基于多Agent的断路器故障诊断系统设计
|
摘要
作为高压电器中一种重要的设备，高压断路器在电力系统中肩负着控制和保护双重任务，其自身的健康状况与运行的可靠性直接关系到电力系统的安全与稳定。因此，为了降低高压断路器的故障率，有效提高高压断路器的可靠性，本文设计了断路器状态监测与故障诊断系统，并着重从以下四个方面对该系统进行了研究。
首先，针对传统故障诊断系统存在的缺点，本文将多Agent技术应用于断路器的故障诊断当中。并对多Agent故障诊断系统的任务分解、组织结构以及通信与协作机制进行了研究。
其次，研究了特征提取Agent提取振动信号特征参数的方法。将经验模态分解和信息熵理论相结合提出了一种新的特征提取方法。测试与仿真结果表明，利用该方法提取的特征向量可以正确地反映高压断路器状态的变化，为断路器的故障诊断提供了新方法。
再次，研究了诊断Agent进行断路器故障诊断所使用的诊断策略。在实际应用中，由于断路器不可能频繁动作，所以无法获得大量的故障样本进行训练。支持向量机是一种基于结构风险最小化的学习机器，为小样本学习分类问题提供了一条有效的解决途径。同时本文又对多诊断Agent诊断结果的模糊融合原理进行了介绍与应用分析。
最后，根据目前国内电力设备管理与运行模式以及断路器状态监测与故障诊断的特殊性，设计了一种基于多Agent的高压断路器状态监测与故障诊断系统，并开发了基于该设计的硬件设备和上位机管理软件。试验结果表明，该系统可以将大型数据库、研究机构专家、设备维护人员和现场监测仪有效地结合起来，实现了对多方诊断资源的有效利用，提高了断路器诊断系统诊断的准确率和效率。
As an important device in high-voltage electrical apparatus, high-voltage circuitbreakers play the dual role of control and protection in the power system. The healthstatus and operating reliability of circuit breakers are directly related to the security andstability of power system. Therefore, the condition monitoring and fault diagnosticsystem was designed in order to reduce the fault rate of high-voltage circuit breakersand effectively improve the reliability of high-voltage circuit breakers. The system wasstudied from the following four aspects.
Firstly, to overcome the shortcomings of traditional systems of fault diagnosis, themulti-agent technology was applied to fault diagnosis of circuit breakers in this paper.The paper have made research on the task decomposition, organization structure, themechanism of communication and coordination which are involved in the systems offault diagnosis based on multi-agent.
Secondly, the paper have studied the extract method of characteristic parametersabout vibration signals which were used by characteristic-extracting agents. A newmethod of feature extraction was proposed by associating the empirical modedecomposition with the information entropy theory. The results of simulation and testshow that the extracted characteristic parameters can sensitively reflect changes ofhigh-voltage circuit breakers status with this method. It provides a new method for faultdiagnosis of circuit breakers.
Thirdly, fault diagnostic strategy of diagnosis agents about high-voltage circuitbreakers was studied. In practical applications, on account of the circuit breakers cannot act frequently, a large numbers of fault samples can not be obtained for training. Thesupport vector machine is a learning machine based on the structural risk minimization,which provides an effective solution for the classification problems of small sample learning. At the same time, introduction and application analysis about fuzzy fusion ofagents’ diagnosis results were performed.
Finally, according to the management and operation mode of currently domesticelectrical equipment and the particularity of the condition monitoring and faultdiagnosis of circuit breakers, a condition monitoring and fault diagnosis system ofcircuit breakers based on multi-agent was designed. At the same time, the hardware andmanagement software of computer based on the design were developed. The test resultshows that the system can effectively unite the large-scale database, the experts ofinstitutes, the equipment maintainer and field monitor to realize the effective utilizationof multi-diagnosis resources. Consequently, the accuracy and efficiency of circuitbreakers fault diagnosis were improved.
首先，针对传统故障诊断系统存在的缺点，本文将多Agent技术应用于断路器的故障诊断当中。并对多Agent故障诊断系统的任务分解、组织结构以及通信与协作机制进行了研究。
其次，研究了特征提取Agent提取振动信号特征参数的方法。将经验模态分解和信息熵理论相结合提出了一种新的特征提取方法。测试与仿真结果表明，利用该方法提取的特征向量可以正确地反映高压断路器状态的变化，为断路器的故障诊断提供了新方法。
再次，研究了诊断Agent进行断路器故障诊断所使用的诊断策略。在实际应用中，由于断路器不可能频繁动作，所以无法获得大量的故障样本进行训练。支持向量机是一种基于结构风险最小化的学习机器，为小样本学习分类问题提供了一条有效的解决途径。同时本文又对多诊断Agent诊断结果的模糊融合原理进行了介绍与应用分析。
最后，根据目前国内电力设备管理与运行模式以及断路器状态监测与故障诊断的特殊性，设计了一种基于多Agent的高压断路器状态监测与故障诊断系统，并开发了基于该设计的硬件设备和上位机管理软件。试验结果表明，该系统可以将大型数据库、研究机构专家、设备维护人员和现场监测仪有效地结合起来，实现了对多方诊断资源的有效利用，提高了断路器诊断系统诊断的准确率和效率。
As an important device in high-voltage electrical apparatus, high-voltage circuitbreakers play the dual role of control and protection in the power system. The healthstatus and operating reliability of circuit breakers are directly related to the security andstability of power system. Therefore, the condition monitoring and fault diagnosticsystem was designed in order to reduce the fault rate of high-voltage circuit breakersand effectively improve the reliability of high-voltage circuit breakers. The system wasstudied from the following four aspects.
Firstly, to overcome the shortcomings of traditional systems of fault diagnosis, themulti-agent technology was applied to fault diagnosis of circuit breakers in this paper.The paper have made research on the task decomposition, organization structure, themechanism of communication and coordination which are involved in the systems offault diagnosis based on multi-agent.
Secondly, the paper have studied the extract method of characteristic parametersabout vibration signals which were used by characteristic-extracting agents. A newmethod of feature extraction was proposed by associating the empirical modedecomposition with the information entropy theory. The results of simulation and testshow that the extracted characteristic parameters can sensitively reflect changes ofhigh-voltage circuit breakers status with this method. It provides a new method for faultdiagnosis of circuit breakers.
Thirdly, fault diagnostic strategy of diagnosis agents about high-voltage circuitbreakers was studied. In practical applications, on account of the circuit breakers cannot act frequently, a large numbers of fault samples can not be obtained for training. Thesupport vector machine is a learning machine based on the structural risk minimization,which provides an effective solution for the classification problems of small sample learning. At the same time, introduction and application analysis about fuzzy fusion ofagents’ diagnosis results were performed.
Finally, according to the management and operation mode of currently domesticelectrical equipment and the particularity of the condition monitoring and faultdiagnosis of circuit breakers, a condition monitoring and fault diagnosis system ofcircuit breakers based on multi-agent was designed. At the same time, the hardware andmanagement software of computer based on the design were developed. The test resultshows that the system can effectively unite the large-scale database, the experts ofinstitutes, the equipment maintainer and field monitor to realize the effective utilizationof multi-diagnosis resources. Consequently, the accuracy and efficiency of circuitbreakers fault diagnosis were improved.
引文
[1]范兴明,邹积岩,丛吉远.电力变压器和高压断路器状态监测技术的发展与现状综述[J].电气应用,2005,24(4):35-39.
[2]胡文平,尹相根等.电气设备在线监测技术的研究与发展[J].华北电力技术,2003,2:23-29.
[3]朱德恒,谈克雄.电气设备状态检测与故障诊断技术的现状与展望[J].电力设备,2003,4:l-8.
[4]荣命哲,贾申利,王小华.电器设备状态检修[M].北京:机械工业出版社,2007.
[5] B. Stephen, S.M. Strachan, S.D.J. McArthur, etc. Design of trip current monitoringsystem for circuit breaker condition assessment [J]. IET Gener. Transm. Distrib,2007,1(1):89-95.
[6] Dennis S. S. Lee, Brian J. Lithgow, Rob E. Morrison. New Fault Diagnosis ofCircuit Breakers [J]. IEEE TRANSACTIONS ON POWER DELIVERY,2003,18(2):454-459.
[7] Maja Knezev, Zarko Djekic, Mladen Kezunovic. Automated Circuit BreakerMonitoring [J]. Power Engineering Society General Meeting,2007:1-6.
[8] M. Kezunovic, C. Nail, Z.Ren. Automated Circuit Breaker Monitoring and Analysis[J]. Power Engineering Society Summer Meeting,2002:559-564.
[9] T. Watanabe1, T. Sugimoto, H. Imagawa,etc. Practical Application of DiagnosticMethod of Circuit Breaker by Measuring Three Current Waveforms [J].2008International Conference on Condition Monitoring and Diagnosis,2007:398-401.
[10]戴怀志,吕一航,贾申利等.断路器综合在线检监测系统研制[J].高压电器,2004,40(2):104-106.
[11]林燕侠,曾庆军.高压真空断路器智能在线监测系统的研制[J].电子设计工程,2009,17(12):21-23.
[12]兰建军,洪智勇,林青瑜.高压断路器机械参数监测与寿命预估方法研究[J].东北电力大学学报,2011,31(1):57-60.
[13]关永刚,黄瑜珑,钱家骊.基于振动信号的高压断路器机械故障诊断[J]. HIGHVOLTAGE ENGINEERING.2000,26(3):66-68.
[14]江渭涛,郑建勇,梅军.基于小波变换的高压断路器振动信号故障诊断仿真研究[J].电工电气.2010,32(1):5-7.
[15]孙来军,胡晓光,纪延超等.小波包-特征嫡在高压断路器故障诊断中的应用[J].电力系统自动化.2006,30(14):62-65.
[16]Jin S. Heo and Kwang Y. Lee. A Multi-Agent System-Based IntelligentIdentification System for Power Plant Control and Fault-Diagnosis [J]. PowerEngineering Society General Meeting,2006:1-6.
[17]Rabie Belkacemi, Ali Feliachi. Multi-Agent Design for Power Distribution SystemReconfiguration Based on the Artificial Immune System Algorithm [J]. Circuits andSystems (ISCAS),2010:3461-3464.
[18]孙红岩.大型旋转机械智能诊断多Agent系统的研究.重庆大学学报,2006,29(5):8-11.
[19]赵文清,张胜龙,牛东晓.多Agent在变压器故障诊断中的研究[J].电力自动化设备,2011,31(1):23-27.
[20]何炎祥等. Agent和多Agent系统的设计与应用[M].武汉:武汉大学出版社,2001.
[21]Michael Wooldridge. An Introduction to Multi-Agent Systems[M].北京:电子工业出版社,2003.
[22]Keinosuke Matsumoto, Tomoaki Maruo, Akifumi Tanimoto. A DependableMulti-Agent System with Self-Diagnostic Function [J].2009Eighth InternationalSymposium on Parallel and Distributed Computing,2009:213-217.
[23]V. Ebrahimipour, K. Rezaie, S. Shokravi. Enhanced FMEA by Multi-agentEngineering FIPA Based System to Analyze Failures[J]. Reliability andMaintainability Symposium (RAMS),2010:1-6.
[24]吴伟蔚,杨叔子.故障诊断Agent研究[J].振动工程学报,2000,13(3):393-399.
[25]张贺.基于MAS技术的新型电网故障诊断系统的研究[J].江西电力,29(6):1-4.
[26]钟联炯,孙璐.多Agent的故障诊断任务分解和结果综合研究[J].火力与指挥控制,2008,33(10):113-116
[27]何永勇,褚福磊,陈真勇.基于多Agent的分布式故障智能诊断原型系统研究[J].计算机工程与科学,2002,24(1):88-92.
[28]詹雄涛.基于组织的多Agent系统问题求解.福州大学硕士学位论文,2005.
[29]Mario J.G.C. Mendes and Jose Sa da Costa. A Multi-agent Approach to aNetworked Fault Detection System [J].2010Conference on Control and FaultTolerant Systems,2010:916-921.
[30]孟永鹏,贾申利,荣命哲.小波包频带能量分解在断路器机械状态监测中的应用[J].西安交通大学学报,2004,38(10):1013-1017.
[31]胡晓光,赵志鹏,赵化业.高压断路器状态参数测试仪的研制[J].电力系统及其自动化学报,2008,20(5):81-86.
[32]吴海诚,郭晓松,赵军阳.多Agent复杂诊断系统分布式协同求解研究[J].电光与控制,2009,16(11):29-32.
[33]韩泉叶,王阳萍.基于CBR和MAS的分布式故障诊断系统模型研究[J].兰州交通大学学报,2004,23(6):74-77.
[34]张复春,张凤鸣,南建国.基于Agent的远程故障诊断系统的实现[J].空军工程大学学报,2003,4(6):68-70.
[35]James A. Momoh, Keisha Alfred and Yan Xia. Framework for Multi-Agent System(MAS) Detection and Control of Arcing of Shipboard Electric Power Systems[J].Intelligent System Applications to Power Systems,2009:1-6.
[36]李伟,王仲生.基于Multi-agent的飞机智能故障诊断与监控系统设计[J].计算机测量与控制,2007.15(11):1424-1427.
[37]武兵,熊诗波,林健等.基于Multi-Agent技术的大型机电设备故障诊断系统[J].测试技术学报,2006,20(5):412-417.
[38]张超,陈建军,郭迅.基于EMD能量熵和支持向量机的齿轮故障诊断方法[J].振动与冲击,2010,29(10):216-221.
[39]张艳丽,张守祥.基于EMD方法的煤岩界面识别研究[J].煤炭技术,2007,(26)9:49-51.
[40]陈伟根,邓帮飞.小波包能谱熵与神经网络在断路器故障诊断中的应用[J].重庆大学学报,2008,7(31):744-748.
[41]熊卫华,赵光宙.基于希尔伯特-黄变换的轴承振动特性分析[J].传感技术学报,2006,19(3):655-658.
[42]袁龙,李小昱,冯耀泽.基于希尔伯特黄变换的发动机故障诊断方法研究[J].湖北农业科学,2010,49(5):1198-1201.
[43]Jan Rozto il, Martin Novák. Fault diagnosis of rotating machinery based onwavelet transforms and Neural Network[J].2010International Conference onApplied Electronics,2010:1-6.
[44]Ping Huang, Ziwei Pan. A New Bearing Fault Diagnosis Method Based on MM andEMD [J].20103rd International Congress on Image and Signal Processing.2010:3975-3979.
[45]Laijun Sun, Mingliang Liu, Haibo Qian and Jianju Zhen. A New Method to FaultDiagnosis for Circuit Breakers Based on Characteristic Entropy of Wavelet Packet[J].2010International Conference on Intelligent System Design and EngineeringApplication,2010,838-841.
[46]Laijun Sun, Mingliang Liu, Jianju Zhen and Guangzhong Ye. A New FaultDiagnosis Method for HV Circuit Breakers Based on Wavelet Packet-Neuralnetwork [J].20116th IEEE Conference on Industrial Electronics and Applications,2011,838-844.
[47]Laijun Sun, Mingliang Liu, Jianju Zhen. Characteristic entropy tree of waveletpacket and its application in fault diagnosis [J]. Journal of Harbin Institute ofTechnology (New Series),2011,(18):293-298.
[48]张新海,雷勇. BP神经网络在机械故障诊断中的应用[J].噪声与振动控制,2008,10(5):95-97.
[49]王玲,杜庆东,杨雨迎.基于BP神经网络的装备智能故障诊断技术研究[J].科学技术与工程,2011,11(6):1344-1347.
[50]杨海马,刘瑾,张菁. BP神经网络在变压器故障诊断中的应用[J].变压器,2009,46(1):67-70.
[51]Vapnik V. The nature of statistical learning theory. New York. Springer-Verlag，1995.
[52]蒋少华,桂卫华,阳春华.支持向量机及其在密闭鼓风炉故障诊断中的应用[J].小型微型计算机系统,2008,29(4):777-781.
[53]左红,顾家铭,于锦禄.基于支持向量机的滚动轴承故障诊断研究[J].轴承,2008,(8):36-39.
[54]Nishchal K. Verma, Abhishek Roy. Motor current signature analysis bymulti-resolution methods using Support Vector Machine[J].2011IEEEInternational Conference on System Engineering and Technology,2011:65-69.
[55]D. Thukaram, H. P. Khincha, IEEE, and H. P. Vijaynarasimha. Artificial NeuralNetwork and Support Vector Machine Approach for Locating Faults in RadialDistribution Systems [J]. IEEE TRANSACTIONS ON POWER DELIVERY,2005,20(2):710-721.
[56]Victor A. Barrera Nú ez, Saurabh Kulkarni, Surya Santoso,etc. SVM-BasedClassification Methodology for Overhead Distribution Fault Events[J].14thIEEEInternational Conference on Harmonics and Quality of Power,2010:1-6.
[57]吴峰崎,孟光.基于支持向量机的转子振动信号故障分类研究[J].振动工程学报,2006,19(2):238-241.
[58]唐发明,王仲东,陈绵云.支持向量机多类分类算法研究[J].华中科技大学,2005,20(7):746-750.
[59]夏建涛,何明一.支持向量机与纠错编码相结合的多类分类算法[J].西北工业大学学报,2003,21(4):443-448.
[60]邱绵浩,王自营,安钢.基于核主元分析与纠错输出编码SVM的齿轮故障诊断[J].振动与冲击,2009,28(5):1-5.
[61]王建.基于模糊理论的多Agent协作的研究.沈阳工业大学硕士学位论文,2007,1:29-39.
[62]蒋志忠,冯玉光,奚文骏.基于多Agent系统的远程故障诊断系统模型[J].计算机工程,2007,33(5):278-280.
[63]A. Akbari, A. Setayeshmehr, H. Borsi, and E. Gockenbach. Intelligent Agent-BasedSystem Using Dissolved Gas Analysis to Detect Incipient Faults in PowerTransformers [J]. Electrical Insulation Magazine,2010,26(6):27-40.
[64]Sajid Hussain, Elhadi Shakshuki, Abdul Wasey Matin. Agent-based SystemArchitecture for Wireless Sensor Networks [J]. Proceedings of the20thInternational Conference on Advanced Information Networking and Applications,2006.
[65]Jacqueline G. Rolim, Patrícia C. Maiola, Henrique R. Baggenstoss, etc. BayesianNetworks Application to Power Transformer Diagnosis[J]. PowerTech2007,2007:999-1004.
[66]Gang Niu, Tian Han, Bo-Suk Yang,etc. Multi-agent decision fusion for motor faultdiagnosis [J]. Mechanical Systems and Signal Processing,2007:1285-1289.
[67]范显峰.基于多Agent系统的卫星故障诊断技术研究.哈尔滨工业大学博士学位论文,2003,3.
[68]肖小锋,蔡金燕,梁玉英.基于多Agent的监测与诊断系统功能模型[J].微计算机信息,2006,22(3):212-214.
[69]Sathish Natarajan, Kaushik Ghosh, Rajagopalan Srinivasan. An evaluation of ahierarchical multi agent based process monitoring system for chemical plants [J].2011International Conference on Networking, Sensing and Control,2011,151-156.
[70]孙来军,胡晓光.基于单片机+CPLD的高压断路器动作信息采集器[J].电气时
代,2006,(3):118-120.
[2]胡文平,尹相根等.电气设备在线监测技术的研究与发展[J].华北电力技术,2003,2:23-29.
[3]朱德恒,谈克雄.电气设备状态检测与故障诊断技术的现状与展望[J].电力设备,2003,4:l-8.
[4]荣命哲,贾申利,王小华.电器设备状态检修[M].北京:机械工业出版社,2007.
[5] B. Stephen, S.M. Strachan, S.D.J. McArthur, etc. Design of trip current monitoringsystem for circuit breaker condition assessment [J]. IET Gener. Transm. Distrib,2007,1(1):89-95.
[6] Dennis S. S. Lee, Brian J. Lithgow, Rob E. Morrison. New Fault Diagnosis ofCircuit Breakers [J]. IEEE TRANSACTIONS ON POWER DELIVERY,2003,18(2):454-459.
[7] Maja Knezev, Zarko Djekic, Mladen Kezunovic. Automated Circuit BreakerMonitoring [J]. Power Engineering Society General Meeting,2007:1-6.
[8] M. Kezunovic, C. Nail, Z.Ren. Automated Circuit Breaker Monitoring and Analysis[J]. Power Engineering Society Summer Meeting,2002:559-564.
[9] T. Watanabe1, T. Sugimoto, H. Imagawa,etc. Practical Application of DiagnosticMethod of Circuit Breaker by Measuring Three Current Waveforms [J].2008International Conference on Condition Monitoring and Diagnosis,2007:398-401.
[10]戴怀志,吕一航,贾申利等.断路器综合在线检监测系统研制[J].高压电器,2004,40(2):104-106.
[11]林燕侠,曾庆军.高压真空断路器智能在线监测系统的研制[J].电子设计工程,2009,17(12):21-23.
[12]兰建军,洪智勇,林青瑜.高压断路器机械参数监测与寿命预估方法研究[J].东北电力大学学报,2011,31(1):57-60.
[13]关永刚,黄瑜珑,钱家骊.基于振动信号的高压断路器机械故障诊断[J]. HIGHVOLTAGE ENGINEERING.2000,26(3):66-68.
[14]江渭涛,郑建勇,梅军.基于小波变换的高压断路器振动信号故障诊断仿真研究[J].电工电气.2010,32(1):5-7.
[15]孙来军,胡晓光,纪延超等.小波包-特征嫡在高压断路器故障诊断中的应用[J].电力系统自动化.2006,30(14):62-65.
[16]Jin S. Heo and Kwang Y. Lee. A Multi-Agent System-Based IntelligentIdentification System for Power Plant Control and Fault-Diagnosis [J]. PowerEngineering Society General Meeting,2006:1-6.
[17]Rabie Belkacemi, Ali Feliachi. Multi-Agent Design for Power Distribution SystemReconfiguration Based on the Artificial Immune System Algorithm [J]. Circuits andSystems (ISCAS),2010:3461-3464.
[18]孙红岩.大型旋转机械智能诊断多Agent系统的研究.重庆大学学报,2006,29(5):8-11.
[19]赵文清,张胜龙,牛东晓.多Agent在变压器故障诊断中的研究[J].电力自动化设备,2011,31(1):23-27.
[20]何炎祥等. Agent和多Agent系统的设计与应用[M].武汉:武汉大学出版社,2001.
[21]Michael Wooldridge. An Introduction to Multi-Agent Systems[M].北京:电子工业出版社,2003.
[22]Keinosuke Matsumoto, Tomoaki Maruo, Akifumi Tanimoto. A DependableMulti-Agent System with Self-Diagnostic Function [J].2009Eighth InternationalSymposium on Parallel and Distributed Computing,2009:213-217.
[23]V. Ebrahimipour, K. Rezaie, S. Shokravi. Enhanced FMEA by Multi-agentEngineering FIPA Based System to Analyze Failures[J]. Reliability andMaintainability Symposium (RAMS),2010:1-6.
[24]吴伟蔚,杨叔子.故障诊断Agent研究[J].振动工程学报,2000,13(3):393-399.
[25]张贺.基于MAS技术的新型电网故障诊断系统的研究[J].江西电力,29(6):1-4.
[26]钟联炯,孙璐.多Agent的故障诊断任务分解和结果综合研究[J].火力与指挥控制,2008,33(10):113-116
[27]何永勇,褚福磊,陈真勇.基于多Agent的分布式故障智能诊断原型系统研究[J].计算机工程与科学,2002,24(1):88-92.
[28]詹雄涛.基于组织的多Agent系统问题求解.福州大学硕士学位论文,2005.
[29]Mario J.G.C. Mendes and Jose Sa da Costa. A Multi-agent Approach to aNetworked Fault Detection System [J].2010Conference on Control and FaultTolerant Systems,2010:916-921.
[30]孟永鹏,贾申利,荣命哲.小波包频带能量分解在断路器机械状态监测中的应用[J].西安交通大学学报,2004,38(10):1013-1017.
[31]胡晓光,赵志鹏,赵化业.高压断路器状态参数测试仪的研制[J].电力系统及其自动化学报,2008,20(5):81-86.
[32]吴海诚,郭晓松,赵军阳.多Agent复杂诊断系统分布式协同求解研究[J].电光与控制,2009,16(11):29-32.
[33]韩泉叶,王阳萍.基于CBR和MAS的分布式故障诊断系统模型研究[J].兰州交通大学学报,2004,23(6):74-77.
[34]张复春,张凤鸣,南建国.基于Agent的远程故障诊断系统的实现[J].空军工程大学学报,2003,4(6):68-70.
[35]James A. Momoh, Keisha Alfred and Yan Xia. Framework for Multi-Agent System(MAS) Detection and Control of Arcing of Shipboard Electric Power Systems[J].Intelligent System Applications to Power Systems,2009:1-6.
[36]李伟,王仲生.基于Multi-agent的飞机智能故障诊断与监控系统设计[J].计算机测量与控制,2007.15(11):1424-1427.
[37]武兵,熊诗波,林健等.基于Multi-Agent技术的大型机电设备故障诊断系统[J].测试技术学报,2006,20(5):412-417.
[38]张超,陈建军,郭迅.基于EMD能量熵和支持向量机的齿轮故障诊断方法[J].振动与冲击,2010,29(10):216-221.
[39]张艳丽,张守祥.基于EMD方法的煤岩界面识别研究[J].煤炭技术,2007,(26)9:49-51.
[40]陈伟根,邓帮飞.小波包能谱熵与神经网络在断路器故障诊断中的应用[J].重庆大学学报,2008,7(31):744-748.
[41]熊卫华,赵光宙.基于希尔伯特-黄变换的轴承振动特性分析[J].传感技术学报,2006,19(3):655-658.
[42]袁龙,李小昱,冯耀泽.基于希尔伯特黄变换的发动机故障诊断方法研究[J].湖北农业科学,2010,49(5):1198-1201.
[43]Jan Rozto il, Martin Novák. Fault diagnosis of rotating machinery based onwavelet transforms and Neural Network[J].2010International Conference onApplied Electronics,2010:1-6.
[44]Ping Huang, Ziwei Pan. A New Bearing Fault Diagnosis Method Based on MM andEMD [J].20103rd International Congress on Image and Signal Processing.2010:3975-3979.
[45]Laijun Sun, Mingliang Liu, Haibo Qian and Jianju Zhen. A New Method to FaultDiagnosis for Circuit Breakers Based on Characteristic Entropy of Wavelet Packet[J].2010International Conference on Intelligent System Design and EngineeringApplication,2010,838-841.
[46]Laijun Sun, Mingliang Liu, Jianju Zhen and Guangzhong Ye. A New FaultDiagnosis Method for HV Circuit Breakers Based on Wavelet Packet-Neuralnetwork [J].20116th IEEE Conference on Industrial Electronics and Applications,2011,838-844.
[47]Laijun Sun, Mingliang Liu, Jianju Zhen. Characteristic entropy tree of waveletpacket and its application in fault diagnosis [J]. Journal of Harbin Institute ofTechnology (New Series),2011,(18):293-298.
[48]张新海,雷勇. BP神经网络在机械故障诊断中的应用[J].噪声与振动控制,2008,10(5):95-97.
[49]王玲,杜庆东,杨雨迎.基于BP神经网络的装备智能故障诊断技术研究[J].科学技术与工程,2011,11(6):1344-1347.
[50]杨海马,刘瑾,张菁. BP神经网络在变压器故障诊断中的应用[J].变压器,2009,46(1):67-70.
[51]Vapnik V. The nature of statistical learning theory. New York. Springer-Verlag，1995.
[52]蒋少华,桂卫华,阳春华.支持向量机及其在密闭鼓风炉故障诊断中的应用[J].小型微型计算机系统,2008,29(4):777-781.
[53]左红,顾家铭,于锦禄.基于支持向量机的滚动轴承故障诊断研究[J].轴承,2008,(8):36-39.
[54]Nishchal K. Verma, Abhishek Roy. Motor current signature analysis bymulti-resolution methods using Support Vector Machine[J].2011IEEEInternational Conference on System Engineering and Technology,2011:65-69.
[55]D. Thukaram, H. P. Khincha, IEEE, and H. P. Vijaynarasimha. Artificial NeuralNetwork and Support Vector Machine Approach for Locating Faults in RadialDistribution Systems [J]. IEEE TRANSACTIONS ON POWER DELIVERY,2005,20(2):710-721.
[56]Victor A. Barrera Nú ez, Saurabh Kulkarni, Surya Santoso,etc. SVM-BasedClassification Methodology for Overhead Distribution Fault Events[J].14thIEEEInternational Conference on Harmonics and Quality of Power,2010:1-6.
[57]吴峰崎,孟光.基于支持向量机的转子振动信号故障分类研究[J].振动工程学报,2006,19(2):238-241.
[58]唐发明,王仲东,陈绵云.支持向量机多类分类算法研究[J].华中科技大学,2005,20(7):746-750.
[59]夏建涛,何明一.支持向量机与纠错编码相结合的多类分类算法[J].西北工业大学学报,2003,21(4):443-448.
[60]邱绵浩,王自营,安钢.基于核主元分析与纠错输出编码SVM的齿轮故障诊断[J].振动与冲击,2009,28(5):1-5.
[61]王建.基于模糊理论的多Agent协作的研究.沈阳工业大学硕士学位论文,2007,1:29-39.
[62]蒋志忠,冯玉光,奚文骏.基于多Agent系统的远程故障诊断系统模型[J].计算机工程,2007,33(5):278-280.
[63]A. Akbari, A. Setayeshmehr, H. Borsi, and E. Gockenbach. Intelligent Agent-BasedSystem Using Dissolved Gas Analysis to Detect Incipient Faults in PowerTransformers [J]. Electrical Insulation Magazine,2010,26(6):27-40.
[64]Sajid Hussain, Elhadi Shakshuki, Abdul Wasey Matin. Agent-based SystemArchitecture for Wireless Sensor Networks [J]. Proceedings of the20thInternational Conference on Advanced Information Networking and Applications,2006.
[65]Jacqueline G. Rolim, Patrícia C. Maiola, Henrique R. Baggenstoss, etc. BayesianNetworks Application to Power Transformer Diagnosis[J]. PowerTech2007,2007:999-1004.
[66]Gang Niu, Tian Han, Bo-Suk Yang,etc. Multi-agent decision fusion for motor faultdiagnosis [J]. Mechanical Systems and Signal Processing,2007:1285-1289.
[67]范显峰.基于多Agent系统的卫星故障诊断技术研究.哈尔滨工业大学博士学位论文,2003,3.
[68]肖小锋,蔡金燕,梁玉英.基于多Agent的监测与诊断系统功能模型[J].微计算机信息,2006,22(3):212-214.
[69]Sathish Natarajan, Kaushik Ghosh, Rajagopalan Srinivasan. An evaluation of ahierarchical multi agent based process monitoring system for chemical plants [J].2011International Conference on Networking, Sensing and Control,2011,151-156.
[70]孙来军,胡晓光.基于单片机+CPLD的高压断路器动作信息采集器[J].电气时
代,2006,(3):118-120.