基于多种群免疫量子粒子群的粗糙集属性约简与故障诊断
|
摘要
随着科学技术的飞速发展,现代工业过程不断向大型化、集成化方向发展,这导致了系统复杂性的提高以及过程变量的大量增加,因此一旦生产过程产生故障,势必会造成巨大的经济损失,甚至是人员伤亡等灾难性后果,所以及时准确地检测和诊断出故障具有重要的现实意义。
为了迅速、可靠地实现故障诊断,本文在深入研究粒子群优化算法的基础上,引进了量子系统、免疫算子、多种群分群等思想,分析了其对寻优性能的影响,提出了一种新的组合算法MIQPSO,该算法对量子粒子群算法进行分群,并通过接种疫苗,指导粒子朝更优化方向进化,提高了量子粒子群的收敛速度和寻优能力。将本文提出的算法应用于粗糙集属性约简,对UCI相关数据集的约简结果表明该算法具有良好的约简效果。将基于MIQPSO的属性约简算法应用在故障诊断的特征选择中,以TE过程为对象开展研究,选择了该过程中相应的一些故障样本,仿真结果表明应用本文提出的算法与PCA等其他方法相比具有更高的诊断性能。
With the progress of modern industries in large-scale and integration, processes have become more and more complex and contain a large lumber of measure variables, so once faults occur in the production process, they will lead to the huge economic losses, and even casualties. Therefore, timely and accurately detecting and diagnosising the process fault has a very practical significance.
To implement fault diagnosis rapadly and reliable, the thorough research has been conducted on Particle Swarm Optimization (PSO). Then the quantum system, Immunity algorithm and Multi-swarm algorithm are introduced. The test results of function show these operations provide better optimization capabilities.
On this basis, MIQPSO is proposed. In this algorithm, it divides the whole particle swarm into different groups and searches in different phases, and vaccination can guide the particles to evolve towards a much better direction. It is validated experimentally that this algorithm achieved much better result both in convergence speed and optimization capabilities in comparison with other algorithms.
Finally, the MIQPSO-based attribute reduction algorithm is applied to solve fault feature selection of fault diagnosis. The simulation results show that feature selection based on this algorithm and SVM has an excellent fault diagnosis performance for fault diagnosis of TE process.
为了迅速、可靠地实现故障诊断,本文在深入研究粒子群优化算法的基础上,引进了量子系统、免疫算子、多种群分群等思想,分析了其对寻优性能的影响,提出了一种新的组合算法MIQPSO,该算法对量子粒子群算法进行分群,并通过接种疫苗,指导粒子朝更优化方向进化,提高了量子粒子群的收敛速度和寻优能力。将本文提出的算法应用于粗糙集属性约简,对UCI相关数据集的约简结果表明该算法具有良好的约简效果。将基于MIQPSO的属性约简算法应用在故障诊断的特征选择中,以TE过程为对象开展研究,选择了该过程中相应的一些故障样本,仿真结果表明应用本文提出的算法与PCA等其他方法相比具有更高的诊断性能。
With the progress of modern industries in large-scale and integration, processes have become more and more complex and contain a large lumber of measure variables, so once faults occur in the production process, they will lead to the huge economic losses, and even casualties. Therefore, timely and accurately detecting and diagnosising the process fault has a very practical significance.
To implement fault diagnosis rapadly and reliable, the thorough research has been conducted on Particle Swarm Optimization (PSO). Then the quantum system, Immunity algorithm and Multi-swarm algorithm are introduced. The test results of function show these operations provide better optimization capabilities.
On this basis, MIQPSO is proposed. In this algorithm, it divides the whole particle swarm into different groups and searches in different phases, and vaccination can guide the particles to evolve towards a much better direction. It is validated experimentally that this algorithm achieved much better result both in convergence speed and optimization capabilities in comparison with other algorithms.
Finally, the MIQPSO-based attribute reduction algorithm is applied to solve fault feature selection of fault diagnosis. The simulation results show that feature selection based on this algorithm and SVM has an excellent fault diagnosis performance for fault diagnosis of TE process.
引文
[1]周东华,叶银忠.现代故障诊断与容错控制.北京：清华大学出版社.2000
[2]夏希楼.机械设备故障检测诊断技术的现状与发展.煤矿机械.2007,28(3)：183-185
[3]范玉刚,李平,宋执玉.基于特征样本的KPCA在故障诊断中的应用.控制与决策.2003,18(2)：229-232
[4]Chiang L. H., Russell E. L, Braatz R. D. Fault detection and diagnosis in industrial systems. Springer-Verlag. London,2000
[5]杜运成,石红瑞,杨晓波.控制系统故障诊断方法综述.工业仪表与自动化装置.2008.5：9-13
[6]Garcia E. A, Frank P. M. On the relationship between observer and parameter ide-notification based approaches to fault detection. Proc. Of IFAC Word Congress.2001:25-29
[7]Ye H, Wang G z, Ding S X. A new parity space approach for fault detection based on stationary wavelet transform. IEEE Trans on Automatic Control.2004,49(2):281-287
[8]魏霞,徐敏强,鹿卫国.故障诊断技术及应用综述.热力透平.2004,3(300)：238-242
[9]牛星岩,沈颂华.基于小波变换的整流装置故障特征提取.电子测量技术.2007,30(10)：122-126
[10]黄大荣,胡必锦.基于专家知识库属性重要度的故障诊断方法研究.计算机仿真.2007,24(4)：155-157
[11]朱旭东,戴文战,郎燕峰.基于神经网络的方法在故障诊断中的应用.机电工程,2003,20(5)：75-78
[12]窦金生,汤天浩.基于知识的故障诊断技术及其在船舶上的应用.船舶工程.2007,29(4)：72-74
[13]赵熙临,刘辉.粗糙集理论在故障诊断中的问题分析.计算机技术与发展.2008,1：132-135
[14]肖小锋,蔡金燕,谌叶飞.基于故障树分析的监测点选取.计算机应用与软件.2007,24(9)：24-25
[15]张金泽,单甘霖.改进的SVM算法及其在故障诊断中的应用研究.电光与控制.2006,13(6)：97-100
[16]许晖,焦留芳,韩西宁.基于两级神经网络的传感器在线故障诊断技术研究.传感技术学报.2008,21(10)：1794-1797
[17]田玉玲.多层免疫故障诊断模型的研究.计算机工程与应用.2008,44(9)：245-248
[18]张力,李相平,陈信.FTA在末制导雷达故障诊断中的应用.海军航空工程学院学报.2004,19(1)：187-190
[19]金鑫,任献彬,周亮.智能故障诊断技术研究综述.理论与方法.2009,28(7)：30-32
[20]Pawlak Z. A rough set view on Bayes'theorem. IntemationaI Journal of Intelligent Systems.2003,18:487-498.
[21]简友光,简曙光.基于Rough集的数据约简算法研究综述.计算机与数字工程.2006(5)： 27-29
[22]申锦标,吕跃进.变精度与程度粗糙集的一种推广.计算机工程与应用.2008,44(36)：45-47
[23]Dutsh I. A logic for rough sets. Theoretical Computer Science.179(1997): 427-436
[24]Pawlak Z. Rough set theory and its applications to data analysis. Cyber-netics and Systems:An International Journal.1998,29(7):661-688
[25]黎平,宋坤等.基于粗糙集理论的关联聚类中长期负荷预测法.继电器.2008.36(1)：43-47
[26]吕士颖,郑晓鸣,王晓东.基于量子粒子群优化的属性约简.计算机工程.2008.18(34)：65-69
[27]丁卫平,邓伟,管致锦.基于粗糙集的属性约简优化算法研究.苏州大学学报.2008.24(2)：52-55
[28]沈晨鸣.基于粗糙集的数据挖掘属性约简算法研究.南京工程学院学报.2007.5(1)：31-34
[29]Ziarko W. Variable Precision Rough Set Model. Journal of Computer and System Sciences.1993,46:39-59
[30]Pawlak Z, Rough set theory and its applications to data analysis, Cyber-netics and system.1998,29(7):661-688
[31]Pawlak Z, Rough sets, rough relations and rough functions, Fundamenta informaticate.1996,27(2,3):103-108
[32]苏志同,李晋宏,林满山.基于差别矩阵的属性约简算法及其应用.计算机工程与应用.2010,46(7)：221-223
[33]蒋瑜,王燮.基于差别矩阵的Rough集属性约简算法.系统仿真学报.2008.20(14)：3717-3725
[34]申锦标，邓春燕,吕跃进.一种基于差别矩阵的新的属性约简方法.重庆工学院学报.2009.23(9)：84-87
[35]叶明全,伍长荣.决策表分解及其最小属性约简研究.计算机工程与应用.2009.45(30)：126-128
[36]覃志华,唐承超,王加阳.不相容决策表的核属性计算.计算机工程与应用.2005. 35：44-46
[37]黄少荣.粒子群优化算法综述.计算机工程与设计,2009,30(8)：1977-1980
[38]郑毅,吴斌.由鸟群和蚂蚁想到的—基于主体的仿真和群集智能的研究.微电脑世界.2001：7-13.
[39]Fan S. K, Liang Y. C, Zahara E. Hybrid simplex search and particle swarm optimization for the global optimization of multimodal functions. Enginee-ring Optimization.2004,36(4):401-418
[40]Mensah D. R, Liang W, et al. Evaluation of nC27 petroleum spray oil for activity against Helicoverpa spp. on commercial cotton fields in Australia. International Journal of Pest Management.2005,51(1):63-70
[41]Ye Z. B, Tang W. C, Li S. S. Analysis of millimetre wave microstrip circulator with a magnetised ferrite sphere by fdtD method with new extrapolation technique. International Journal of Electronics.2009,96(4):409-417
[42]Liu J. L, Lin J. H. Evolutionary computation of unconstrained and constrained problems using a novel momentum-type particle swarm optimization. Enginee-ring Optimization.2007,39(3):287-305
[43]Dong S.F, Dong Z. C, et al. Improved PSO algorithm based on chaos theory and its application to design flood hydrograph. Water Science and Enginee-ring.2010,3(2):156-165
[44]Zhu G. Y, Zhang W. B. Drilling path optimization by the particle swarm optimization algorithm with global convergence characteristics. Interna-tional Journal of Production Research.2007,46(8):2299-2311
[45]杨传将,刘清,黄珍.一种量子粒子群算法的改进方法.计算技术与自动化.2009,8(21)：100-103
[46]Kuang S, Cong S. Generalized control of quantum systems in the frame of vector treatment.2009,7(4):395-399
[47]王加阳,谢曩.基于量子粒子群优化的最小属性约简算法.计算机工程.2009,35(12)：148-153
[48]高鹰,谢胜利.免疫粒子群优化算法.计算机工程与应用.2004.6：4-6
[49]Chun J. S, Kim M. K, Jung H. K. Shape optimization of electromagnetic devices using immune algorithm. IEEE Trans on Magnetics.1997,33(2):1876-1879.
[50]蔡自兴,龚涛.免疫算法研究的进展.控制与决策.2004,19(8)：842-846
[51]张洪波.多种群粒子群分层进化优化算法.中国科技信息.2010,8：40-42
[52]李爱国.多粒子群协同优化算法.复旦学报.2004,43(5)：923-925
[53]陈国初,俞金寿.两群微粒群优化算法及其应用.2007,24(2)：294-298.
[54]许珂,刘栋.多粒子群协同进化算法.计算机工程与应用.2009,45(3)：51-54
[55]高翔,唐普英.设立禁区的多粒子群优化算法.计算机工程与应用.2010,46(10)：38-40
[56]杨传将,刘清,黄珍.一种量子粒子群算法的改进方法.计算技术与自动化.2009,28(1)：100-103
[57]袁晓蜂,许化龙,陈淑红.基于量子遗传算法的粗糙集属性约简新方法.计算机工程.2007,33(15)：184-186
[58]高家全,何桂霞,王雨顺.典型的人工免疫算法性能比较与分析.计算机工程与应用.2009,45(10)：208-210
[59]Sa J. P. M. D. Pattern Recognition. Concepts, Methods and Applications. Springer.2001
[60]边肇祺,张学工.模式识别(第二版).北京,清华大学出版社,2000
[61]Theodoridis S, Koutroumbas K. Pattern recognition, Elsevier,2003
[62]Baudat G, Anouar F. Feature vector selection and projection using kerls. Neuro computing.2003,55:21-38
[63]Webb A.R. Statistical pattern recognition. Wiley.2002
[64]唐静远,师奕兵.采用模糊支持向量机的模拟电路故障诊断新方法.电子测量与仪器学报.2009,6：7-12
[65]张勇,陈莉.聚类与PCA融合的特征提取方法研究.计算机工程与应用.2010.46(11)：148-150
[66]Sangdon L. Comparative analyses of anthropometry associated with verweight and obesity:PCA and ICA approaches. Theoretical Issues in Ergonomics Science.2008,9(5):441-475
[67]Dash M, Liu H. Consistency-based search in featuure selection. Artificial intelligence.2003,151:155-176
[68]Dettling M, Buhlmann P. Finding predictive gene groups from microarray data. Journal of multivariate analysis.2004,90:106-131
[69]吕成岭,彭力,张立位.一种基于快速特征选择的故障诊断方法.计算机工程与应用.2010,46(14)：235-237
[70]Sun Z. H, Bebis Z. H. Object Detection using feature subset selection. Pattern Recognition.2004,37:2165-2176
[71]Jain A, Duin R, et al. Statistical pattern recognition:a review. IEEE Transactions on Pattern Analysis and Machine Intelligence.2000,22(1): 4-37.
[72]YU Y, LU Z, et al. Scheduling problems on tardiness penalty and earliness award with simply linear processing time. Journal of Shanghai Univer-sity.2009,13(2):123-128
[73]叶玉玲,伞冶.一种混合决策系统属性约简算法研究.系统仿真学报,200,19(13)：2988-2991
[74]徐淑平林福宗.基于图像中心加权特征的图像检索.计算机应用与软件.2006,23(2)：3-5
[75]Burges C.J.C. A tutorial on support vector machines for pattern recog-nition. Data Mining and KnowledgeDiscovery.1998,.2:127-167
[76]WangA. N, Yuan W. J. A study of a multi-class classificational algorithm of SVM combined with ART, IEEE Third Intemantional Conference on Natual Compu-tation.2007
[77]Zhang R., Ma J. An improved SVM method P-SVM for classification of remotely sensed data. International Journal of Remote Sensing.2008,29(20): 6029-6036
[78]Kressel U, Pairwise. Classification and support vector machines in Advanees in Kerne Methods-Support Veetor Leaming. MIT Press Cambridge Massaehusetts, chapter 15,1999
[79]王海清,蒋宁.自适应Kernel学习网络在TE过程组分仪建模中的应用.化工学报.2007,58(2)：425-430
[80]Li W. H, Yue H H, et al. Recursive PCA for adaptive process monitoring. Jour-nal of Proeess Control.2000,19:471-486
[2]夏希楼.机械设备故障检测诊断技术的现状与发展.煤矿机械.2007,28(3)：183-185
[3]范玉刚,李平,宋执玉.基于特征样本的KPCA在故障诊断中的应用.控制与决策.2003,18(2)：229-232
[4]Chiang L. H., Russell E. L, Braatz R. D. Fault detection and diagnosis in industrial systems. Springer-Verlag. London,2000
[5]杜运成,石红瑞,杨晓波.控制系统故障诊断方法综述.工业仪表与自动化装置.2008.5：9-13
[6]Garcia E. A, Frank P. M. On the relationship between observer and parameter ide-notification based approaches to fault detection. Proc. Of IFAC Word Congress.2001:25-29
[7]Ye H, Wang G z, Ding S X. A new parity space approach for fault detection based on stationary wavelet transform. IEEE Trans on Automatic Control.2004,49(2):281-287
[8]魏霞,徐敏强,鹿卫国.故障诊断技术及应用综述.热力透平.2004,3(300)：238-242
[9]牛星岩,沈颂华.基于小波变换的整流装置故障特征提取.电子测量技术.2007,30(10)：122-126
[10]黄大荣,胡必锦.基于专家知识库属性重要度的故障诊断方法研究.计算机仿真.2007,24(4)：155-157
[11]朱旭东,戴文战,郎燕峰.基于神经网络的方法在故障诊断中的应用.机电工程,2003,20(5)：75-78
[12]窦金生,汤天浩.基于知识的故障诊断技术及其在船舶上的应用.船舶工程.2007,29(4)：72-74
[13]赵熙临,刘辉.粗糙集理论在故障诊断中的问题分析.计算机技术与发展.2008,1：132-135
[14]肖小锋,蔡金燕,谌叶飞.基于故障树分析的监测点选取.计算机应用与软件.2007,24(9)：24-25
[15]张金泽,单甘霖.改进的SVM算法及其在故障诊断中的应用研究.电光与控制.2006,13(6)：97-100
[16]许晖,焦留芳,韩西宁.基于两级神经网络的传感器在线故障诊断技术研究.传感技术学报.2008,21(10)：1794-1797
[17]田玉玲.多层免疫故障诊断模型的研究.计算机工程与应用.2008,44(9)：245-248
[18]张力,李相平,陈信.FTA在末制导雷达故障诊断中的应用.海军航空工程学院学报.2004,19(1)：187-190
[19]金鑫,任献彬,周亮.智能故障诊断技术研究综述.理论与方法.2009,28(7)：30-32
[20]Pawlak Z. A rough set view on Bayes'theorem. IntemationaI Journal of Intelligent Systems.2003,18:487-498.
[21]简友光,简曙光.基于Rough集的数据约简算法研究综述.计算机与数字工程.2006(5)： 27-29
[22]申锦标,吕跃进.变精度与程度粗糙集的一种推广.计算机工程与应用.2008,44(36)：45-47
[23]Dutsh I. A logic for rough sets. Theoretical Computer Science.179(1997): 427-436
[24]Pawlak Z. Rough set theory and its applications to data analysis. Cyber-netics and Systems:An International Journal.1998,29(7):661-688
[25]黎平,宋坤等.基于粗糙集理论的关联聚类中长期负荷预测法.继电器.2008.36(1)：43-47
[26]吕士颖,郑晓鸣,王晓东.基于量子粒子群优化的属性约简.计算机工程.2008.18(34)：65-69
[27]丁卫平,邓伟,管致锦.基于粗糙集的属性约简优化算法研究.苏州大学学报.2008.24(2)：52-55
[28]沈晨鸣.基于粗糙集的数据挖掘属性约简算法研究.南京工程学院学报.2007.5(1)：31-34
[29]Ziarko W. Variable Precision Rough Set Model. Journal of Computer and System Sciences.1993,46:39-59
[30]Pawlak Z, Rough set theory and its applications to data analysis, Cyber-netics and system.1998,29(7):661-688
[31]Pawlak Z, Rough sets, rough relations and rough functions, Fundamenta informaticate.1996,27(2,3):103-108
[32]苏志同,李晋宏,林满山.基于差别矩阵的属性约简算法及其应用.计算机工程与应用.2010,46(7)：221-223
[33]蒋瑜,王燮.基于差别矩阵的Rough集属性约简算法.系统仿真学报.2008.20(14)：3717-3725
[34]申锦标，邓春燕,吕跃进.一种基于差别矩阵的新的属性约简方法.重庆工学院学报.2009.23(9)：84-87
[35]叶明全,伍长荣.决策表分解及其最小属性约简研究.计算机工程与应用.2009.45(30)：126-128
[36]覃志华,唐承超,王加阳.不相容决策表的核属性计算.计算机工程与应用.2005. 35：44-46
[37]黄少荣.粒子群优化算法综述.计算机工程与设计,2009,30(8)：1977-1980
[38]郑毅,吴斌.由鸟群和蚂蚁想到的—基于主体的仿真和群集智能的研究.微电脑世界.2001：7-13.
[39]Fan S. K, Liang Y. C, Zahara E. Hybrid simplex search and particle swarm optimization for the global optimization of multimodal functions. Enginee-ring Optimization.2004,36(4):401-418
[40]Mensah D. R, Liang W, et al. Evaluation of nC27 petroleum spray oil for activity against Helicoverpa spp. on commercial cotton fields in Australia. International Journal of Pest Management.2005,51(1):63-70
[41]Ye Z. B, Tang W. C, Li S. S. Analysis of millimetre wave microstrip circulator with a magnetised ferrite sphere by fdtD method with new extrapolation technique. International Journal of Electronics.2009,96(4):409-417
[42]Liu J. L, Lin J. H. Evolutionary computation of unconstrained and constrained problems using a novel momentum-type particle swarm optimization. Enginee-ring Optimization.2007,39(3):287-305
[43]Dong S.F, Dong Z. C, et al. Improved PSO algorithm based on chaos theory and its application to design flood hydrograph. Water Science and Enginee-ring.2010,3(2):156-165
[44]Zhu G. Y, Zhang W. B. Drilling path optimization by the particle swarm optimization algorithm with global convergence characteristics. Interna-tional Journal of Production Research.2007,46(8):2299-2311
[45]杨传将,刘清,黄珍.一种量子粒子群算法的改进方法.计算技术与自动化.2009,8(21)：100-103
[46]Kuang S, Cong S. Generalized control of quantum systems in the frame of vector treatment.2009,7(4):395-399
[47]王加阳,谢曩.基于量子粒子群优化的最小属性约简算法.计算机工程.2009,35(12)：148-153
[48]高鹰,谢胜利.免疫粒子群优化算法.计算机工程与应用.2004.6：4-6
[49]Chun J. S, Kim M. K, Jung H. K. Shape optimization of electromagnetic devices using immune algorithm. IEEE Trans on Magnetics.1997,33(2):1876-1879.
[50]蔡自兴,龚涛.免疫算法研究的进展.控制与决策.2004,19(8)：842-846
[51]张洪波.多种群粒子群分层进化优化算法.中国科技信息.2010,8：40-42
[52]李爱国.多粒子群协同优化算法.复旦学报.2004,43(5)：923-925
[53]陈国初,俞金寿.两群微粒群优化算法及其应用.2007,24(2)：294-298.
[54]许珂,刘栋.多粒子群协同进化算法.计算机工程与应用.2009,45(3)：51-54
[55]高翔,唐普英.设立禁区的多粒子群优化算法.计算机工程与应用.2010,46(10)：38-40
[56]杨传将,刘清,黄珍.一种量子粒子群算法的改进方法.计算技术与自动化.2009,28(1)：100-103
[57]袁晓蜂,许化龙,陈淑红.基于量子遗传算法的粗糙集属性约简新方法.计算机工程.2007,33(15)：184-186
[58]高家全,何桂霞,王雨顺.典型的人工免疫算法性能比较与分析.计算机工程与应用.2009,45(10)：208-210
[59]Sa J. P. M. D. Pattern Recognition. Concepts, Methods and Applications. Springer.2001
[60]边肇祺,张学工.模式识别(第二版).北京,清华大学出版社,2000
[61]Theodoridis S, Koutroumbas K. Pattern recognition, Elsevier,2003
[62]Baudat G, Anouar F. Feature vector selection and projection using kerls. Neuro computing.2003,55:21-38
[63]Webb A.R. Statistical pattern recognition. Wiley.2002
[64]唐静远,师奕兵.采用模糊支持向量机的模拟电路故障诊断新方法.电子测量与仪器学报.2009,6：7-12
[65]张勇,陈莉.聚类与PCA融合的特征提取方法研究.计算机工程与应用.2010.46(11)：148-150
[66]Sangdon L. Comparative analyses of anthropometry associated with verweight and obesity:PCA and ICA approaches. Theoretical Issues in Ergonomics Science.2008,9(5):441-475
[67]Dash M, Liu H. Consistency-based search in featuure selection. Artificial intelligence.2003,151:155-176
[68]Dettling M, Buhlmann P. Finding predictive gene groups from microarray data. Journal of multivariate analysis.2004,90:106-131
[69]吕成岭,彭力,张立位.一种基于快速特征选择的故障诊断方法.计算机工程与应用.2010,46(14)：235-237
[70]Sun Z. H, Bebis Z. H. Object Detection using feature subset selection. Pattern Recognition.2004,37:2165-2176
[71]Jain A, Duin R, et al. Statistical pattern recognition:a review. IEEE Transactions on Pattern Analysis and Machine Intelligence.2000,22(1): 4-37.
[72]YU Y, LU Z, et al. Scheduling problems on tardiness penalty and earliness award with simply linear processing time. Journal of Shanghai Univer-sity.2009,13(2):123-128
[73]叶玉玲,伞冶.一种混合决策系统属性约简算法研究.系统仿真学报,200,19(13)：2988-2991
[74]徐淑平林福宗.基于图像中心加权特征的图像检索.计算机应用与软件.2006,23(2)：3-5
[75]Burges C.J.C. A tutorial on support vector machines for pattern recog-nition. Data Mining and KnowledgeDiscovery.1998,.2:127-167
[76]WangA. N, Yuan W. J. A study of a multi-class classificational algorithm of SVM combined with ART, IEEE Third Intemantional Conference on Natual Compu-tation.2007
[77]Zhang R., Ma J. An improved SVM method P-SVM for classification of remotely sensed data. International Journal of Remote Sensing.2008,29(20): 6029-6036
[78]Kressel U, Pairwise. Classification and support vector machines in Advanees in Kerne Methods-Support Veetor Leaming. MIT Press Cambridge Massaehusetts, chapter 15,1999
[79]王海清,蒋宁.自适应Kernel学习网络在TE过程组分仪建模中的应用.化工学报.2007,58(2)：425-430
[80]Li W. H, Yue H H, et al. Recursive PCA for adaptive process monitoring. Jour-nal of Proeess Control.2000,19:471-486