基于神经网络的液压动力系统多源诊断信息融合方法研究
|
摘要
结合液压系统故障诊断的特点和发展趋势,本文以信息融合的基本理论为指导思想,对液压动力系统多源诊断信息的获取、分析及融合方面的问题进行了研究,提出了适用于液压动力系统的多源诊断信息融合方法,其主要研究工作归纳如下:
(1)综述现代液压系统故障诊断技术的现状及趋势,强调引入多源诊断信息融合技术的重要性,介绍适用于故障监测、报警和诊断的多源诊断信息融合结构及多源诊断信息融合算法。
(2)对液压动力系统多源诊断信息获取与实验系统进行详细的介绍,最后通过实例应用来验证该实验系统所获取多源诊断信息的适用性。
(3)根据多源信息监测技术的应用特点及液压系统的工作参数,给出液压系统运行状态的多源信息监测系统模型;对应用于液压系统的多源监测信息进行分析,主要分析电流信号和油压信号;分析基于电阻应变计压力信号监测时桥路的选择、管路形状对压力信号的影响及监测信号的选取。
(4)介绍对向传播神经网络(CPN)的基本理论和特点,结合频谱分析法对液压动力系统的典型故障进行分类;通过与BP网络分类能力相比较分析其在故障分类方面的优势。
(5)针对单源信号提供信息量的不足,以及故障间的相互影响而造成的误判等问题,提出基于模糊CPN神经网络的多源诊断信息融合方法;给出适用于液压系统的多源诊断信息融合模型,并建立模糊隶属度函数。最后通过实例应用来验证该方法的有效性,说明开展神经网络与其它融合方法相结合的研究是十分必要的。
In the light of the characteristic and development of the hydraulic system fault diagnosis,this paper,based on the information fusion theory,presents an intensive to the acquisition,analysis and fusion of information from multi-sensor applied to the fusion technique of hydraulic power system's multi-source fault information.The research covers the following essential contents and conclusions:
(1)The paper first summarized the actuality & development of modern hydraulic system fault diagnosis technology,stressed the importance of multi-source information fusion,introduced the fusion configuration and algorithm of multi-sources fault information,which is applicable for fault monitoring,alarm and diagnosis.
(2)Detailed introduced the multi-source fault information collection and analysis of experimental system of hydraulic power system.Finally,through the examples used to verify that the system is practical.
(3)According to the application features of multi-source information monitoring technique and the operation parameters of hydraulic system,and then bring forward the multi-source information monitoring system model operation status of hydraulic system; The multi-source information of hydraulic system was analyzed such as current signal and pressure signal;In addition,it analyzed choices of bridge type while monitoring pressure signal with resistor strain gauge,effects of pipeline shape to pressure signal and selections of monitoring signals.
(4)On basic theory and characteristics of Counter-propagation Networks,and fusion the method of spectrum analysis used for typical fault classifications to hydraulic power system;Compared with BP neural network,CPN showed its advantage.
(5)The fusion technique of multi-source fault information,based on the fuzzy CPN neural network,solved the problems such as inadequate information offered by single-source and misjudgment induced by effects among faults;The multi-source fault information fusion model applied to hydraulic system has been given and fuzzy membership function has been built.Effectiveness has been authenticated by application examples at last,at the same time,it showed that it is necessary to combine neural network with other fusion methods.
(1)综述现代液压系统故障诊断技术的现状及趋势,强调引入多源诊断信息融合技术的重要性,介绍适用于故障监测、报警和诊断的多源诊断信息融合结构及多源诊断信息融合算法。
(2)对液压动力系统多源诊断信息获取与实验系统进行详细的介绍,最后通过实例应用来验证该实验系统所获取多源诊断信息的适用性。
(3)根据多源信息监测技术的应用特点及液压系统的工作参数,给出液压系统运行状态的多源信息监测系统模型;对应用于液压系统的多源监测信息进行分析,主要分析电流信号和油压信号;分析基于电阻应变计压力信号监测时桥路的选择、管路形状对压力信号的影响及监测信号的选取。
(4)介绍对向传播神经网络(CPN)的基本理论和特点,结合频谱分析法对液压动力系统的典型故障进行分类;通过与BP网络分类能力相比较分析其在故障分类方面的优势。
(5)针对单源信号提供信息量的不足,以及故障间的相互影响而造成的误判等问题,提出基于模糊CPN神经网络的多源诊断信息融合方法;给出适用于液压系统的多源诊断信息融合模型,并建立模糊隶属度函数。最后通过实例应用来验证该方法的有效性,说明开展神经网络与其它融合方法相结合的研究是十分必要的。
In the light of the characteristic and development of the hydraulic system fault diagnosis,this paper,based on the information fusion theory,presents an intensive to the acquisition,analysis and fusion of information from multi-sensor applied to the fusion technique of hydraulic power system's multi-source fault information.The research covers the following essential contents and conclusions:
(1)The paper first summarized the actuality & development of modern hydraulic system fault diagnosis technology,stressed the importance of multi-source information fusion,introduced the fusion configuration and algorithm of multi-sources fault information,which is applicable for fault monitoring,alarm and diagnosis.
(2)Detailed introduced the multi-source fault information collection and analysis of experimental system of hydraulic power system.Finally,through the examples used to verify that the system is practical.
(3)According to the application features of multi-source information monitoring technique and the operation parameters of hydraulic system,and then bring forward the multi-source information monitoring system model operation status of hydraulic system; The multi-source information of hydraulic system was analyzed such as current signal and pressure signal;In addition,it analyzed choices of bridge type while monitoring pressure signal with resistor strain gauge,effects of pipeline shape to pressure signal and selections of monitoring signals.
(4)On basic theory and characteristics of Counter-propagation Networks,and fusion the method of spectrum analysis used for typical fault classifications to hydraulic power system;Compared with BP neural network,CPN showed its advantage.
(5)The fusion technique of multi-source fault information,based on the fuzzy CPN neural network,solved the problems such as inadequate information offered by single-source and misjudgment induced by effects among faults;The multi-source fault information fusion model applied to hydraulic system has been given and fuzzy membership function has been built.Effectiveness has been authenticated by application examples at last,at the same time,it showed that it is necessary to combine neural network with other fusion methods.
引文
[1]周汝胜,焦宗夏,王少萍.液压系统故障诊断技术的研究现状与发展趋势[J].机械工程学报,2006(9):6-14.
[2]周东华,叶银忠.现代故障诊断与容错控制[M].清华大学出版社,2000.
[3]谷立臣.工程机械诊断信息融合理论与方法研究[D].西安交通大学博士学位论文,2002.
[4]郭丽艳.基于BP网络特征级信息融合及在目标识别中的应用研究[D].武汉大学硕士学位论文,2004.
[5]刘延俊,谢玉东.液压系统故障诊断技术的现状及发展趋势[J].液压与气动,2006(2):80-82.
[6]何敏等.故障诊断技术方法综述[J].国外电子测量技术,2006(5):4-6.
[7]刘泽华.基于小波理论的液压系统诊断特征提取与故障分类方法研究[D].西安建筑科技大学硕士学位论文,2007.
[8]李令莱,周东华.基于解析模型的非线性系统鲁棒故障诊断方法综述[J].信息与控制,2004(4):451-456.
[9]姜万录,张淑清,王益群.液压泵故障的小波变换诊断方法[J].机械工程学报,2001(6):34-37.
[10]潘兵,熊静琪.多传感器信息融合在液压系统智能故障诊断中的应用[J].机床与液压,2006(5):190-192.
[11]Prawito Prajitno and Neil Mort.A Fuzzy Model-based Multi-sensor Date Fusion System[J].Proceedings of SPIE,2001(1):301-312.
[12]REN C.LUO,MICHAEL GKAY.Multisensor integration and fusion in intelligent systems[J].IEEE Trans.on Systems,Man and Cybernetics,1989(5):901-931.
[13]Bassel.Information Fusion Concepts:From information elements definition to the application of fusion approaches[J].Proceedings of SPIE,2001(1):205-212.
[14]C.Ray Smith.Multisensor data fusion:concepts and principles[J].IEEE Pacific Rim Conference on Communications,Computers and Signal Processing,May 9-10,1991:235-237.
[15]刘同明,夏祖勋等.数据融合技术及其应用[M].国防工业出版社,1998.
[16]Eddy K.Tsui,Russell Thomas.Real-time multi-sensor data fusion for target detection,classification,tracking,counting,and range estimates[J].Proceedings of SPIE,2004(4):811-821.
[17]W.Chang,H.S.Soliman & A.H.Sung.Image Data Compression Using Counterpropagation Network[J].Proceedings of IEEE,1992(8)405-409.
[18]Hamid Rasoulian,Louis F.Kazda.A multisensor data fusion model for multitarget tracking[J].Proceedings of SPIE,1990(2):24-34.
[19]REN C.LUO,MIN-HSIUNG LIN,RALPH S.SCHERP.Dynamic Multi-Sensor Data Fusion System for Intelligent Robots[J].IEEE Journal Of Robotics and Automation,1988(4):386-396.
[20]潘泉,于昕,程咏梅,张洪才.信息融合理论的基本方法与进展[J].自动化学报,2003(4):599-615.
[21]王志鹏.基于信息融合技术的故障诊断方法的研究与应用[D].大连理工大学博士学位论文,2001.
[22]袁小宏,屈梁生.机械故障诊断中的信息融合利用问题研究[J].振动、测试与诊断,1999(3):187-192.
[23]张彦铎,姜兴渭.多传感器信息融合及在智能故障诊断中的应用[J].传感器技术,1999(2):1R-22.
[24]Chih-Chen Yih,and Kuo Lan Su.Multisensor Fusion and Integration:Approaches,Applications,and Future Research Directions[J].IEEE Sensors Journal,2002(2):107-119(in Chinese).
[25]周芳,韩立岩.多传感器信息融合技术综述[J].遥测遥控,2006(3):1-7.
[26]Bassel Solaiman,Leland E.Pierce,and Fawwaz T.Ulaby.Multisensor Data Fusion Using Fuzzy Concepts:Application to Land-Cover Classification Using ERS-1/JERS-1 SAR Composites[J].IEEE Transactions On Geoscience And Remote Sensing,1999(3):1316-1326.
[27]Zhaoli Zhang,Qi Wang,Shenghe Sun.A New Fuzzy Neural Network Architecture for Multisensor Data fusion in Non-destructive Testing[J].1999 IEEE International Fuzzy Systems Conference Proceedings,1999(99):Ⅲ-1661-Ⅲ-1665(in Chinese).
[28]白士红,李晓雷,庞思勤.模糊-灰色关联-神经网络故障诊断方法研究[J].机械设计与制造,2003(6):10-11.
[29]Diqi Zhu,Shenglin Yu.Neural Networks Data Fusion Algorithm of Electronic Equipment Fault Diagnosis.Proceedings of the 5~(th)World Congress on Intelligent Control and Automation,2004(4):1815-818(in Chinese).
[30]N.Yadaiah,Lakshman Singh,Raju S.Bapi,V.Seshagiii Rao,B.L.Deekshatulu,and Atul Negi.Multisensor Data Fusion Using Neural Networks[J].2006 International Joint Conference on Neural Networks,2006(6):875-881.
[31]EVAGGELOS GERANIOTIS,AND YAWGENG A.CHAD.Robust Data Fusion for Multisensor Detection Systems[J].IEEE Transactions On Information Theory,1990(6):1265-1279.
[32]Jean-Franpois Grandin,Miguel Marques.Robust Data Fusion[J].Proceedings of IEEE,2000(3):3-11.
[33]王江萍.基于神经网络的信息融合故障诊断技术[J].机械科学与技术,2002,21(1):127-149.
[34]谷立臣,张优云,丘大谋.液压动力系统运行状态识别技术研究[J].机械工程学报,2001,37(6):61-65.
[35]张文苑,秦志英.动态参量综合测试实验装置的研发及应用[J].河北科技大学学报,2004,25(1):46-48.
[36]秦旭达,王国锋等.动态测试与信号分析系统研究与应用[J].精密制造与自动化,2003年增刊:101-103.
[37]袁希光.传感器技术手册[M].国防工业出版社,1986.
[38]李益平.基于虚拟仪器的液压动力系统故障诊断研究[D].西安建筑科技大学硕士学位论文,2007.
[39]雷天觉.新编液压工程手册[M].北京理工大学出版社,1998.
[40]闻新著.MATLAB神经网络仿真与应用.科学出版社,2003.
[41]梁健.异类传感器数据融合技术应用[J].无线电工程,2006(7):33-35.
[42]赵文武.液压用压力传感器及其合理选用[J].液压与气动,2001(10):23-25.
[43]戚红雨.液压管路应变测量及其在系统故障诊断中的应用研究[D].第二炮兵工程学院硕士学位论文,2000.
[44]王锡良.机械量测试技术[M].东北工学院出版社,1992.
[45]兰箭,穆希,马振书,杜峰坡,夏辉.管道对液压系统的影响[J].科学技术与工程,2007,7(21):5513-5516.
[46]张啸男.液压系统中压力损失的分析与计算[J].一重技术,2006(5):17-18.
[47]黄长艺,严普强.机械工程测试技术基础[M].机械工业出版社,2002.
[48]汤晓君,刘君华.多传感器技术的现状与展望[J].仪器仪表学报,2006,26(12):1309-1313.
[49]张晓雁.振动传感器的校准及误差分析[J].山东商业职业技术学院学报,2007,7(6):102-106.
[50]黄俊钦.测试系统动力学[M].国防工业出版社,1996.
[51]方崇智,肖德云.过程辨识[M].清华大学出版社,1998.
[52]彭文季,罗兴锜,逯鹏.基于对向传播神经网络的水电机组振动故障诊断研究[J].西安理工大学学报,2006,22(4):365-368.
[53]Ang Li-minn and Hon Nin Cheung.Counterpropagation Network and Time-Frequency Shift-Tolerant Preprocessing for Phoneme Recognition[J].Proceeding of the IEEE,1995(3):2037-2040.
[54]Z.Lin,K.Khorasani and R.V.Patel.A counter-propagation neural network for function approximation[J].Proceedings of SPIE,1990(6):382-384.
[55]Carmen Fierascu,Claudia Lidia Badea.Counterpropagation with delays for financial prediction[J].Proceedings of IEEE,1990(6):2795-2799.
[56]Junhong Nie,Member.Constructing Fuzzy Model by Self-organizing Counterpropagation Network[J].IEEE Transactions On Systems,Man,And Cybemetics,1995,6:963-970.
[57]蔺杰.数据融合的神经计算方法[D].浙江大学博士学位论文,2005.
[58]马玉,谷立臣.基于电流信号的液压设备状态监测技术研究[J].液压与气动,2005(6):25-28.
[59]谷立臣.机械信号处理及应用[M].陕西科学技术出版社,2000.
[60]彭恒义.基于振动分析的内燃机故障诊断研究[D].华中科技大学硕士学位论文,2004.
[61]周辉.齿轮故障的特征提取与模式识别技术研究[D].郑州大学硕士学位论文,2005.
[62]罗志增.应用模糊信息融合实现目标物的分类[J].仪器仪表学报,1999,20(4):401-404.
[63]朱玉鹏.信息融合的神经网络原理及应用研究[D].国防科学技术大学硕士学位论文,2004.
[64]Junhong Nie,Member.Constructing Fuzzy Model by Self-organizing Counterpropagation Network[J].IEEE Transactions On Systems,Man,And Cybernetics,1995,6:963-970.
[65]王浩,庄钊文.模糊可靠性分析中的隶属函数确定[J].电子产品可靠性与环境试验,2000,10(4):2-7.
[66]蔺杰.数据融合的神经计算方法[D].浙江大学博士学位论文,2005.
[67]Niu Lihong,Ni Guoqiang,Liu Mingqi.CPN Based Multi-Sensor Data Fusion for Target Classification[J].Proceedings of SPIE,2002(2):671-676.
[68]朱大奇,史慧.人工神经网络原理及应用[M].科学出版社,2006.
[2]周东华,叶银忠.现代故障诊断与容错控制[M].清华大学出版社,2000.
[3]谷立臣.工程机械诊断信息融合理论与方法研究[D].西安交通大学博士学位论文,2002.
[4]郭丽艳.基于BP网络特征级信息融合及在目标识别中的应用研究[D].武汉大学硕士学位论文,2004.
[5]刘延俊,谢玉东.液压系统故障诊断技术的现状及发展趋势[J].液压与气动,2006(2):80-82.
[6]何敏等.故障诊断技术方法综述[J].国外电子测量技术,2006(5):4-6.
[7]刘泽华.基于小波理论的液压系统诊断特征提取与故障分类方法研究[D].西安建筑科技大学硕士学位论文,2007.
[8]李令莱,周东华.基于解析模型的非线性系统鲁棒故障诊断方法综述[J].信息与控制,2004(4):451-456.
[9]姜万录,张淑清,王益群.液压泵故障的小波变换诊断方法[J].机械工程学报,2001(6):34-37.
[10]潘兵,熊静琪.多传感器信息融合在液压系统智能故障诊断中的应用[J].机床与液压,2006(5):190-192.
[11]Prawito Prajitno and Neil Mort.A Fuzzy Model-based Multi-sensor Date Fusion System[J].Proceedings of SPIE,2001(1):301-312.
[12]REN C.LUO,MICHAEL GKAY.Multisensor integration and fusion in intelligent systems[J].IEEE Trans.on Systems,Man and Cybernetics,1989(5):901-931.
[13]Bassel.Information Fusion Concepts:From information elements definition to the application of fusion approaches[J].Proceedings of SPIE,2001(1):205-212.
[14]C.Ray Smith.Multisensor data fusion:concepts and principles[J].IEEE Pacific Rim Conference on Communications,Computers and Signal Processing,May 9-10,1991:235-237.
[15]刘同明,夏祖勋等.数据融合技术及其应用[M].国防工业出版社,1998.
[16]Eddy K.Tsui,Russell Thomas.Real-time multi-sensor data fusion for target detection,classification,tracking,counting,and range estimates[J].Proceedings of SPIE,2004(4):811-821.
[17]W.Chang,H.S.Soliman & A.H.Sung.Image Data Compression Using Counterpropagation Network[J].Proceedings of IEEE,1992(8)405-409.
[18]Hamid Rasoulian,Louis F.Kazda.A multisensor data fusion model for multitarget tracking[J].Proceedings of SPIE,1990(2):24-34.
[19]REN C.LUO,MIN-HSIUNG LIN,RALPH S.SCHERP.Dynamic Multi-Sensor Data Fusion System for Intelligent Robots[J].IEEE Journal Of Robotics and Automation,1988(4):386-396.
[20]潘泉,于昕,程咏梅,张洪才.信息融合理论的基本方法与进展[J].自动化学报,2003(4):599-615.
[21]王志鹏.基于信息融合技术的故障诊断方法的研究与应用[D].大连理工大学博士学位论文,2001.
[22]袁小宏,屈梁生.机械故障诊断中的信息融合利用问题研究[J].振动、测试与诊断,1999(3):187-192.
[23]张彦铎,姜兴渭.多传感器信息融合及在智能故障诊断中的应用[J].传感器技术,1999(2):1R-22.
[24]Chih-Chen Yih,and Kuo Lan Su.Multisensor Fusion and Integration:Approaches,Applications,and Future Research Directions[J].IEEE Sensors Journal,2002(2):107-119(in Chinese).
[25]周芳,韩立岩.多传感器信息融合技术综述[J].遥测遥控,2006(3):1-7.
[26]Bassel Solaiman,Leland E.Pierce,and Fawwaz T.Ulaby.Multisensor Data Fusion Using Fuzzy Concepts:Application to Land-Cover Classification Using ERS-1/JERS-1 SAR Composites[J].IEEE Transactions On Geoscience And Remote Sensing,1999(3):1316-1326.
[27]Zhaoli Zhang,Qi Wang,Shenghe Sun.A New Fuzzy Neural Network Architecture for Multisensor Data fusion in Non-destructive Testing[J].1999 IEEE International Fuzzy Systems Conference Proceedings,1999(99):Ⅲ-1661-Ⅲ-1665(in Chinese).
[28]白士红,李晓雷,庞思勤.模糊-灰色关联-神经网络故障诊断方法研究[J].机械设计与制造,2003(6):10-11.
[29]Diqi Zhu,Shenglin Yu.Neural Networks Data Fusion Algorithm of Electronic Equipment Fault Diagnosis.Proceedings of the 5~(th)World Congress on Intelligent Control and Automation,2004(4):1815-818(in Chinese).
[30]N.Yadaiah,Lakshman Singh,Raju S.Bapi,V.Seshagiii Rao,B.L.Deekshatulu,and Atul Negi.Multisensor Data Fusion Using Neural Networks[J].2006 International Joint Conference on Neural Networks,2006(6):875-881.
[31]EVAGGELOS GERANIOTIS,AND YAWGENG A.CHAD.Robust Data Fusion for Multisensor Detection Systems[J].IEEE Transactions On Information Theory,1990(6):1265-1279.
[32]Jean-Franpois Grandin,Miguel Marques.Robust Data Fusion[J].Proceedings of IEEE,2000(3):3-11.
[33]王江萍.基于神经网络的信息融合故障诊断技术[J].机械科学与技术,2002,21(1):127-149.
[34]谷立臣,张优云,丘大谋.液压动力系统运行状态识别技术研究[J].机械工程学报,2001,37(6):61-65.
[35]张文苑,秦志英.动态参量综合测试实验装置的研发及应用[J].河北科技大学学报,2004,25(1):46-48.
[36]秦旭达,王国锋等.动态测试与信号分析系统研究与应用[J].精密制造与自动化,2003年增刊:101-103.
[37]袁希光.传感器技术手册[M].国防工业出版社,1986.
[38]李益平.基于虚拟仪器的液压动力系统故障诊断研究[D].西安建筑科技大学硕士学位论文,2007.
[39]雷天觉.新编液压工程手册[M].北京理工大学出版社,1998.
[40]闻新著.MATLAB神经网络仿真与应用.科学出版社,2003.
[41]梁健.异类传感器数据融合技术应用[J].无线电工程,2006(7):33-35.
[42]赵文武.液压用压力传感器及其合理选用[J].液压与气动,2001(10):23-25.
[43]戚红雨.液压管路应变测量及其在系统故障诊断中的应用研究[D].第二炮兵工程学院硕士学位论文,2000.
[44]王锡良.机械量测试技术[M].东北工学院出版社,1992.
[45]兰箭,穆希,马振书,杜峰坡,夏辉.管道对液压系统的影响[J].科学技术与工程,2007,7(21):5513-5516.
[46]张啸男.液压系统中压力损失的分析与计算[J].一重技术,2006(5):17-18.
[47]黄长艺,严普强.机械工程测试技术基础[M].机械工业出版社,2002.
[48]汤晓君,刘君华.多传感器技术的现状与展望[J].仪器仪表学报,2006,26(12):1309-1313.
[49]张晓雁.振动传感器的校准及误差分析[J].山东商业职业技术学院学报,2007,7(6):102-106.
[50]黄俊钦.测试系统动力学[M].国防工业出版社,1996.
[51]方崇智,肖德云.过程辨识[M].清华大学出版社,1998.
[52]彭文季,罗兴锜,逯鹏.基于对向传播神经网络的水电机组振动故障诊断研究[J].西安理工大学学报,2006,22(4):365-368.
[53]Ang Li-minn and Hon Nin Cheung.Counterpropagation Network and Time-Frequency Shift-Tolerant Preprocessing for Phoneme Recognition[J].Proceeding of the IEEE,1995(3):2037-2040.
[54]Z.Lin,K.Khorasani and R.V.Patel.A counter-propagation neural network for function approximation[J].Proceedings of SPIE,1990(6):382-384.
[55]Carmen Fierascu,Claudia Lidia Badea.Counterpropagation with delays for financial prediction[J].Proceedings of IEEE,1990(6):2795-2799.
[56]Junhong Nie,Member.Constructing Fuzzy Model by Self-organizing Counterpropagation Network[J].IEEE Transactions On Systems,Man,And Cybemetics,1995,6:963-970.
[57]蔺杰.数据融合的神经计算方法[D].浙江大学博士学位论文,2005.
[58]马玉,谷立臣.基于电流信号的液压设备状态监测技术研究[J].液压与气动,2005(6):25-28.
[59]谷立臣.机械信号处理及应用[M].陕西科学技术出版社,2000.
[60]彭恒义.基于振动分析的内燃机故障诊断研究[D].华中科技大学硕士学位论文,2004.
[61]周辉.齿轮故障的特征提取与模式识别技术研究[D].郑州大学硕士学位论文,2005.
[62]罗志增.应用模糊信息融合实现目标物的分类[J].仪器仪表学报,1999,20(4):401-404.
[63]朱玉鹏.信息融合的神经网络原理及应用研究[D].国防科学技术大学硕士学位论文,2004.
[64]Junhong Nie,Member.Constructing Fuzzy Model by Self-organizing Counterpropagation Network[J].IEEE Transactions On Systems,Man,And Cybernetics,1995,6:963-970.
[65]王浩,庄钊文.模糊可靠性分析中的隶属函数确定[J].电子产品可靠性与环境试验,2000,10(4):2-7.
[66]蔺杰.数据融合的神经计算方法[D].浙江大学博士学位论文,2005.
[67]Niu Lihong,Ni Guoqiang,Liu Mingqi.CPN Based Multi-Sensor Data Fusion for Target Classification[J].Proceedings of SPIE,2002(2):671-676.
[68]朱大奇,史慧.人工神经网络原理及应用[M].科学出版社,2006.