模拟电路故障诊断神经网络数据融合方法
详细信息    本馆镜像全文|  推荐本文 |  |   获取CNKI官网全文
摘要
模拟电路故障诊断经过三十多年发展,已经有很多故障诊断理论和方法,但是这些理论和方法只适合于非容差或小容差线性电路。随着电子技术的发展,特别是超大规模模拟电路和模数混合电路发展,对模拟电路故障诊断提出了新的挑战,需要探索新的模拟电路故障诊断理论与方法。人工神经网络用于模拟电路故障诊断是一门崭新的学科,近年来,受到了普遍的关注和重视。数据融合作为许多传统学科和新兴工程领域相结合而产生的一个新的前沿学科,超越了在军事领域的应用,已经在许多领域都得到了广泛的应用。
     虽然模拟电路故障诊断、人工神经网络和数据融合技术在各自的领域或者两两相互结合的领域取得了一定的发展,但是目前关于人工神经网络和数据融合技术相结合对模拟电路进行故障诊断的文献还未有所见。本文把数据融合技术引入人工神经网络来对模拟电路进行故障诊断,形成一种新的方法。
     本文在传统的模拟电路故障字典法的基础上引入了数据融合中的数据挖掘技术,优化了故障字典的建立。本文在神经网络对模拟电路进行故障诊断的基础上提出了基于人工神经网络的数据融合方法,主要目的是为了解决故障诊断中的容差问题并提高诊断的正确率和诊断速度。本文探讨了RBF神经网络结合D-S证据理论的D-S证据神经网络在模拟电路故障诊断上的应用。神经网络的联想记忆功能、容错性和鲁棒性及非线性映射能力和数据融合技术对多源数据的分析、综合、推理能力相结合,使得这一方法明显优于传统的神经网络诊断方法。通过对电路进行仿真表明,利用所提出的证据神经网络方法对模拟电路故障进行了较准确的诊断,达到了较好的目标。
In the past thirty years, it has developed a great deal of theory and approaches for fault diagnosis. But these methods only adapt to linear circuits with non-tolerance or mini-tolerance.Along with development of electrical technology,especially VLSI and mixed circuits, It brings up new challenge to fault diagnosis of analog circuits.It is in great need of new theory and approaches to it.It is a new subject for fault diagnosis to make use of Artifical Neural Network. In recent years, researchers paid more attention to ANN than before. The application of ANN has turned into a succeed aspect for ANN. Data fusion has been used widely in many areas besides military area as a new advanced knowledge which was combined with many traditional konwledge and new engineering areas.
    Though fault detect and diagnosis for analog circuits, ANN and data fusion has made great progress in each area and some areas combined with each two of them, there are few
    papers in fault detect and diagnosis for analog circuits with method combined with Artificial Neural Network and data fusion. In this paper, data fusion was imported in ANN to diagnosis fault of analog circuits. It comes to be a new technology.
    In the paper, we used data mining in data fusion on the basis of traditional DC dictionary approach to optimize the course of construction a fault dictionary. The paper present a data fusion technology with ANN based on diagnosis for analog circuits with ANN. It aimed to deal with parameter tolerance, correctness and diagnosis speed. A Radial Basis Function(RBF) ANN using Dempster-Shafer theory of evidence which is abbreviated evidence network is presented to diagnose analog circuits. The combination of association memory function, robustness, nonlinear mapping ability of ANN and analysis, synthesis and reasoning ability to multisource data of data fusion made it better than traditional approaches. The simulation to analog circuits can indicate that it is a good approach to diagnose analog circuits correctly. It proved to be feasible under lots of experiment.
引文
[1]Bandler J W, Salama A E. Fault diagnosis of analog circuits. Proc. IEEE,1985,73(8): 1279-1327
    [2]J.W.Bandler and E.Salama. Fault Diagnosis of Analog Circuits, IEEE Int.Symp.on CAS.,1984,(2): 660-663
    [3]杨士元,童诗白.模拟系统的故障诊断与可靠性设计.北京:清华大学出版社, 2001,1-7
    [4]杨光正,吴岷,张晓莉.模式识别.合肥:中国科学技术出版社,2001,1-6
    [5]郑君里,杨行峻.人工神经网络.北京:高等教育出版社,1992,26-62
    [6]丛爽.神经网络、模糊系统及其在运动控制中的应用.北京:中国科学技术大学出版社,2001,20-23
    [7]高文焕,汪蕙.模拟电路的计算机分析与设计-Pspice程序应用.北京:清华大学出版社,1999,185
    [8]徐丽娜.神经网络控制.哈尔滨:哈尔滨工业大学出版社,1999,18-22
    [9]闻新,周露,王丹力等.MATLAB神经网络应用设计.科学出版社,2000,244-260
    [10]蓝国兴,艾国强.信息融合技术.计算机世界,1997,107-108
    [11]林明星,付晨钟.基于神经网络的多传感器信息融合技术.新技术工艺,1999,6-8
    [12]康耀红.数据融合理论与应用.西安:西安电子科技大学出版社,1997,2-24
    [13]Lawrence A. Klein. Sensor and Data Fusion Concepts and Applications. SPIE Optical Engineering Press,1999, 198-203
    [14]刘同明,夏祖勋,解洪成.数据融合技术及其应用.北京:国防工业出版社,1998,1-9
    [15]胡良梅.基于D-S证据理论的神经网络形状识别系统:[合肥工业大学硕士论文].合肥工业大学图书馆:合肥工业大学,2002,8-10
    [16]David L. Hall, James Linas. An introduction to Multisensor Data Fusion. Proceeding of the IEEE. 1997,85(1): 6-23
    [17]赵志刚,陈学诠.遥感图像分类的统计融合方法及性能分析.计算机工程,2000,26(10):136-137
    [18]汤志伟,汪建国,黄顺吉.使用小波分析的图像融合算法.电子科技大学学报,2000,29(2):122-124
    [19]Jason S. McCarley, William K. Krebs. Visibility of road hazards in thermal,
    
    visible, and sensor-fused night-time imagery. Applied Ergonomics 31(2000):523-530
    [20] R.C.Luo,er al.A hierarchical Target Representation for autonomous Recognition Using Distributed Sensors. Proc. SPIE Conf. On Sensor Fusion Ⅲ,1989, 537
    [21] H.F.Durrant-Whyte. Consistent Integration and Propagation of Disparate Sensor Observation. Inter Journal of Robotics Research, 1987,No.6(3): 3-24
    [22] T P Garey, er al. An Inference Technique for Integration Knowledge-from Disparate Source. Proc. The Inter. Joint Conf on Artificial Intelligence, Vancouver, August 1981,319-325
    [23] E L Waltz, D M Buede. Data Fusion and Decision Support for Command and Control. IEEE Trans. On SMC,1986,616:865-879
    [24] Lang Hong,et al. Recursive Temporal-Spatial Information Fusion with Applications to Target Identification. IEEE Trans. On Aerospace and Electronic Systems,1993,29(2): 435-445
    [25] T L Huntsherger, et al. A framework for Multisensor Fusion in the Presence of Uncertainty. Proc. of Workshop on Spatial Reasoning and Multi-sensor Fusion, St. Charles, Ⅰ Ⅲ Ⅰ,Oct,1987, 345-350
    [26] J Llines et al. Dat Fusion Technology forecast for C3MIS.Proc. of the 3rd International Conference on Command, Control, Communications and MIS, Bournemouth, UK, IEE, London, March 1989, 5-18
    [27] Hoel P G, Port S C, Stone C J. Introduction to statistical theory. Houghton Mifflin Comlany, 1971, 43-50
    [28] 何灿芝,吴俊杰.概率论与数理统计.长沙湖南科学技术出版社,1999,33-35
    [29] 苏奕.人工神经网络数据融合方法研究与应用:[浙江大学硕士论文].浙江大学图书馆:浙江大学,2002,35-40
    [30] 李宏,徐晖,安伟等.基于人工神经网络与证据理论相结合地信息融合空间点目标识别方法研究.信息与控制,1997,26(2):151-155
    [31] 敬思良,杨永胜,李建勋等.基于模糊神经网络和D-S推理的智能特征信息融合研究.信息与控制,1997,26(2):107-111
    [32] HAN Jia-wei,MICHELINE KAMBER.数据挖掘:概念与技术.北京:机械工业出版社,2001,3-22
    [33] SCOTT URMAN.Oracle 8 PL/SQL Programming[M].北京:机械工业出版社,1988,14-20
    [34] 黄瑛,陶云刚.D-S证据理论在多传感器数据融合中的应用.计量学报,2000,21(2): 148-152
    
    
    [35]王浩,庄钊文.模糊可靠性分析中的隶属函数确定.电子产品可靠性与环境试验,2000,10(4):2-7
    [36]朱大奇,于盛林.电子电路故障诊断的神经网络数据融合算法.东南大学学报,2001,31(6):87-90
    [37]朱大奇,于盛林.基于D-S证据理论的数据融合算法及其在电路故障诊断中的应用.电子学报,2002,30(2):221-223
    [38]郑金兴,张铭钧,徐建安.电火花切割故障诊断中基于神经网络的数据融合技术.哈尔滨工程大学学报,2001,22(5):48-51
    [39]黎湘,庄钊文,郭桂蓉.模糊自组织神经网络及其在信息融合目标识别中的应用.国防科技大学学报,1997,19(3):12-15
    [40]赵振宇等.模糊理论与神经网络的基础与应用.北京:清华大学出版社,1996,4-120
    [41]胡守仁等.神经网络应用技术.长沙:国防科技大学出版社,1993,130-180
    [42]郁少贤,雍少为,郭桂蓉.多传感器信息融合技术评述.国防工业大学学报,1994,16(3):1-11
    [43]虞和济,陈长征,张省,周建男,基于神经网络的智能诊断,冶金工业出版社,2002,191-200
    [44]周玉芬等:模拟电路故障诊断,国防工业出版社,1989,154
    [45]J.M.Keller, M.R. Gray, and J.A. Givens. A fuzzy k-nn neighbor algorithm. IEEE Trans. Syst. Man Cybern.,1985, SMC-15(4): 580-585
    [46]A. Jozwik. A learning scheme for a fuzzy k-nn rule. Pattern Recognition Letters, 1983, 287-289
    [47]Thierry Denoeux. A Neural Network Classifier Based on Dempster-Shafer Theory. IEEE Transactions on System, Man and Cybernetics, 2000,10(2): 131-150
    [48]T. Denoeux. A k-nearest neighbor classification rule based on Dempster-Shafer theory. IEEE Transctions on System, Man and Cybernetics, 1995,25(05):804-813
    [49]Thierry Denoeux. A Neural Network Classifier Based on Dempster-Shafer Theory. IEEE Transactions on System, Man and Cybernetics, 2000,10(2):131-150
    [50]许东,吴铮.基于MATLAB6.x的系统分析与设计——神经网络(第二版).西安电子科技大学出版社.2002,21-57

© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号

地址:北京市海淀区学院路29号 邮编:100083

电话:办公室:(+86 10)66554848;文献借阅、咨询服务、科技查新:66554700