基于PCA和SVM的汽车涂装线机电设备智能诊断
|
摘要
随着新的汽车涂装生产技术、生产工艺以及大型复杂设备的不断涌现和迅速发展,为了保证生产和设备高效、可靠的运行,因此对汽车涂装系统各机电设备运行状态的准确诊断提出了更高的要求。由于智能理论的发展,设备状态判别进入了智能化发展阶段。本文详细研究了主成分分析法和支持向量机在涂装线设备诊断中的应用,并结合虚拟仪器进行了涂装线设备监控与智能诊断系统的设计。论文主要内容如下:
1.根据汽车涂装线生产工艺,对各子系统主要设备的故障机理进行了分析研究,指出了设备经常发生的故障类型和征兆,在各系统内建立了数据采集系统。
2.研究了故障征兆提取技术。在实际环境下,众多传感器采集到的信号,一方面,并不是所有变量都反映设备状态的重要信息,有些会干扰诊断;另一方面,设备信号特征的输出有一定相关性。因此,论文讨论了主成分分析方法和改进的主成分分析法的应用。通过烘房燃烧加热系统设备的实例对比分析,验证了此方法的优势。
3.较深入研究了核函数类型及核参数对分类器精度的影响。通过双螺旋数据样本仿真试验,分别分析了高斯核和多项式核对分类精度的影响,以及高斯核宽度系数和惩罚参数对分类精度的影响,表明高斯核参数和惩罚参数在某个范围时,分类器精度最好。
4.提出了一种基于主成分分析和支持向量机的设备状态分类识别方法。结合主成分分析法的特征提取和向量机的识别优势,采用网格搜索交叉验证法寻求最优核参数,来建立向量机训练模型。通过烘房燃烧加热系统4种设备的12种状态进行了验证。分别分析了主成分分析法改进前后的分类精度,识别率都基本达到85%以上。
5.结合虚拟仪器进行了涂装线设备监控智能诊断系统的设计,对数据采集、时域和频域分析、特征提取和智能诊断等模块进行了介绍。
6.最后,对全文进行了总结,并对进一步的研究提出一些展望。
Due to the rapid development of automobile coating line both in newly painting technology and production processes, even in greater and more complicated equipments, it’s given a higher requirement to make an exact diagnosis for electrical and mechanical equipments on condition that the process in production and the efficient and reliable equipments operation in line is a sure thing. As the intelligent theory brought into and developed, the equipment status recognition will be getting into a stage of intelligence. This paper gave a detailed description about the application in equipment diagnosis of coating line with principal component analysis and support vector machine. In addition, the monitoring and intelligent diagnostic system in automobile coating line was designed under the circumstance of virtual instrument. Thesis’s contents are mainly as follows:
1. According to the production process in an automobile coating line, the failure about formation and occurrence of major equipments from various subsystems was analyzed and studied, pointing out the frequent failure types and signs of equipment within each subsystem. The data acquisition system was established based on that.
2. The methods of fault symptoms extraction were studied. Under the real system and working environment, various signals picked up by sensors, on the one hand, were not entirely reflect the significant information on device states, some variables can interfere with diagnosis. On the other hand, the outputs of equipment signals feature had some certain relevance. Therefore, the application of both principal component analysis and principal component analysis improvement model is mainly discussed in paper. Meanwhile, the advantages of this method were verified through analysis to equipments in oven heating system of coating line.
3. The influence the kernel function types and kernel parameters brought on classification accuracy was deeply studied. According to the simulation samples data from double helix, the effect Gaussian and polynomial kernel functions imposed on was analyzed respectively. So did the Gaussian kernel width and punishment parameters. The results showed that the best classification accuracy can be found when the Gaussian kernel function parameter and penalty parameter was at a range.
4. A method of equipment status recognition was proposed based on principal component analysis and support vector machine. Combined with feature extraction by principal component analysis and better recognition function by vector machine, the vector machine training model was created with the best kernel parameters optimizing by using a grid search and cross-validation method. That was verified through the 12 different states from four kinds of equipments in heating system. The classification accuracy was analyzed on basis of before and after the principal component analysis improvement, and the rate up to 85% basically or more.
5. The monitoring and intelligently diagnostic system in equipments of automobile coating line was designed accompanied with virtual instruments. At the same time, the modules were introduced including data acquisition, time and frequency domain analysis, feature extraction and intelligent diagnosis.
6. Finally, a summary of the paper was given and some prospects for further research was provided.
1.根据汽车涂装线生产工艺,对各子系统主要设备的故障机理进行了分析研究,指出了设备经常发生的故障类型和征兆,在各系统内建立了数据采集系统。
2.研究了故障征兆提取技术。在实际环境下,众多传感器采集到的信号,一方面,并不是所有变量都反映设备状态的重要信息,有些会干扰诊断;另一方面,设备信号特征的输出有一定相关性。因此,论文讨论了主成分分析方法和改进的主成分分析法的应用。通过烘房燃烧加热系统设备的实例对比分析,验证了此方法的优势。
3.较深入研究了核函数类型及核参数对分类器精度的影响。通过双螺旋数据样本仿真试验,分别分析了高斯核和多项式核对分类精度的影响,以及高斯核宽度系数和惩罚参数对分类精度的影响,表明高斯核参数和惩罚参数在某个范围时,分类器精度最好。
4.提出了一种基于主成分分析和支持向量机的设备状态分类识别方法。结合主成分分析法的特征提取和向量机的识别优势,采用网格搜索交叉验证法寻求最优核参数,来建立向量机训练模型。通过烘房燃烧加热系统4种设备的12种状态进行了验证。分别分析了主成分分析法改进前后的分类精度,识别率都基本达到85%以上。
5.结合虚拟仪器进行了涂装线设备监控智能诊断系统的设计,对数据采集、时域和频域分析、特征提取和智能诊断等模块进行了介绍。
6.最后,对全文进行了总结,并对进一步的研究提出一些展望。
Due to the rapid development of automobile coating line both in newly painting technology and production processes, even in greater and more complicated equipments, it’s given a higher requirement to make an exact diagnosis for electrical and mechanical equipments on condition that the process in production and the efficient and reliable equipments operation in line is a sure thing. As the intelligent theory brought into and developed, the equipment status recognition will be getting into a stage of intelligence. This paper gave a detailed description about the application in equipment diagnosis of coating line with principal component analysis and support vector machine. In addition, the monitoring and intelligent diagnostic system in automobile coating line was designed under the circumstance of virtual instrument. Thesis’s contents are mainly as follows:
1. According to the production process in an automobile coating line, the failure about formation and occurrence of major equipments from various subsystems was analyzed and studied, pointing out the frequent failure types and signs of equipment within each subsystem. The data acquisition system was established based on that.
2. The methods of fault symptoms extraction were studied. Under the real system and working environment, various signals picked up by sensors, on the one hand, were not entirely reflect the significant information on device states, some variables can interfere with diagnosis. On the other hand, the outputs of equipment signals feature had some certain relevance. Therefore, the application of both principal component analysis and principal component analysis improvement model is mainly discussed in paper. Meanwhile, the advantages of this method were verified through analysis to equipments in oven heating system of coating line.
3. The influence the kernel function types and kernel parameters brought on classification accuracy was deeply studied. According to the simulation samples data from double helix, the effect Gaussian and polynomial kernel functions imposed on was analyzed respectively. So did the Gaussian kernel width and punishment parameters. The results showed that the best classification accuracy can be found when the Gaussian kernel function parameter and penalty parameter was at a range.
4. A method of equipment status recognition was proposed based on principal component analysis and support vector machine. Combined with feature extraction by principal component analysis and better recognition function by vector machine, the vector machine training model was created with the best kernel parameters optimizing by using a grid search and cross-validation method. That was verified through the 12 different states from four kinds of equipments in heating system. The classification accuracy was analyzed on basis of before and after the principal component analysis improvement, and the rate up to 85% basically or more.
5. The monitoring and intelligently diagnostic system in equipments of automobile coating line was designed accompanied with virtual instruments. At the same time, the modules were introduced including data acquisition, time and frequency domain analysis, feature extraction and intelligent diagnosis.
6. Finally, a summary of the paper was given and some prospects for further research was provided.
引文
[1]陈淼峰.基于EMD与支持向量机的转子故障诊断方法研究[D] .长沙:湖南大学, 2005.
[2]田义潮.旋转机械故障诊断专家系统研究与实现[D] .大连:大连理工大学, 2009.
[3]屈良生,何正嘉.机械故障诊断学[M].上海:上海科技出版社, 1986.
[4]盛兆顺,尹琦岭.设备状态监测与故障诊断技术及应用[M].北京:化学工业出版社,2003.
[5] Sohre. J.S. Trouble-shooting to stop vibration of centrifugal [J]. Petro/Chem Engineer, 1968: 22-23.
[6]程琴.基于LabVIEW的风机性能远程测试系统的研究[D] .西安:西北农林科技大学, 2008.
[7]闻邦春,顾家柳,夏松波.高等转子动力学[M].北京:机械工业出版社,2000.
[8]陈安华,钟掘.转子系统非线性振动的辨识建模[J].中国有色金属学报, 1997, 7(3): 159-163.
[9]高金吉.高速涡轮机械振动故障机理及诊断方法研究[D] .北京:清华大学, 1993.
[10]朱颖辉,李友荣,刘安中等. SVM在齿轮小样本故障诊断中的应用[J].煤矿机械, 2006, 27(11): 186-188.
[11]夏松波,张嘉钟,徐世昌等.旋转机械故障诊断技术的现状与展望[J].振动与冲击, 1997, 16(2): 1-5.
[12]屈梁生,史冬锋.全息谱十年:回顾与展望[J].振动、测试与诊断, 1998, 18(4): 235-242.
[13]胡劲松,吴晗同,严拱标.提高旋转机械振动信号整周期采样精度的一种方法[J].浙江大学学报, 2002, 36(3): 273-275.
[14] Sweldens W. The Lifting Scheme: a Construction of Second Generation Wavelets [J].Math Anal, 1996.
[15] Efron. B, Tibshirani. R. Bootstrap Techniques for Signal Processing [M]. Cambridge University Press, 2004.
[16]何学文,赵海鸣.支持向量机及其在机械故障诊断中的应用[J].中南大学学报, 2005, 36(1): 98-101.
[17]吉尚伟,金志浩,金文等.基于小波-支持向量机的旋转机械碰摩故障诊断[J].工业安全与环保, 2010, 36(3): 1-3.
[18]赵玉龙,曾广锡.最大熵谱分析法在注水泵故障诊断中的应用[J].西安石油学院学报, 2001, 16(3): 64-66.
[19]刘强.基于Hilbert-Huang变换的机电设备故障诊断综述[J].煤炭技术, 2007, 16(5): 21-24.
[20]胡桥,何正嘉,张周锁等.经验模式分解模糊特征提取的支持向量机[J].西安交通大学学报, 2005, 39(3): 291-294.
[21]田立柱,张来斌,王朝晖.相图及方差在注水泵故障诊断中的应用[J].石油大学学报(自然科学版), 2003, 27(4): 88-90.
[22]金鑫,任献彬,周亮.智能故障诊断技术研究综述[J].理论与方法, 2009, 28(7): 30-32.
[23]李小军.基于RS-SVM的汽轮发电机组振动故障智能诊断技术研究[D].南京:东南大学, 2009.
[24]高隽.人工神经网络原理及仿真实例[M].北京:机械工业出版社, 2002.
[25] Sorsa T., Koivo H.N., Koivisto H. Neural networks in process fault diagnosis [J]. IEEE Transactions on systems, Man, and Cybernetics, 1991, 21(4): 815-824.
[26] Bernieri A., Apuzzo M.D., Sansone L., et al. A neural network approach for identification and fault diagnosis on dynamic systems [J]. IEEE Transactions on Instrumentation and Measurement, 1994,43(6): 867-873.
[27] Jackson J E. A user’s guide to principal components [M]. New York: John Wiley, 1991.
[28] Mevlut Ture, Imran Kurt, Zekeriya Akturk. Comparison of dimension reduction methods using patient satisfaction data [J]. Expert Systems with Applications, 2007, 32(1), 422-426.
[29]何晓群.多元统计分析[M].北京:中国人民大学出版社,2008.
[30] Pearson K. On lines and planes of closer fit to systems of points in space [J]. Philos. Mag, 1901, 2: 559-572.
[31] Hotelling H. Analysis of a complex of statistical variables into principal components [J]. J. Edu. Psych, 1933, 24: 417-441.
[32]段祎林,田亚爱.一种提高Kernel PCA特征提取性能的核优化算法[J].西安石油大学学报(自然科学版), 2009, 24(5): 82-85.
[33]卢正鼎,赵萍.一种基于支持向量机的PCA分析方法[J].华中科技大学学报(自然科学版), 2005, 33(1): 25-27.
[34]孙延春,马齐爽.改进PCA在热波图像处理中的应用[J].北京航空航天大学学报, 2008, 34(9): 1012-1015.
[35]谢永林. PCA算法及其在人脸识别中的应用[J].计算机与现代化, 2009, 34(6): 88-90.
[36]毛先柏,李昌禧. PCA-SVM在模拟电路故障诊断中的应用[J].计算机测量与控制, 2009, 17(7): 1250-1252.
[37]杨海荣,薄翠梅,龚伟俊等.基于PCA-SVM集成阀门故障诊断方法研究[J].流体机械, 2009, 37(7): 28-32.
[38]李冬辉,王乐英,李晟.基于PCA的空调系统传感器故障诊断[J].电工技术学报, 2008, 23(6): 130-136.
[39]乔巍巍,贾亚洲.基于PCA的数控系统故障原因分析[J].机床与液压, 2009, 37(9): 269-271.
[40]冯俊婷,王桂增.基于主元分析的核电站主冷却剂泵故障诊断[J].原子能科学技术, 2003, 37(5): 395-398.
[41]王磊.基于主成分分析的支持向量机回归预测模型[J].信息技术, 2008, 3(12): 58-60.
[42]赵小强,王新明,王迎.基于PCA与KPCA的TE过程故障检测应用研究[J].自动化仪表, 2011, 32(1): 8-11.
[43]孙卫祥,陈进,吴立伟等.基于PCA与决策树的转子故障诊断[J].振动与冲击, 2007, 26(3): 72-74.
[44] Duda R., Hart P., Pattern classification and scene analysis [M]. Hoboken, NJ, John Wiley&Sons, 1973.
[45] Cristianini N., Shawe-Taylor J. An Introduction to Support Vector Machines [M]. Cambridge University Press, 2000.
[46] Vladimir N. Vapnik著,张学工译.统计学习理论的本质[M].北京:清华大学出版社, 2000.
[47] Cristianini. N.等著,李国正,王猛,曾华军译.支持向量机导论[M].北京:电子工业出版社, 2004.
[48]刘忠艳,周波,李丹.支持向量机的分类策略在图像识别中的应用[J].信息技术, 2008, 32(7): 32-34.
[49]韩永章.基于支持向量机的旋转机械故障诊断研究[J].科技信息, 2002, 12(2): 372-373.
[50]刘亚娟,张晓芹.基于支持向量机的旋转机械故障诊断[J].计算机工程与设计, 2005, 26(12): 3436-3438.
[51]赵冲冲,廖明夫,于潇.基于支持向量机的旋转机械故障诊断[J].振动、测试与诊断, 2006, 26(1): 53-57.
[52]陈志刚,连香姣,于会媛等.多元支持向量机在压缩机故障诊断中的应用[J].石油机械, 2009, 37 (11): 63-65.
[53]杨琦,孙玉清.基于SVM的液压设备仿真模型的故障诊断[J].机电设备, 2007, 14 (5): 15-17.
[54]罗邦劼.旋转机械故障诊断技术的研究现状及发展趋势[J].机电产品开发与创新, 2008, 21(3): 85-87.
[55]徐小力,王为真,徐洪安.大型旋转机械非平稳时间序列预测模型的研究[J].北京机械工业学院学报, 2001, 16(3): 1-4.
[56] Ting Liu, Andrew W. Moore, Alexander Gray. New Algorithms for Efficient High-Dimensional Nonparametric Classification [J]. Machine Learning Research, 2006, 16(7): 1135-1158.
[57] Koby Crammer, Ofer Dekel, Joseph Keshet. Online Passive-Aggressive Algorithms [J]. Machine Learning Research, 2006, 16(7): 551-585.
[58]高晓清,姚竹亭.小波-神经网络在旋转机械故障诊断中的应用[J].四川兵工学报, 2007, 12(5): 40-43.
[59]洪光日.涂装前处理工艺及装备[J].汽车工艺与材料, 2001, 12(2): 8-11.
[60]王海军.汽车涂装线常用磷化除渣系统简述[J].现代涂料与涂装, 2007, 10(7): 31-33.
[61]范琴.板式换热器常见故障及处理[J].石油化工设备, 2006, 35(5): 104-105.
[62]王锡春.涂装工艺技术[M].北京:化学工业出版社, 2004.
[63]李志生,张国强,刘建龙等.基于冷水量变化的冷水机组性能测试与故障诊断[J].暖通空调, 2006, 36(8): 108-112.
[64]张玉军.车身涂装线烘干及废气焚烧新技术的应用[J].材料保护, 2003, 36(9): 44-45.
[65]兰丽丽.基于PCA的空气源热泵空调系统故障诊断[D] .长沙:湖南大学, 2008.
[66]韦洁.基于主元分析的电机状态监测方法的研究[D] .北京:北京交通大学, 2009.
[67] Zhang Xi, Yan Weiwu, Zhao Xu. Nonlinear online process monitoring and fault diagnosis of condenser based on kernel PCA plus FDA [J]. Journal of Southeast University (English Edition), 2007, 23(1): 51– 56.
[68] Masayuki Tamura, Shinsuke Tsujita. A study on the number of principal components and sensitivity of fault detection using PCA [J]. Computers and Chemical Engineering, 2007(31): 1035-1046.
[69]王海清,宋执环,李平.主元分析法的故障可检测性研究[J].仪器仪表学报, 2002, 23(3): 232-240.
[70]范宇,马孝江.基于主分量分析的柴油机振动信号特征提取[J].中国机械工程, 2007, 18(8): 971-974.
[71]滕建.基于ICA的工业过程监控技术研究[D].北京:北京化工大学, 2008.
[72]彭璐.基于向量机分类算法研究与应用[D] .长沙:湖南大学, 2007.
[73]袁胜发,褚福磊. SVM多类分类算法及其在故障诊断中的应用[J].振动工程学报, 2004, 17,增刊: 420-421.
[74]徐仁林.基于虚拟仪器的压缩机故障诊断系统研究[D] .无锡:江南大学, 2008.
[75]刘君华.基于LabVIEW的虚拟仪器的设计[M].北京:电子工业出版社, 2002.
[76]鲍丙豪,周燕,许桢英.传感器手册[M].北京:化学工业出版社, 2008.
[2]田义潮.旋转机械故障诊断专家系统研究与实现[D] .大连:大连理工大学, 2009.
[3]屈良生,何正嘉.机械故障诊断学[M].上海:上海科技出版社, 1986.
[4]盛兆顺,尹琦岭.设备状态监测与故障诊断技术及应用[M].北京:化学工业出版社,2003.
[5] Sohre. J.S. Trouble-shooting to stop vibration of centrifugal [J]. Petro/Chem Engineer, 1968: 22-23.
[6]程琴.基于LabVIEW的风机性能远程测试系统的研究[D] .西安:西北农林科技大学, 2008.
[7]闻邦春,顾家柳,夏松波.高等转子动力学[M].北京:机械工业出版社,2000.
[8]陈安华,钟掘.转子系统非线性振动的辨识建模[J].中国有色金属学报, 1997, 7(3): 159-163.
[9]高金吉.高速涡轮机械振动故障机理及诊断方法研究[D] .北京:清华大学, 1993.
[10]朱颖辉,李友荣,刘安中等. SVM在齿轮小样本故障诊断中的应用[J].煤矿机械, 2006, 27(11): 186-188.
[11]夏松波,张嘉钟,徐世昌等.旋转机械故障诊断技术的现状与展望[J].振动与冲击, 1997, 16(2): 1-5.
[12]屈梁生,史冬锋.全息谱十年:回顾与展望[J].振动、测试与诊断, 1998, 18(4): 235-242.
[13]胡劲松,吴晗同,严拱标.提高旋转机械振动信号整周期采样精度的一种方法[J].浙江大学学报, 2002, 36(3): 273-275.
[14] Sweldens W. The Lifting Scheme: a Construction of Second Generation Wavelets [J].Math Anal, 1996.
[15] Efron. B, Tibshirani. R. Bootstrap Techniques for Signal Processing [M]. Cambridge University Press, 2004.
[16]何学文,赵海鸣.支持向量机及其在机械故障诊断中的应用[J].中南大学学报, 2005, 36(1): 98-101.
[17]吉尚伟,金志浩,金文等.基于小波-支持向量机的旋转机械碰摩故障诊断[J].工业安全与环保, 2010, 36(3): 1-3.
[18]赵玉龙,曾广锡.最大熵谱分析法在注水泵故障诊断中的应用[J].西安石油学院学报, 2001, 16(3): 64-66.
[19]刘强.基于Hilbert-Huang变换的机电设备故障诊断综述[J].煤炭技术, 2007, 16(5): 21-24.
[20]胡桥,何正嘉,张周锁等.经验模式分解模糊特征提取的支持向量机[J].西安交通大学学报, 2005, 39(3): 291-294.
[21]田立柱,张来斌,王朝晖.相图及方差在注水泵故障诊断中的应用[J].石油大学学报(自然科学版), 2003, 27(4): 88-90.
[22]金鑫,任献彬,周亮.智能故障诊断技术研究综述[J].理论与方法, 2009, 28(7): 30-32.
[23]李小军.基于RS-SVM的汽轮发电机组振动故障智能诊断技术研究[D].南京:东南大学, 2009.
[24]高隽.人工神经网络原理及仿真实例[M].北京:机械工业出版社, 2002.
[25] Sorsa T., Koivo H.N., Koivisto H. Neural networks in process fault diagnosis [J]. IEEE Transactions on systems, Man, and Cybernetics, 1991, 21(4): 815-824.
[26] Bernieri A., Apuzzo M.D., Sansone L., et al. A neural network approach for identification and fault diagnosis on dynamic systems [J]. IEEE Transactions on Instrumentation and Measurement, 1994,43(6): 867-873.
[27] Jackson J E. A user’s guide to principal components [M]. New York: John Wiley, 1991.
[28] Mevlut Ture, Imran Kurt, Zekeriya Akturk. Comparison of dimension reduction methods using patient satisfaction data [J]. Expert Systems with Applications, 2007, 32(1), 422-426.
[29]何晓群.多元统计分析[M].北京:中国人民大学出版社,2008.
[30] Pearson K. On lines and planes of closer fit to systems of points in space [J]. Philos. Mag, 1901, 2: 559-572.
[31] Hotelling H. Analysis of a complex of statistical variables into principal components [J]. J. Edu. Psych, 1933, 24: 417-441.
[32]段祎林,田亚爱.一种提高Kernel PCA特征提取性能的核优化算法[J].西安石油大学学报(自然科学版), 2009, 24(5): 82-85.
[33]卢正鼎,赵萍.一种基于支持向量机的PCA分析方法[J].华中科技大学学报(自然科学版), 2005, 33(1): 25-27.
[34]孙延春,马齐爽.改进PCA在热波图像处理中的应用[J].北京航空航天大学学报, 2008, 34(9): 1012-1015.
[35]谢永林. PCA算法及其在人脸识别中的应用[J].计算机与现代化, 2009, 34(6): 88-90.
[36]毛先柏,李昌禧. PCA-SVM在模拟电路故障诊断中的应用[J].计算机测量与控制, 2009, 17(7): 1250-1252.
[37]杨海荣,薄翠梅,龚伟俊等.基于PCA-SVM集成阀门故障诊断方法研究[J].流体机械, 2009, 37(7): 28-32.
[38]李冬辉,王乐英,李晟.基于PCA的空调系统传感器故障诊断[J].电工技术学报, 2008, 23(6): 130-136.
[39]乔巍巍,贾亚洲.基于PCA的数控系统故障原因分析[J].机床与液压, 2009, 37(9): 269-271.
[40]冯俊婷,王桂增.基于主元分析的核电站主冷却剂泵故障诊断[J].原子能科学技术, 2003, 37(5): 395-398.
[41]王磊.基于主成分分析的支持向量机回归预测模型[J].信息技术, 2008, 3(12): 58-60.
[42]赵小强,王新明,王迎.基于PCA与KPCA的TE过程故障检测应用研究[J].自动化仪表, 2011, 32(1): 8-11.
[43]孙卫祥,陈进,吴立伟等.基于PCA与决策树的转子故障诊断[J].振动与冲击, 2007, 26(3): 72-74.
[44] Duda R., Hart P., Pattern classification and scene analysis [M]. Hoboken, NJ, John Wiley&Sons, 1973.
[45] Cristianini N., Shawe-Taylor J. An Introduction to Support Vector Machines [M]. Cambridge University Press, 2000.
[46] Vladimir N. Vapnik著,张学工译.统计学习理论的本质[M].北京:清华大学出版社, 2000.
[47] Cristianini. N.等著,李国正,王猛,曾华军译.支持向量机导论[M].北京:电子工业出版社, 2004.
[48]刘忠艳,周波,李丹.支持向量机的分类策略在图像识别中的应用[J].信息技术, 2008, 32(7): 32-34.
[49]韩永章.基于支持向量机的旋转机械故障诊断研究[J].科技信息, 2002, 12(2): 372-373.
[50]刘亚娟,张晓芹.基于支持向量机的旋转机械故障诊断[J].计算机工程与设计, 2005, 26(12): 3436-3438.
[51]赵冲冲,廖明夫,于潇.基于支持向量机的旋转机械故障诊断[J].振动、测试与诊断, 2006, 26(1): 53-57.
[52]陈志刚,连香姣,于会媛等.多元支持向量机在压缩机故障诊断中的应用[J].石油机械, 2009, 37 (11): 63-65.
[53]杨琦,孙玉清.基于SVM的液压设备仿真模型的故障诊断[J].机电设备, 2007, 14 (5): 15-17.
[54]罗邦劼.旋转机械故障诊断技术的研究现状及发展趋势[J].机电产品开发与创新, 2008, 21(3): 85-87.
[55]徐小力,王为真,徐洪安.大型旋转机械非平稳时间序列预测模型的研究[J].北京机械工业学院学报, 2001, 16(3): 1-4.
[56] Ting Liu, Andrew W. Moore, Alexander Gray. New Algorithms for Efficient High-Dimensional Nonparametric Classification [J]. Machine Learning Research, 2006, 16(7): 1135-1158.
[57] Koby Crammer, Ofer Dekel, Joseph Keshet. Online Passive-Aggressive Algorithms [J]. Machine Learning Research, 2006, 16(7): 551-585.
[58]高晓清,姚竹亭.小波-神经网络在旋转机械故障诊断中的应用[J].四川兵工学报, 2007, 12(5): 40-43.
[59]洪光日.涂装前处理工艺及装备[J].汽车工艺与材料, 2001, 12(2): 8-11.
[60]王海军.汽车涂装线常用磷化除渣系统简述[J].现代涂料与涂装, 2007, 10(7): 31-33.
[61]范琴.板式换热器常见故障及处理[J].石油化工设备, 2006, 35(5): 104-105.
[62]王锡春.涂装工艺技术[M].北京:化学工业出版社, 2004.
[63]李志生,张国强,刘建龙等.基于冷水量变化的冷水机组性能测试与故障诊断[J].暖通空调, 2006, 36(8): 108-112.
[64]张玉军.车身涂装线烘干及废气焚烧新技术的应用[J].材料保护, 2003, 36(9): 44-45.
[65]兰丽丽.基于PCA的空气源热泵空调系统故障诊断[D] .长沙:湖南大学, 2008.
[66]韦洁.基于主元分析的电机状态监测方法的研究[D] .北京:北京交通大学, 2009.
[67] Zhang Xi, Yan Weiwu, Zhao Xu. Nonlinear online process monitoring and fault diagnosis of condenser based on kernel PCA plus FDA [J]. Journal of Southeast University (English Edition), 2007, 23(1): 51– 56.
[68] Masayuki Tamura, Shinsuke Tsujita. A study on the number of principal components and sensitivity of fault detection using PCA [J]. Computers and Chemical Engineering, 2007(31): 1035-1046.
[69]王海清,宋执环,李平.主元分析法的故障可检测性研究[J].仪器仪表学报, 2002, 23(3): 232-240.
[70]范宇,马孝江.基于主分量分析的柴油机振动信号特征提取[J].中国机械工程, 2007, 18(8): 971-974.
[71]滕建.基于ICA的工业过程监控技术研究[D].北京:北京化工大学, 2008.
[72]彭璐.基于向量机分类算法研究与应用[D] .长沙:湖南大学, 2007.
[73]袁胜发,褚福磊. SVM多类分类算法及其在故障诊断中的应用[J].振动工程学报, 2004, 17,增刊: 420-421.
[74]徐仁林.基于虚拟仪器的压缩机故障诊断系统研究[D] .无锡:江南大学, 2008.
[75]刘君华.基于LabVIEW的虚拟仪器的设计[M].北京:电子工业出版社, 2002.
[76]鲍丙豪,周燕,许桢英.传感器手册[M].北京:化学工业出版社, 2008.