基于遗传算法和神经网络的模拟电路故障诊断理论与方法
|
摘要
模拟电路故障诊断的研究经过二十多年的发展，已经形成一系列诊断理论和方法，但由于其本身理论的复杂以及目前诊断方法的实用性不强使得应用前景和人们的期望差距甚远。人工神经网络理论近年来得到了快速发展，已开始在各个领域广泛应用。随着微电子技术尤其是数模混合电路和VLSI技术的发展，对具有容差的模拟电路的测试和故障诊断的需求日益迫切。
本文主要研究了容差模拟电路故障诊断的神经网络方法，在此基础上提出了一些改进的神经网络方法，主要目的是减少诊断时间和提高容差模拟电路的诊断正确率。
本文基于误差后向传播神经网络(BP)的改进算法提出了一些新的故障诊断方法，这些改进算法是将不同的优化算法与BP算法结合起来，不仅考虑了误差在曲面上变化趋势的影响，而且保证网络总是以最适当的学习速率学习。神经网络的联想、记忆和推理功能以及容错性、鲁棒性和很好的非线性映射能力，使这一诊断方法明显优于传统的故障字典法。
本文将模糊逻辑和遗传算法融入前向人工神经网络，提出了一种非线性模拟系统的故障辨识方法，构造了一个基于模糊加权型推理法的模糊神经网络，利用遗传算法来训练网络连接权值、优化隶属度函数，根据训练后的网络权值可以自动提取出模糊规则，并通过仿真实验验证了该方法的有效性。
本文对大规模模拟电路的网络撕裂算法进行了深入的研究，提出了一些改进的大规模模拟电路子网络级多级诊断算法。这种算法讨论了在网络含有线性或非线性子网络的情况下不可及撕裂节点电压的计算。本文通过对大规模模拟电路的仿真表明，本文所提出的改进方法具有良好的诊断效果和可行性。
For several decades, fault diagnosis of analog circuits, the forefront of modern circuit theory, has a series of diagnosis theory and methods. However, complicated theory and poor practicability of these methods make these methods' application foreground far from expectation of people. Artifical Neural Networks(ANN) have gained quick development and have been widely applied in many areas recently. With the development of micro-electronics technology especially mixed-signal circuits and VLSI technology, test and fault diagnosis technology of large-scale analog circuits with tolerances are increasingly important and imminent.
This paper mainly researches ANN based methods for fault diagnosis of analog circuits with tolerances and presents some improved ANN based methods which can decrease diagnosis time and enhance diagnosis efficiency for analog circuits with tolerances.
This paper presents some new fault diagnosis methods on the basis of improved error back propogation Neural Network (BP). The algorithm considers not only the impact of change trend of error, but also ensures that the network studies at the maximal study speed. Artificial Neural Network has associational and memorial abilities, strong study ability, strong robust and non-linear mapping ability, which make this diagnosis method better than traditional fault dictionary methods in the way of diagnosis effect and diagnosis time.
This paper combines genetic algorithm, fuzzy logic with ANN and presents a fault identification method for non-linear analog systems. In the method, a Fuzzy Neural Network is developed based on the improved fuzzy weighted reasoning method. The training of network weights and optimization of membership functions are conducted employing genetic algorithms. Fuzzy rules can be automatically obtained according to .the weights of the network. The availability of the method are examined by simulated
tests.
This paper deeply researches network decomposition algorithms of large-scale analog circuits and presents some improved multistage decomposition algorithms for diagnosing subnetworks in large-scale analog circuits. This algorithm computes the voltages of inaccessible nodes of decomposition in linear subnetworks or non-linear subnetworks. Simulated tests for large-scale analog circuits show these methods have good diagnosis effect and feasibility.
本文主要研究了容差模拟电路故障诊断的神经网络方法，在此基础上提出了一些改进的神经网络方法，主要目的是减少诊断时间和提高容差模拟电路的诊断正确率。
本文基于误差后向传播神经网络(BP)的改进算法提出了一些新的故障诊断方法，这些改进算法是将不同的优化算法与BP算法结合起来，不仅考虑了误差在曲面上变化趋势的影响，而且保证网络总是以最适当的学习速率学习。神经网络的联想、记忆和推理功能以及容错性、鲁棒性和很好的非线性映射能力，使这一诊断方法明显优于传统的故障字典法。
本文将模糊逻辑和遗传算法融入前向人工神经网络，提出了一种非线性模拟系统的故障辨识方法，构造了一个基于模糊加权型推理法的模糊神经网络，利用遗传算法来训练网络连接权值、优化隶属度函数，根据训练后的网络权值可以自动提取出模糊规则，并通过仿真实验验证了该方法的有效性。
本文对大规模模拟电路的网络撕裂算法进行了深入的研究，提出了一些改进的大规模模拟电路子网络级多级诊断算法。这种算法讨论了在网络含有线性或非线性子网络的情况下不可及撕裂节点电压的计算。本文通过对大规模模拟电路的仿真表明，本文所提出的改进方法具有良好的诊断效果和可行性。
For several decades, fault diagnosis of analog circuits, the forefront of modern circuit theory, has a series of diagnosis theory and methods. However, complicated theory and poor practicability of these methods make these methods' application foreground far from expectation of people. Artifical Neural Networks(ANN) have gained quick development and have been widely applied in many areas recently. With the development of micro-electronics technology especially mixed-signal circuits and VLSI technology, test and fault diagnosis technology of large-scale analog circuits with tolerances are increasingly important and imminent.
This paper mainly researches ANN based methods for fault diagnosis of analog circuits with tolerances and presents some improved ANN based methods which can decrease diagnosis time and enhance diagnosis efficiency for analog circuits with tolerances.
This paper presents some new fault diagnosis methods on the basis of improved error back propogation Neural Network (BP). The algorithm considers not only the impact of change trend of error, but also ensures that the network studies at the maximal study speed. Artificial Neural Network has associational and memorial abilities, strong study ability, strong robust and non-linear mapping ability, which make this diagnosis method better than traditional fault dictionary methods in the way of diagnosis effect and diagnosis time.
This paper combines genetic algorithm, fuzzy logic with ANN and presents a fault identification method for non-linear analog systems. In the method, a Fuzzy Neural Network is developed based on the improved fuzzy weighted reasoning method. The training of network weights and optimization of membership functions are conducted employing genetic algorithms. Fuzzy rules can be automatically obtained according to .the weights of the network. The availability of the method are examined by simulated
tests.
This paper deeply researches network decomposition algorithms of large-scale analog circuits and presents some improved multistage decomposition algorithms for diagnosing subnetworks in large-scale analog circuits. This algorithm computes the voltages of inaccessible nodes of decomposition in linear subnetworks or non-linear subnetworks. Simulated tests for large-scale analog circuits show these methods have good diagnosis effect and feasibility.
引文
[1] Berkowitz R S. Condition for Network-element-value Solvability. IRE Trans. Circuits Theory, 1962,15(9): 25-29
[2] J.W.Bandler. Fault Diagnosis of Analog Circuits. Proceedings of the IEEE, 1995,73(8): 1279-1327-
[3] 邹锐．模拟电路故障诊断原理和方法．武汉：华中理工大学出版社，1988， 10-15
[4] OzawaT. Analog Methods for Computer-Aided Circuit AnalysisandDiagnosis. New York: 1988,50-60
[5] 赵国南，郭裕顺．模拟电路故障诊断．哈尔滨：哈尔滨工业大学出版社，1991， 30-35
[6] 吴成禧．模拟电路自动故障诊断评论．国防科技大学学报，1984，12(4)： 38—42
[7] Bandler J W, Salama A E. Recent Advances in Fault Location of In: Proe. IEEE Int. Symp. Circuits and Systems. Canada: 1984,660-663
[8] Duhanel P, Rault J C. Automatic Test Generation Techniques for Analog Circuits and Systems—A Review. IEEE Trans Circuits and Systems, 1979,26(4): 41-44
[9] Wey C L. A Decision Process for Analog System Fault Diagnosis. IEEE Trans. Circuits Syst,1987,34(1): 107-109
[10] Rueywen Liu. Testing and Diagnosis of Analog Circuits and System. New York. 1991,22-30
[11] 孙义闯．模拟电路故障诊断理论与方法综述．大连海运学院学报，1989，15(4)：68-75
[12] 谭阳红，何怡刚．模拟电路故障诊断的新故障字典法．微电子学，2001，31(4)：252-254
[13] F.Aminian, et al. Analog Fault Diagnosis of Actual Circuits Using Neural Networks. IEEE Trans. On Instrumentation and Measurement,2002,51(3): 544-550
[14] 谭阳红，何怡刚．大规模电路故障诊断神经网络方法．湖南大学学报，2001，6(4)：25-28
[15] Somayajula S S. A neural network approach to hierarchical analog fault diagnosis. In: Autotestcon'93. IEEE Systems Readiness Technology
Conference. Proceeding. New York: 1993,699-706
[16] Fanni.A, et al. Neural networks for multiple fault diagnosis in analog circuits. Defect and Fault Tolerance in VLSI Systems, 1993,27(10): 303-310
[17] 焦李成．神经网络的应用与实现．西安：西安电子科技大学出版社，1996，1-10
[18] 杨行峻，郑君里．人工神经网络与盲信号处理．北京：清华大学出版社，2003，1-20
[19] Nielsen R H.Theory of the back propagation neural network. Proc. Of IJCNN, 1989,12(1): 2593-2605
[20] 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，2000，50-70
[21] 丛爽．面向MATLAB工具箱的神经网络理论与应用．合肥：中国科学技术大学出版社，1998，62-73
[22] S Lee and R M Kil. A Gaussian potential function network with hierarchically self-organizing learning. Neural network, 1991,12(4) :207-224
[23] 丛爽．神经网络、模糊系统及其在运动控制中的应用．北京：中国科技大学出版社，2001，21-30
[24] 丛爽，赵何．反向传播网络的不足与改进．自动化博览，1999，12(1)：25-27
[25] Chwan-Chia Wu, et al. Analog Fault Diagnosis with Failure Bounds. IEEE Trans. CAS,1982,29(5): 277-283
[26] 王小平，曹立明．遗传算法—理论、应用与软件实现．西安：西安交通大学出版社，2002，25—40
[27] 唐飞．十进制编码遗传算法的模式定理研究．小型微型计算机系统，2000，21(4)：364-367
[28] 曹先彬．融合神经网络的一种改进遗传算法．模式识别与人工智能，1999，12(4)：486-491
[29] Higgins C M, Goodman R M. Fuzzy rule-based network for control. IEEE Trans. On Fuzzy Systems,1994,2(1): 82-88
[30] 周志坚，毛宗源．模糊神经网络的交叉研究．电路与系统学报，1998，3(3)：81-85
[31] 李映，白本督，焦李成．一种基于模糊神经网络的非线性系统模型辨识方法．电子与信息学报，2002，24(3)：355-360
[32] 崔莼，罗先觉，邱关源．基于模糊规则神经分类器的模拟电路故障诊断法．微电子学，1997，27(1)：32-36
[33] 王鹏宇，黄智刚．模糊理论与神经网络结合对模拟电路进行分层故障诊断．
电子测量技术，2002，12(1)：7—9
[34] C K Ho, et al. Hierarchical Fault Diagnosis of Analog Integrated Circuits.IEEE Trans. CAS-1,2001,48(8): 921-928
[35] 彭敏放，何怡刚．容差电路的K故障屏蔽方法研究．电路与系统学报，2002，7(2)：92-95
[36] 王晖．一种改进的模拟电路K故障诊断算法．深圳大学学报，1997，14(4)：14-18
[37] Salama A E, et al. A Unified decomposition approach for fault location in large analog networks. IEEE trans. CAS,1984,31(7): 609-621
[38] Yuqing Chen. Experiment on Fault Location in Large-Scale Analog Circuits. IEEE Trans. On Instrumentation and Measurement,1993,42(1), 30-34
[39] Radoslaw M B,et al. Multiple-Fault Location of Analog Circuits. IEEE Trans. CAS,1981,28(5): 361-367
[40] T.Ozawa. Diagnosability in the Decomposition Approach for Fault Location in Large Analog Networks.IEEE Trans. CAS,1985,32(4): 415-416
[41] 孙雨耕．大规模模拟电路子网络级故障诊断的改进节点撕裂法．天津大学学报，1997，30(3)：265—273
[42] 陈圣俭．容差模拟电路子网络级故障诊断的新方法．电子测量与仪器学报，1998，12(2)：61-65
[43] 蔡金锭．网络故障交叉撕裂的神经元网络诊断法．小型微型计算机系统，2000，21(7)：700-702
[44] 蔡金锭．大规模网络故障的快速诊断法．电路与系统学报，2001，6(2)：11—14
[45] 罗先觉．大规模模拟电路子网络级多级诊断．电工技术学报，1995，12(4)：64-69
[46] 吴芝路．模拟电路实用故障诊断新方法．电子测量与仪器学报，2000，14(2)：41-45
[47] 罗先觉，范丽娟．模拟电路子网络级的故障定位．西安交通大学学报，1989，23(2)：1-8
[48] M F Abdel Mageed, et al. Fault Detection and Indentification Using a hierarchical neural network-based system. In: Industrial Electronics, control, and Instrumentation,1993. Proceedings of the IECON'93. International Conference. New York: 1993,338-342
[49] K Mohammadi, et al. Fault Diagnosis of Analog Circuits with Tolerances By Using RBF and BP Neural Networks. Student Conference on Research and
Development Proceedings,2002,12(2): 317-321
[50] C K Ho. Hierarchical Fault Diagnosis of Analog Integrated Circuits. IEEE Trans. CAS-1,2001,48(8): 921-928
[51] Huang D Q. Two New Torn-Searched Approaches and its Diagnosability. In: China 1991 International Conference on CAS. Beijing: 1991,501-504
[52] D Q Huang, et al. Topological conditions for fault diagnosability at subnetwork level. In: Circuits and Systems,1990, IEEE International Symposium on. New York: 1990, 2240-2243
[53] M Catelani, A Fort. Soft Fault Detection and Isolation in Analog Circuit: Some Result and a Comparison Between a Fuzzy Approach and Radial Basis Function Network. IEEE Trans. Instrumentation and measurement,2002,51(2): 196-202
[2] J.W.Bandler. Fault Diagnosis of Analog Circuits. Proceedings of the IEEE, 1995,73(8): 1279-1327-
[3] 邹锐．模拟电路故障诊断原理和方法．武汉：华中理工大学出版社，1988， 10-15
[4] OzawaT. Analog Methods for Computer-Aided Circuit AnalysisandDiagnosis. New York: 1988,50-60
[5] 赵国南，郭裕顺．模拟电路故障诊断．哈尔滨：哈尔滨工业大学出版社，1991， 30-35
[6] 吴成禧．模拟电路自动故障诊断评论．国防科技大学学报，1984，12(4)： 38—42
[7] Bandler J W, Salama A E. Recent Advances in Fault Location of In: Proe. IEEE Int. Symp. Circuits and Systems. Canada: 1984,660-663
[8] Duhanel P, Rault J C. Automatic Test Generation Techniques for Analog Circuits and Systems—A Review. IEEE Trans Circuits and Systems, 1979,26(4): 41-44
[9] Wey C L. A Decision Process for Analog System Fault Diagnosis. IEEE Trans. Circuits Syst,1987,34(1): 107-109
[10] Rueywen Liu. Testing and Diagnosis of Analog Circuits and System. New York. 1991,22-30
[11] 孙义闯．模拟电路故障诊断理论与方法综述．大连海运学院学报，1989，15(4)：68-75
[12] 谭阳红，何怡刚．模拟电路故障诊断的新故障字典法．微电子学，2001，31(4)：252-254
[13] F.Aminian, et al. Analog Fault Diagnosis of Actual Circuits Using Neural Networks. IEEE Trans. On Instrumentation and Measurement,2002,51(3): 544-550
[14] 谭阳红，何怡刚．大规模电路故障诊断神经网络方法．湖南大学学报，2001，6(4)：25-28
[15] Somayajula S S. A neural network approach to hierarchical analog fault diagnosis. In: Autotestcon'93. IEEE Systems Readiness Technology
Conference. Proceeding. New York: 1993,699-706
[16] Fanni.A, et al. Neural networks for multiple fault diagnosis in analog circuits. Defect and Fault Tolerance in VLSI Systems, 1993,27(10): 303-310
[17] 焦李成．神经网络的应用与实现．西安：西安电子科技大学出版社，1996，1-10
[18] 杨行峻，郑君里．人工神经网络与盲信号处理．北京：清华大学出版社，2003，1-20
[19] Nielsen R H.Theory of the back propagation neural network. Proc. Of IJCNN, 1989,12(1): 2593-2605
[20] 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，2000，50-70
[21] 丛爽．面向MATLAB工具箱的神经网络理论与应用．合肥：中国科学技术大学出版社，1998，62-73
[22] S Lee and R M Kil. A Gaussian potential function network with hierarchically self-organizing learning. Neural network, 1991,12(4) :207-224
[23] 丛爽．神经网络、模糊系统及其在运动控制中的应用．北京：中国科技大学出版社，2001，21-30
[24] 丛爽，赵何．反向传播网络的不足与改进．自动化博览，1999，12(1)：25-27
[25] Chwan-Chia Wu, et al. Analog Fault Diagnosis with Failure Bounds. IEEE Trans. CAS,1982,29(5): 277-283
[26] 王小平，曹立明．遗传算法—理论、应用与软件实现．西安：西安交通大学出版社，2002，25—40
[27] 唐飞．十进制编码遗传算法的模式定理研究．小型微型计算机系统，2000，21(4)：364-367
[28] 曹先彬．融合神经网络的一种改进遗传算法．模式识别与人工智能，1999，12(4)：486-491
[29] Higgins C M, Goodman R M. Fuzzy rule-based network for control. IEEE Trans. On Fuzzy Systems,1994,2(1): 82-88
[30] 周志坚，毛宗源．模糊神经网络的交叉研究．电路与系统学报，1998，3(3)：81-85
[31] 李映，白本督，焦李成．一种基于模糊神经网络的非线性系统模型辨识方法．电子与信息学报，2002，24(3)：355-360
[32] 崔莼，罗先觉，邱关源．基于模糊规则神经分类器的模拟电路故障诊断法．微电子学，1997，27(1)：32-36
[33] 王鹏宇，黄智刚．模糊理论与神经网络结合对模拟电路进行分层故障诊断．
电子测量技术，2002，12(1)：7—9
[34] C K Ho, et al. Hierarchical Fault Diagnosis of Analog Integrated Circuits.IEEE Trans. CAS-1,2001,48(8): 921-928
[35] 彭敏放，何怡刚．容差电路的K故障屏蔽方法研究．电路与系统学报，2002，7(2)：92-95
[36] 王晖．一种改进的模拟电路K故障诊断算法．深圳大学学报，1997，14(4)：14-18
[37] Salama A E, et al. A Unified decomposition approach for fault location in large analog networks. IEEE trans. CAS,1984,31(7): 609-621
[38] Yuqing Chen. Experiment on Fault Location in Large-Scale Analog Circuits. IEEE Trans. On Instrumentation and Measurement,1993,42(1), 30-34
[39] Radoslaw M B,et al. Multiple-Fault Location of Analog Circuits. IEEE Trans. CAS,1981,28(5): 361-367
[40] T.Ozawa. Diagnosability in the Decomposition Approach for Fault Location in Large Analog Networks.IEEE Trans. CAS,1985,32(4): 415-416
[41] 孙雨耕．大规模模拟电路子网络级故障诊断的改进节点撕裂法．天津大学学报，1997，30(3)：265—273
[42] 陈圣俭．容差模拟电路子网络级故障诊断的新方法．电子测量与仪器学报，1998，12(2)：61-65
[43] 蔡金锭．网络故障交叉撕裂的神经元网络诊断法．小型微型计算机系统，2000，21(7)：700-702
[44] 蔡金锭．大规模网络故障的快速诊断法．电路与系统学报，2001，6(2)：11—14
[45] 罗先觉．大规模模拟电路子网络级多级诊断．电工技术学报，1995，12(4)：64-69
[46] 吴芝路．模拟电路实用故障诊断新方法．电子测量与仪器学报，2000，14(2)：41-45
[47] 罗先觉，范丽娟．模拟电路子网络级的故障定位．西安交通大学学报，1989，23(2)：1-8
[48] M F Abdel Mageed, et al. Fault Detection and Indentification Using a hierarchical neural network-based system. In: Industrial Electronics, control, and Instrumentation,1993. Proceedings of the IECON'93. International Conference. New York: 1993,338-342
[49] K Mohammadi, et al. Fault Diagnosis of Analog Circuits with Tolerances By Using RBF and BP Neural Networks. Student Conference on Research and
Development Proceedings,2002,12(2): 317-321
[50] C K Ho. Hierarchical Fault Diagnosis of Analog Integrated Circuits. IEEE Trans. CAS-1,2001,48(8): 921-928
[51] Huang D Q. Two New Torn-Searched Approaches and its Diagnosability. In: China 1991 International Conference on CAS. Beijing: 1991,501-504
[52] D Q Huang, et al. Topological conditions for fault diagnosability at subnetwork level. In: Circuits and Systems,1990, IEEE International Symposium on. New York: 1990, 2240-2243
[53] M Catelani, A Fort. Soft Fault Detection and Isolation in Analog Circuit: Some Result and a Comparison Between a Fuzzy Approach and Radial Basis Function Network. IEEE Trans. Instrumentation and measurement,2002,51(2): 196-202
© 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 |