基于量子神经网络的容差模拟电路的软故障诊断
|
摘要
模拟电路故障诊断一直以来都是十分必要且有意义的,已成为热门的研究课题。传统的模拟电路故障诊断的方法也有很多种,但是它们一般都是用于诊断开路、短路这种硬故障的,难以发现在电路中的各个元器件存在类似器件缺陷或缓慢失效之类的软故障。此外,在很多情况下,一些电路只有一个可测试点,也就是它的输出端,传统的方法根本无法对它们进行有效诊断。而基于神经网络的模拟电路故障诊断方法可以很好地解决这些问题。已用在模拟电路故障诊断中的神经网络主要有BP网络、SOFM网络,以及结合模糊理论的模糊神经网络,结合小波分析的小波神经网络,但是仍然存在问题,例如模糊度如何准确地定量化,对故障信号进行小波变换之后怎样构造能表征故障类别的特征等,都有待进一步研究[1]。
量子神经网络(Quantum Neural Network)简称QNN,因其隐层神经元采用多层激励函数使网络具有了一种固有的模糊性,它能将决策的不确定性数据合理地分配到各模式中,从而减少模式识别的不确定度,提高模式识别的准确性。量子神经网络已成功应用于图像处理、气象预测及语音识别等,但用在模拟电路故障诊断中不多见,本文结合不同的故障提取方法,提出了基于量子神经网络的容差模拟电路的软故障诊断,通过仿真实验,将量子神经网络成功应用到模拟电路的软故障诊断中,并与BP神经网络相比,提高了故障诊断的正确性。
Analog circuit fault diagnosis has been very necessary and meaningful, and it has become a hot topic for research. There are many ways for diagnosing traditional analog circuit fault, but they are mainly used to diagnose hardware faults such as open, short circuits, those soft faults such as similar device defects or gradually invalidation existing in various parts of the circuit are hard to be found. In addition, in many cases, there is only one testing point for some circuits, that is, its output, traditional methods are unable to effectively carry out their diagnosis.The method of analog circuit fault diagnosis based on neural network can solve these problems properly. The neural network used in analog circuit fault diagnosis are BP network, SOFM network, fuzzy neural network combined with fuzzy theory, wavelet neural network combined with wavelet analysis. But there are still problems, such as how to accurately quantify the ambiguity, how to construct features that can show types of the faults after the wavelet transform of fault signal. All of these need further study [1].
Quantum Neural Network, which is simplified as QNN, has a kind of inherent fuzziness because its hidden neurons adopt multi-layer stimulating functions. It can reasonably distribute uncertainty data to every model, Thereby the uncertainty of Pattern Recognition is reduced and the accuracy of pattern recognition is improved. Quantum neural network has been successfully applied to image processing, weather forecasts and voice recognition, but using in analog circuit fault diagnosis is rare. By combining different faults extraction methods, the paper proposes soft fault diagnosis of analog circuit based on quantum neural network, applies quantum neural network successfully to the soft fault diagnosis of analog circuits through the simulation. By comparing with BP neural network, the accuracy of fault diagnosis is improved.
量子神经网络(Quantum Neural Network)简称QNN,因其隐层神经元采用多层激励函数使网络具有了一种固有的模糊性,它能将决策的不确定性数据合理地分配到各模式中,从而减少模式识别的不确定度,提高模式识别的准确性。量子神经网络已成功应用于图像处理、气象预测及语音识别等,但用在模拟电路故障诊断中不多见,本文结合不同的故障提取方法,提出了基于量子神经网络的容差模拟电路的软故障诊断,通过仿真实验,将量子神经网络成功应用到模拟电路的软故障诊断中,并与BP神经网络相比,提高了故障诊断的正确性。
Analog circuit fault diagnosis has been very necessary and meaningful, and it has become a hot topic for research. There are many ways for diagnosing traditional analog circuit fault, but they are mainly used to diagnose hardware faults such as open, short circuits, those soft faults such as similar device defects or gradually invalidation existing in various parts of the circuit are hard to be found. In addition, in many cases, there is only one testing point for some circuits, that is, its output, traditional methods are unable to effectively carry out their diagnosis.The method of analog circuit fault diagnosis based on neural network can solve these problems properly. The neural network used in analog circuit fault diagnosis are BP network, SOFM network, fuzzy neural network combined with fuzzy theory, wavelet neural network combined with wavelet analysis. But there are still problems, such as how to accurately quantify the ambiguity, how to construct features that can show types of the faults after the wavelet transform of fault signal. All of these need further study [1].
Quantum Neural Network, which is simplified as QNN, has a kind of inherent fuzziness because its hidden neurons adopt multi-layer stimulating functions. It can reasonably distribute uncertainty data to every model, Thereby the uncertainty of Pattern Recognition is reduced and the accuracy of pattern recognition is improved. Quantum neural network has been successfully applied to image processing, weather forecasts and voice recognition, but using in analog circuit fault diagnosis is rare. By combining different faults extraction methods, the paper proposes soft fault diagnosis of analog circuit based on quantum neural network, applies quantum neural network successfully to the soft fault diagnosis of analog circuits through the simulation. By comparing with BP neural network, the accuracy of fault diagnosis is improved.
引文
[1]杨士元等.模拟电路软故障的研究[J].微电子学与计算机, 2008, 25(1),1-3
[2] J W Bandler. A Nonlinear L1 Optimization Algonithm for Design Model and Diagnosis of networks. IEEE Trans. CAS.1987,34(2):174-181
[3] Berkowitz R S. Condition for Network-element-value Solvablity. IRE T rans. on Circuit Theory, 1962,15(9):25-29
[4] N Navid and A A Willson. A theory and an Algorithm for Analog Circuit Fault Diagnosis. IEEE Trans. on CAS,1979,26(7):440-457
[5] J W Bandler,et al. Fault Diagnosis of Analog Circuits. Proceedings of the IEEE,1985,73 (8):1279-1327
[6] J H Lee and S D Bedrosian. Fault Isolation Algorithm for Analog Electronic Systems using the Fuzzy Concept. IEEE Trans. On CAS,1979,26(7):518-522
[7] T Ozawa ,M Yamada. Conditions for Determining Parameter Values in a Linear Active Network from Node Voltage Measurements. In: Proceeding of IEEE Int.Symp.CAS,1982,274-277
[8] A E Salama,et al. A Unified Decomposition Approach for Fault Location in Large Analog Networks. IEEE Trans. On CAS,1984,31(7):609-621
[9] Robert Spain, Shambhu Upadhyaya. Linear Circuit Fault Diagnosis Using Neuromorphic Analyzers, IEEE Transaction on Circuits and Systems-II, Analog and Digital Signal Processing, 1997,44(3):188 -196
[10] F Aminian,M Aminian, H.W.Collins . Analog Fault Diagnosis of Actual Circuits Using Neural Networks .IEEE Trans.Instrum.Meas, 2002 , 51(3) :44-550
[11] M Aminian, F Aminian. Neural–network based analog–circuit fault diagnosis using wavelet transform as preprocessor. IEEE Trans.Circuits Syst -II, 2000, 47(2):151-156
[12] Yigang He,Yonghong Tan,Yichuan Sun. Class- based neural network method for fault location of large-scale analogue circuits.(in): Conf. of ISCAS proceedings. Bangkok,Thailand: 2003,V-733-736
[13]谭阳红,何怡刚.模拟电路故障诊断的小波方法[J] .电工技术学报, 2005,20 (8) :89-93
[14] Zhu-Qiang Liu,Francia Yan.Fuzzy neural network in Case-based diagnostic system.IEEE Trans.fuzzy systems,1997,5(2):209-222
[15]彭敏放,何怡刚.容差模拟电路的模糊软故障字典法诊断[J] .湖南大学学报:自然科学版, 2005 ,32 (1) :25- 28
[16]彭刚,彭敏放,何怡刚.基于聚类模糊神经网络的非线性电路故障诊断[J ] .微电子学与计算机, 2006 ,23(8) :1-3
[17]王玲,彭敏放,何怡刚.容差模拟电路故障模糊诊断方法及其实现[J] .微电子学与计算机, 2006 ,23 (4) :189-192
[18]赵华敏,陈开周.解非线性方程组的神经网络方法[J].电子学报, 2002,30(4): 601-604
[19]王虎符,伍远生,杨叔孔.非线性电路的k故障屏蔽[J].电子学报, 1990 ,18 (1) :104-108
[20]谭阳红,基于小波和神经网络的大规模模拟电路故障诊断研究[湖南大学博士论文],2004,75-77
[21]彭羽中,樊锐,刘强.基于人工神经网络的电路故障诊断专家系统[J] .系统工程与电子技术, 2002 , 24(10) :116-119
[22]陈圣俭,洪灿熔,王月芳.可诊断容差模拟电路软故障的新故障字典法[J].电子学报, 2000 ,28 (2) :12
[23]彭敏放,何怡刚,沈美娥,等.基于多目标遗传优化的容差电路故障屏蔽诊断[J] .电工技术学报, 2006 ,21(3) :118-122
[24]谭阳红,何怡刚.模拟电路故障诊断的新故障字典法[J] .微电子学, 2001 ,31 (4) :252-254
[25]何怡刚,梁戈超.模拟电路故障诊断的BP神经网络方法[J].湖南大学学报:自然科学版, 2003,30 (5) :35-39
[26]赵建,林争辉.一种适用于大规模模拟电路多故障定位的方法[J].上海交通大学学报, 1997; 31 (5): 48251
[27] Czaja Z , Zielonko R. Fault diagnosis in electronic circuits based on bilinear transformation in 3D and 4D spaces[J] . IEEE Trans. on Instrumentation and Measurement ,2003 ,52 (1) :97-102
[28] Feng Li , Woo Pengyung. The invariance of node - volt2age sensitivity sequence and its application in a unified fault detection dictionary method [J]. IEEE Trans. On CAS I : Fundamental Theory and Applications , 1999 ,46(10) :1222–1227
[29]汪鹏,杨士元.电压增量的线性相关性及在电路测试中的应用[J] .清华大学学报:自然科学版, 2007 , 47(7) :1245-1248
[30] Hu M, Wang H , Hu G. Soft fault diagnosis for analog circuits based on slope fault feature and BP neural networks[J]. Tsinghua Science and Technology, 2007,12 (S1) :26-31
[31]飞思科技产品研发中心.小波分析理论与Matlab7实现.北京:电子工业出版社,2006.117-120
[32] Gopathy Purushothaman and Nicolaos B.Karayiannis.Quantum Neural Networks(QNN’S):Inherently Fuzzy Feed forward Neural Networks[J],IEEE Transactions on neural networks,1997,682-684
[33] L1 Fei Dong,Xiaoliang Zhao,Shengmei Zheng,Baoyu. A learning algorithm for quantum neural. tCSP’04 Proceedings, 2004, 1538-1541
[34] Zhou J,Gan Q,Krzyzak Aand Suen C Y.Recognition of Handwriten Numerals by Quantum Neural Network with fuzzy featuers. http://www.cenparmi.concodia.ca.2001
[35] Li F,ZhaoS Mand Zheng B Y.Quantum neural network sinspeech re cognition.Proc.of ICSP02, Beijing:,2002,1267-1270
[36]谢涛.基于神经网络和小波变换的模拟电路故障诊断理论与方法.湖南大学硕士学位论文.2007,32-34
[37] Qu Haini, Xu Weisheng, Yu Youling. Design of Neural Network Output Layer in Fault Diagnosis of Analog Circuit. The Eighth International Conference on Electronic Measurement and Instruments.2007,639-641
[38] Anna Wang, Junfang Liu, Jie Wu, Xinhua Zhang.Researches on Soft Fault Diagnosis Algorithm of Analogy Circuits Based on DDAGSVMs. Proceedings of the 2007 IEEE International Conference on Integration Technology. Shenzhen, China.2007,499-502
[39] Yongkui Sun and Guangju Chen.SVM Method for Diagnosing Analog Circuits Fault Based on Testability Analysis. Proceedings of the 2007 IEEE International Conference on Mechatronics and Automation. Harbin, China.2007,3452-3456
[40] Yigang He, Yanghong Tan and Yichuang Sun.Fault Diagnosis of Analog Circuits based on Wavelet Packets. IEEE. 2004,267-270
[41] F Aminian, M Aminian and H W Collins."Analog Fault Diagnosis of Actual Circuits Using Neural Networks", IEEE Trans.Instrum. Meas, Vol.51(3), June 2002, pp544-550
[42] Y He, Y Ding and Y Sun.“Fault diagnosis of analog circuits with tolerances using artificial neural networks,”Proc. IEEE APCCAS, Tianjin, 2000, pp.292-295
[43] Y He,Y Tan,Y Sun. Fault diagnosis of analog circuits based on wavelet packet. [in]Proc.IEEE TENCON .CHANG,2004, 379-384
[44] M Aminian and F Aminian.“Neural–network based analog circuit fault diagnosisusing wavelet transform as preprocessor”, IEEE Trans.Circuits Syst-II, vol. 47(2) ,2000, pp.151-156
[45] Song Guoming,Wang Houjun,Jiang Shuyan and Liu Hong. Fault Diagnosis Approach of Analog Circuits Based on Genetic Wavelet Neural Network. The Eighth International Conference on Electronic Measurement and Instruments. 2007 IEEE,3-675-3-679
[46] KakS.On Quantum Neural Computing.In formation Sciences,Vol.83: 1995,14 3-160
[47] BehrmanE C, Niemel Jand Skinner S R.A Quantum Dot Neural N etwork. Porceedings of the 4th Workshop on Physicsof Computation, 1996,22 -24
[48] Ventura D, Martinez T R. Quantum associative memory. Information Sciences, Vo1.124(1-4),2000,273-296
[2] J W Bandler. A Nonlinear L1 Optimization Algonithm for Design Model and Diagnosis of networks. IEEE Trans. CAS.1987,34(2):174-181
[3] Berkowitz R S. Condition for Network-element-value Solvablity. IRE T rans. on Circuit Theory, 1962,15(9):25-29
[4] N Navid and A A Willson. A theory and an Algorithm for Analog Circuit Fault Diagnosis. IEEE Trans. on CAS,1979,26(7):440-457
[5] J W Bandler,et al. Fault Diagnosis of Analog Circuits. Proceedings of the IEEE,1985,73 (8):1279-1327
[6] J H Lee and S D Bedrosian. Fault Isolation Algorithm for Analog Electronic Systems using the Fuzzy Concept. IEEE Trans. On CAS,1979,26(7):518-522
[7] T Ozawa ,M Yamada. Conditions for Determining Parameter Values in a Linear Active Network from Node Voltage Measurements. In: Proceeding of IEEE Int.Symp.CAS,1982,274-277
[8] A E Salama,et al. A Unified Decomposition Approach for Fault Location in Large Analog Networks. IEEE Trans. On CAS,1984,31(7):609-621
[9] Robert Spain, Shambhu Upadhyaya. Linear Circuit Fault Diagnosis Using Neuromorphic Analyzers, IEEE Transaction on Circuits and Systems-II, Analog and Digital Signal Processing, 1997,44(3):188 -196
[10] F Aminian,M Aminian, H.W.Collins . Analog Fault Diagnosis of Actual Circuits Using Neural Networks .IEEE Trans.Instrum.Meas, 2002 , 51(3) :44-550
[11] M Aminian, F Aminian. Neural–network based analog–circuit fault diagnosis using wavelet transform as preprocessor. IEEE Trans.Circuits Syst -II, 2000, 47(2):151-156
[12] Yigang He,Yonghong Tan,Yichuan Sun. Class- based neural network method for fault location of large-scale analogue circuits.(in): Conf. of ISCAS proceedings. Bangkok,Thailand: 2003,V-733-736
[13]谭阳红,何怡刚.模拟电路故障诊断的小波方法[J] .电工技术学报, 2005,20 (8) :89-93
[14] Zhu-Qiang Liu,Francia Yan.Fuzzy neural network in Case-based diagnostic system.IEEE Trans.fuzzy systems,1997,5(2):209-222
[15]彭敏放,何怡刚.容差模拟电路的模糊软故障字典法诊断[J] .湖南大学学报:自然科学版, 2005 ,32 (1) :25- 28
[16]彭刚,彭敏放,何怡刚.基于聚类模糊神经网络的非线性电路故障诊断[J ] .微电子学与计算机, 2006 ,23(8) :1-3
[17]王玲,彭敏放,何怡刚.容差模拟电路故障模糊诊断方法及其实现[J] .微电子学与计算机, 2006 ,23 (4) :189-192
[18]赵华敏,陈开周.解非线性方程组的神经网络方法[J].电子学报, 2002,30(4): 601-604
[19]王虎符,伍远生,杨叔孔.非线性电路的k故障屏蔽[J].电子学报, 1990 ,18 (1) :104-108
[20]谭阳红,基于小波和神经网络的大规模模拟电路故障诊断研究[湖南大学博士论文],2004,75-77
[21]彭羽中,樊锐,刘强.基于人工神经网络的电路故障诊断专家系统[J] .系统工程与电子技术, 2002 , 24(10) :116-119
[22]陈圣俭,洪灿熔,王月芳.可诊断容差模拟电路软故障的新故障字典法[J].电子学报, 2000 ,28 (2) :12
[23]彭敏放,何怡刚,沈美娥,等.基于多目标遗传优化的容差电路故障屏蔽诊断[J] .电工技术学报, 2006 ,21(3) :118-122
[24]谭阳红,何怡刚.模拟电路故障诊断的新故障字典法[J] .微电子学, 2001 ,31 (4) :252-254
[25]何怡刚,梁戈超.模拟电路故障诊断的BP神经网络方法[J].湖南大学学报:自然科学版, 2003,30 (5) :35-39
[26]赵建,林争辉.一种适用于大规模模拟电路多故障定位的方法[J].上海交通大学学报, 1997; 31 (5): 48251
[27] Czaja Z , Zielonko R. Fault diagnosis in electronic circuits based on bilinear transformation in 3D and 4D spaces[J] . IEEE Trans. on Instrumentation and Measurement ,2003 ,52 (1) :97-102
[28] Feng Li , Woo Pengyung. The invariance of node - volt2age sensitivity sequence and its application in a unified fault detection dictionary method [J]. IEEE Trans. On CAS I : Fundamental Theory and Applications , 1999 ,46(10) :1222–1227
[29]汪鹏,杨士元.电压增量的线性相关性及在电路测试中的应用[J] .清华大学学报:自然科学版, 2007 , 47(7) :1245-1248
[30] Hu M, Wang H , Hu G. Soft fault diagnosis for analog circuits based on slope fault feature and BP neural networks[J]. Tsinghua Science and Technology, 2007,12 (S1) :26-31
[31]飞思科技产品研发中心.小波分析理论与Matlab7实现.北京:电子工业出版社,2006.117-120
[32] Gopathy Purushothaman and Nicolaos B.Karayiannis.Quantum Neural Networks(QNN’S):Inherently Fuzzy Feed forward Neural Networks[J],IEEE Transactions on neural networks,1997,682-684
[33] L1 Fei Dong,Xiaoliang Zhao,Shengmei Zheng,Baoyu. A learning algorithm for quantum neural. tCSP’04 Proceedings, 2004, 1538-1541
[34] Zhou J,Gan Q,Krzyzak Aand Suen C Y.Recognition of Handwriten Numerals by Quantum Neural Network with fuzzy featuers. http://www.cenparmi.concodia.ca.2001
[35] Li F,ZhaoS Mand Zheng B Y.Quantum neural network sinspeech re cognition.Proc.of ICSP02, Beijing:,2002,1267-1270
[36]谢涛.基于神经网络和小波变换的模拟电路故障诊断理论与方法.湖南大学硕士学位论文.2007,32-34
[37] Qu Haini, Xu Weisheng, Yu Youling. Design of Neural Network Output Layer in Fault Diagnosis of Analog Circuit. The Eighth International Conference on Electronic Measurement and Instruments.2007,639-641
[38] Anna Wang, Junfang Liu, Jie Wu, Xinhua Zhang.Researches on Soft Fault Diagnosis Algorithm of Analogy Circuits Based on DDAGSVMs. Proceedings of the 2007 IEEE International Conference on Integration Technology. Shenzhen, China.2007,499-502
[39] Yongkui Sun and Guangju Chen.SVM Method for Diagnosing Analog Circuits Fault Based on Testability Analysis. Proceedings of the 2007 IEEE International Conference on Mechatronics and Automation. Harbin, China.2007,3452-3456
[40] Yigang He, Yanghong Tan and Yichuang Sun.Fault Diagnosis of Analog Circuits based on Wavelet Packets. IEEE. 2004,267-270
[41] F Aminian, M Aminian and H W Collins."Analog Fault Diagnosis of Actual Circuits Using Neural Networks", IEEE Trans.Instrum. Meas, Vol.51(3), June 2002, pp544-550
[42] Y He, Y Ding and Y Sun.“Fault diagnosis of analog circuits with tolerances using artificial neural networks,”Proc. IEEE APCCAS, Tianjin, 2000, pp.292-295
[43] Y He,Y Tan,Y Sun. Fault diagnosis of analog circuits based on wavelet packet. [in]Proc.IEEE TENCON .CHANG,2004, 379-384
[44] M Aminian and F Aminian.“Neural–network based analog circuit fault diagnosisusing wavelet transform as preprocessor”, IEEE Trans.Circuits Syst-II, vol. 47(2) ,2000, pp.151-156
[45] Song Guoming,Wang Houjun,Jiang Shuyan and Liu Hong. Fault Diagnosis Approach of Analog Circuits Based on Genetic Wavelet Neural Network. The Eighth International Conference on Electronic Measurement and Instruments. 2007 IEEE,3-675-3-679
[46] KakS.On Quantum Neural Computing.In formation Sciences,Vol.83: 1995,14 3-160
[47] BehrmanE C, Niemel Jand Skinner S R.A Quantum Dot Neural N etwork. Porceedings of the 4th Workshop on Physicsof Computation, 1996,22 -24
[48] Ventura D, Martinez T R. Quantum associative memory. Information Sciences, Vo1.124(1-4),2000,273-296