing (ICONIP-02)[C], Singapore,2002,2312-2316.
[65]. Ali A.Ghorbani, Virendrakumar C.Bhavsar. Incremental communication for Multilayer neural networks:error analysis[J], IEEE transactions on neural networks,1998, 9(1):68-82.
[66]. Shing Chiang, Tan, Chee Peng, Lim. Condition monitoring and fault prediction via an adaptive neural network[A]. TENCON 2000. Proceedings,2000,13-17 vol.11.
[67]. 程惠涛,黄文虎姜兴渭.基于灰色模型的故障预测技术及其在空间推进系统上的应用[J],推进技术,1998,19(03)：74-77.
[68]. 李勇,孙艳萍孙海波宋景东.用于故障预测的bp网络模型及改进[J],东北电力学院学报,1999,19(01)：27-32.
[69]. 黄景德,崔山宝王兴贵王祖光.正向推理型故障模糊预测系统的知识表示与推理[J],计算机工程,2001,27(02)：78-79.
[70]. 黄景德,王兴贵 王祖光.动态模糊综合评判法及其在故障预测中的应用[J],模糊系统与数学,2001,15(04)：96-99.
[71]. 黄景德,王兴贵王祖光.基于模糊评判的故障预测系统研究[J],电子机械工程,2000,(06)：42-44,55.
[72]. 黄景德,王强王兴贵王祖光.基于知识的故障模糊预测系统的设计方法[J],计算机自动测量与控制,2001,9(05)：26-27.
[73]. 赵海东,缪旭东,吕世聘.基于神经网络的军用飞机故障预测系统研究[J],系统工程与电子技术,2003,25(07)：894-896.
[74]. 郭明,谢磊,王树青.基于模型的多尺度间歇过程性能监控[J],系统工程理论与实践,2004,(01)：97-102.
[75]. 李骥,张洪钺.基于预测滤波器的故障诊断方法研究[J],中国科学e辑,2004,34(12)：1375-1392.
[76]. Lewin, D. R. Predictive maintenance using PCA[J], Control Engineering Practice, 1995,3(3):415-421.
[77]. 张蕾,曹其新,Lee, Jay, Lewis, Frank L.基于pca-Cmac的设备性能退化评估(英文)[J], Journal of Southeast University(English Edition),2005,21(3):299-303.
[78]. 胡终须.非完整移动机器人的鲁棒控制研究[D).广州：华南理工大学,2000.
[79]. 胡国良.盾构模拟试验平台电液控制系统关键技术研究(D).杭州：浙江大学,2006.
[80]. 陈庆樟.汽车再生制动稳定性与制动踏板平稳性控制研究[D].镇江：江苏大学,2008.
[81]. JACKSON J E. A User's Guide to Principal Components [M]. New York:Wiley, 1991.
[82]. Kourti T, MacGregor J F. Process analysis, monitoring and diagnosis, using multivariate projection methods [J], Chemometrics and Intelligent Laboratory Systems, 1995,28(19):3-21.
[83]. Wang X Z. Data mining and knowledge discovery for process monitoring and control [M], Springer:London,1999.
[84]. GEL ADI P, KOWALSHI B R. Partial least squares regression:A tutorial [J]. Analytica Chimica Acta,1986,185(1):1-17.
[85]. HOSKULDSSON A. PLS regression methods [J]. Journal of Chemometrics,1988, 2(3):211-228.
[86]. 陆宁云,王福利,高福荣,王姝.间歇过程的统计建模与在线监测,自动化学报,2006,32(3)：400-410
[87]. Nomikos P, MacGregor J F. Multi-way partial least squares in monitoring batch processes [J], Chemometrics and Intelligent Laboratory Systems,1995(1):30,97-108.
[88]. Nomikos P, MacGregor J F. Multivariate SPC charts for monitoring batch processes [J]. Technometrics,1995,37(1):41-59.
[89]. Lu N Y, Gao F R, Wang F L. A sub-PCA modeling and on-line monitoring strategy for batch processes. AIChE J,2004,50(1):255-259.
[90]. Chunhui Zhao, Fuli Wang, Ningyun Lu, Mingxing Jia. Stage-based soft-transition multiple PC A modeling and on-line monitoring strategy for batch processes. Journal of Process Control,2007,17(9),728-741.
[91]. Miller, P., Swanson, R.E. and Heckler, C.E. Contribution plots:A missing link in multivariate quality control [J], Appl. Math. And Comp. Sci.,1992,8(4):775-792.
[92]. Undey C, Cinar A. Statistical monitoring of multistage, multiphase batch processes [J], IEEE Control Systems Magazine,2002,22(55):40-52.
[93]. Kosanovich K A, Dahl K S, Piovoso M J. Improved process understanding using multiway principal component analysis [J], Industrial & Engineering Chemistry Research, 1996,35(1):138-146.
[94]. Lennox B, Hiden H, Montague G, Kornfeld G, Goulding P. Application of multivariate statistical process control to batch operations [J], Computers & Chemical Engineering,2000,24(2-7):291-296.
[95]. Doan X T, Srinivasan R, Bapat, P M, Wangikar P P. Detection of phase shifts in batch fermentation via statistical analysis of the online measurements:A case study with rifamycin B fermentation [J], J Biotechnology,2007,132(2):156-166.
[96]. Lu N Y, Gao F R. Stage-Based Process Analysis and Quality Prediction for Batch Processes [J], Industrial & Engineering Chemistry Research,2005,44(10):3547-3555.
[97]. Lu N Y, Gao F R. Stage-Based Online Quality Control for Batch Processes. Industrial & Engineering Chemistry Research,2006,45(7):2272-2280.
[98]. Camacho J, Pico J. Online monitoring of batch processes using multi-phase principal component analysis [J], J Process Control,2006,16(10):1021-1035.
[99]. Camacho J, Pico J. Multi-phase principal component analysis for batch processes modeling [J], Chemometrics and Intelligent Laboratory Systems,2006,81(2):127-136.
[100]. Lu N Y, Yang Y, Wang F L, Gao F R. Stage-based multivariate statistical analysis for injection molding [J], Proceedings of International symposium on advanced control of chemical processes,2003,471-476.
[101]. Lu N Y, Gao F R, Yang Y, Wang F L. PCA-based modeling and on-line monitoring strategy for uneven-length batch processes [J], Industrial & Engineering Chemistry Research,2004,43(13),3343-3352.
[102]. Lu N Y, Yang Y, Wang F L, Gao F R.A Stage-based Monitoring Method for Batch Process with Limited Reference Data [J],7th International Symposium on Dynamics and Control of Process Systems,2004.
[103]. Chunhui Zhao, Fuli Wang, Zhizhong Mao, Ningyun Lu, and Mingxing Jia.Quality prediction based on phase-specific average trajectory for batch processes. AIChE Journal, 2008,54(3),693-705.
[104]. Fisher R. A., The utilization of multiple measurements in taxonomic problem [J], Annals of Eugenics,1936,7(2):179-188.
[105]. 陈亚华,蒋丽英,郭明,王树青.基于多向Fisher判据分析的间歇过程性能监控[J],吉林大学学报(信息科学版),2004,22(4)：384-387.
[106]. 蒋浩天.工业系统的故障检测与诊断[M].北京：机械工业出版社,2003.
[107].蒋丽英.基于FDADPLS方法的流程工业故障诊断研[D].浙江大学,2005,3.
[108]. Xu Y., Yang J. Y. and Jin Z.. A novel method for Fisher discriminant analysis [J], Pattern Recognition,2004.37(2):381-384.
[109]. Geladi P., Kowalski B. R.. Partial least-squares regression:A tutorial [J]. Analytica Chimica Acta,1986,185:1-17.
[110]. J Wise B. M., Gallagher N. B.. The process chemometrics approach to process monitoring and fault detection [J], Journal of Process Control,1996,6(6):329-348.
[111]. L.Ljung.System Identification [M], Theory for Users, New Jersey:Prentice-Hall, 1987.
[112]. Miller P., Swanson R. E., Heckler C. F.. Contribution plots:the missing link in multivariate statistical process control [J], Annual Reviews in Control,1999,23:35-44.
[113]. He Q. P., Qin S. J., Wang J.. A new fault diagnosis method using fault directions in Fisher discriminant analysis [J], AIChE J.,2005,51(2):555-571.
[114]. Efron Bradley. Bootstrap methods:another look at the jackknife [J]. The Annals of Statistics,1979,7(1):1-26.
[115]. Quenodille M H. Approximate tests of correlation in time - series[J]. Journal of Royal Statistical Society, B,1949 (11):68-
[116]. Zhang J. Martin E B, Morris A J, Kiparissies C. Inferential estimation of polymer quality using stacked neural networks [J], Computers & Chemical Engineering,1997, 21(sup):1025-1030.
[117]. Zhang J. Inferential estimation of polymer quality using bootstrap aggregated neural networks [J], Neural Networks,1999,12(6):927-928.
[118]. Zhang J. Developing robust non-linear models through bootstrap aggregated neural networks [J], Neurocomputing,1999,25(1):93-113.
[119]. Wehrens R, Putter H, Buy dens L M C. The bootstrap:a tutorial [J], Chemometrics and Intelligent Laboratory Systems,2000,54(1):35-52.
[120]. Zhang J, Martin E B, Morris A J, Kiparissies C. Inferential estimation of polymer quality using stacked neural networks [J], Computers & Chemical Engineering,1997, 21(sup):1025-1030.
[121]. Zhang J. Inferential estimation of polymer quality using bootstrap aggregated neural networks [J], Neural Networks,1999,12(6):927-928.
[122]. Zhang J. Developing robust non-linear models through bootstrap aggregated neural networks [J], Neurocomputing,1999,25(1):93-113.
[123]. Mika,S.,Ratsch,G.,Weston,J.Fisher discriminant analysis with kernels[J], Nerual Networks for Signal Processing IX,1999,41-48.
[124]. Scholkopf,B.,Mika,S.,Burges,C. Input space versus feature space in kernel-based methods. IEEE Tran. Neural Networks,1999,10(5):1000-1016.
[125]. Box G. E, Jenkins G. M. Time Series Analysis Forecasting and Control [M], San Francisco:Holden-Day,1970.
[126].杨素春,王朝晖,于晓红.基于ARMA模型的往复式压缩机状态预测[J],石油化工设备,2007,36(1)：1-4.
[127]. 吴怀宇.时间序列分析与综合[M].武汉大学出版社,2004：66-80.
[128]. Martin,E.B.,Morris,A.J.Non-parametric confidence bounds for process performance monitoring charts[J] Journal of Process Control,1996,6:349-358.