基于非高斯性分析的BP神经网络模拟电路故障诊断研究
|
摘要
随着现代电子技术的高速发展,电子设备的结构越来越复杂,其集成度和密集度不断增加,而相应的电路故障诊断技术,尤其是模拟电路故障诊断技术却发展缓慢,制约着设备保障能力的发展与提高。因此,模拟电路故障诊断技术研究具有十分重要的现实意义,从而成为当前电路故障诊断领域的研究热点。
在对当前模拟电路故障诊断领域的研究现状进行归纳总结的基础上,本文采用了基于BP神经网络的模拟电路故障诊断方法。针对该方法诊断模型的建立流程,重点对特征提取算法和BP神经网络优化算法进行了深入研究和探讨,提出了基于非高斯性分析的特征提取算法和改进的GA—BP神经网络算法,主要工作包括:
1.从特征提取、智能故障诊断和BP神经网络优化的角度出发,对现有的各类算法进行了较为系统的总结,综合对比了各类算法的性能和优缺点。
2.针对特征提取过程中特征向量维数较高,计算复杂度较大的问题,提出了一种基于非高斯性分析的特征提取算法。该算法利用电路在正常模式及各种故障模式下输出信号偏离高斯信号的不同程度,将信号的峭度、负熵和重心作为特征参数进行特征提取。仿真结果和实际验证表明,该算法故障分辨率高,能有效降低特征向量维数,且计算方法简单,易于实现,具有一定通用性。
3.深入研究了普通的GA—BP神经网络算法,针对其在同时优化BP神经网络结构和初始权值阈值时,存在编码过于冗长,优化性能较差等问题,提出了一种改进的GA—BP神经网络算法。该算法对原有算法的编码方式和适应度计算方法进行了优化,有效缩短了编码长度。仿真结果和实际验证表明,该算法有效提高了BP神经网络的设计效率、收敛成功率及网络的性能。
4.针对实际设备中的较大规模电路,设计了基于故障二叉树和BP神经网络的TPS开发方法,编写了相应的用户开发界面。最后结合XX自动测试诊断系统,将本文算法在WJ8615P超短波接收机的TPS开发中予以实现。实际测试结果达到了预期的要求,进一步验证了本文所提算法的可行性与有效性。
With the developing of modern electronic technology, the electronic equipment's structure becomes more and more complicated, and its integration and density is also increasing continuously. But the corresponding technology of fault diagnosis of circuits, especially that of analog circuits is developing slowly, which restricts the maintainability of equipments. Therefore, it is of great significance to study the fault diagnosis technology of analog circuits, which has become a hotspot in the fault diagnosis field of circuits nowadays.
After summarizing the current technologies of fault diagnosis of analog circuits, this thesis adopts BP neural network algorithm. This paper makes a study of the feature extraction algorithm and the optimizition algorithm of BP neural network, which both are critical sections in the fault diagnosis procedure. This thesis proposes a feature extraction algorithm based on the non-gaussianity analysis and an optimized algorithm of GA-BP neural network. The main work is as follows:
1 This paper summarizes the current algorithms in the field of feature extraction, fault diagnosis using artificial intelligence and the optimization of BP neural network, the credits and infects of all those technologies above are also illustrated.
2 A feature extraction algorithm based on the non-gaussianity analysis is proposed. It can overcome the problem of large dimension and high computing complexity, which exist in the current algorithms of feature extraction. This algorithm selects the centroid, the kurtosis and engentropy of the signal as the features. The last two features reflect the deviations between a gauss signal and signals sampled in the normal mode and various faulty modes of the circuit. According to the outcome of simulations and actual experiments, this algorithm has the advantage of high definition, low feature dimension and computing simplicity. It is also easy to realize and has generality to some extent.
3 The normal GA-BP algorithm has the disadvantages of long codes and poor optimization performance. This thesis puts forward an improved GA-BP algorithm. The methods of coding and fitness computing are optimized to have a short coding length. According to the outcome of simulations and actual experiments, this algorithm can achieve a better designing efficiency, a higher ratio of convergence and a better performance of network.
4 A developing method of TPS based on fault binary tree and BP neural network is designed to cope with the larger scale circuits in the equipment. The corresponding developing interface for users is also provided. Finally, the algorithms of this thesis are applied to an ATS to develop the TPS of WJ8615P, which is a VHF receiver. The results of experiment achieve the anticipated performance, proving the feasibility and effectiveness of the algorithms proposed in this paper.
在对当前模拟电路故障诊断领域的研究现状进行归纳总结的基础上,本文采用了基于BP神经网络的模拟电路故障诊断方法。针对该方法诊断模型的建立流程,重点对特征提取算法和BP神经网络优化算法进行了深入研究和探讨,提出了基于非高斯性分析的特征提取算法和改进的GA—BP神经网络算法,主要工作包括:
1.从特征提取、智能故障诊断和BP神经网络优化的角度出发,对现有的各类算法进行了较为系统的总结,综合对比了各类算法的性能和优缺点。
2.针对特征提取过程中特征向量维数较高,计算复杂度较大的问题,提出了一种基于非高斯性分析的特征提取算法。该算法利用电路在正常模式及各种故障模式下输出信号偏离高斯信号的不同程度,将信号的峭度、负熵和重心作为特征参数进行特征提取。仿真结果和实际验证表明,该算法故障分辨率高,能有效降低特征向量维数,且计算方法简单,易于实现,具有一定通用性。
3.深入研究了普通的GA—BP神经网络算法,针对其在同时优化BP神经网络结构和初始权值阈值时,存在编码过于冗长,优化性能较差等问题,提出了一种改进的GA—BP神经网络算法。该算法对原有算法的编码方式和适应度计算方法进行了优化,有效缩短了编码长度。仿真结果和实际验证表明,该算法有效提高了BP神经网络的设计效率、收敛成功率及网络的性能。
4.针对实际设备中的较大规模电路,设计了基于故障二叉树和BP神经网络的TPS开发方法,编写了相应的用户开发界面。最后结合XX自动测试诊断系统,将本文算法在WJ8615P超短波接收机的TPS开发中予以实现。实际测试结果达到了预期的要求,进一步验证了本文所提算法的可行性与有效性。
With the developing of modern electronic technology, the electronic equipment's structure becomes more and more complicated, and its integration and density is also increasing continuously. But the corresponding technology of fault diagnosis of circuits, especially that of analog circuits is developing slowly, which restricts the maintainability of equipments. Therefore, it is of great significance to study the fault diagnosis technology of analog circuits, which has become a hotspot in the fault diagnosis field of circuits nowadays.
After summarizing the current technologies of fault diagnosis of analog circuits, this thesis adopts BP neural network algorithm. This paper makes a study of the feature extraction algorithm and the optimizition algorithm of BP neural network, which both are critical sections in the fault diagnosis procedure. This thesis proposes a feature extraction algorithm based on the non-gaussianity analysis and an optimized algorithm of GA-BP neural network. The main work is as follows:
1 This paper summarizes the current algorithms in the field of feature extraction, fault diagnosis using artificial intelligence and the optimization of BP neural network, the credits and infects of all those technologies above are also illustrated.
2 A feature extraction algorithm based on the non-gaussianity analysis is proposed. It can overcome the problem of large dimension and high computing complexity, which exist in the current algorithms of feature extraction. This algorithm selects the centroid, the kurtosis and engentropy of the signal as the features. The last two features reflect the deviations between a gauss signal and signals sampled in the normal mode and various faulty modes of the circuit. According to the outcome of simulations and actual experiments, this algorithm has the advantage of high definition, low feature dimension and computing simplicity. It is also easy to realize and has generality to some extent.
3 The normal GA-BP algorithm has the disadvantages of long codes and poor optimization performance. This thesis puts forward an improved GA-BP algorithm. The methods of coding and fitness computing are optimized to have a short coding length. According to the outcome of simulations and actual experiments, this algorithm can achieve a better designing efficiency, a higher ratio of convergence and a better performance of network.
4 A developing method of TPS based on fault binary tree and BP neural network is designed to cope with the larger scale circuits in the equipment. The corresponding developing interface for users is also provided. Finally, the algorithms of this thesis are applied to an ATS to develop the TPS of WJ8615P, which is a VHF receiver. The results of experiment achieve the anticipated performance, proving the feasibility and effectiveness of the algorithms proposed in this paper.
引文
[1]杨士元.模拟系统故障诊断与可靠性设计[M].北京:清华大学出版社,1993:1.
[2] J.W.Bandler, A.Salama. Fault Diagnosis of Analog Circuits[J]. Proc. IEEE ISCAS, 1985: 1279-1325.
[3] Feng Li, Peng-Yung Woo. Fault Detection for Linear Analog IC-the Method of Short-circuit Admittance Parameters[J]. IEEE Transactions on Circuits and Systems 1: Fundamental Theory and Application, 2002, 49(1): 105-108.
[4] F.Aminian , M.Aminian . Analog Fault Diagnosis of Actual Circuits Using Neural Networks[J].Trans. Instrum. Measur,2002:544-550.
[5]王承,陈光礻禹,谢永乐.基于主元分析与神经网络的模拟电路故障诊断[J].电子测量与仪器学报,2005,19(5):14-17.
[6] J.Wan, X.Li, S.Qin. Kernel-based Nonlinear Feature Extractor and its Application in Electronic Circuit Fault Diagnosis[A]. Proceedings of the 5th World Congress on Intelligent Control and Automation[C], Hangzhou, China, 2004: 1775-1779.
[7] Y.Sun, G.Chen, H.Li. Analog Circuits Fault Diagnosis Using Support Vector Machine[A]. International Conference on Communications, Circuits and Systems[C], Kokura, Japan, 2007: 1003-1006.
[8] W.Su, Y.Su, H.Zhao, et al. Integration of Rough Set and Neural Network for Application of Generator Fault Diagnosis[A]. Proceedings of RSCTC[C], Uppsala, Sweden, 2004: 549-553.
[9] M.Aminian, F.Aminian. Neural-network Based Analog-circuit Fault Diagnosis Using Wavelet Transform as Preprocessor[J]. IEEE Transaction on Circuits and System II: Analog and Digital Signal Processing, 2000, 47(2): 151-156.
[10]谭阳红,叶佳卓.模拟电路故障诊断的小波方法[J].电子与信息学报,2006,28(9):1748-1751.
[11] Y.He, Y.Tan, Y.Sun. Fault Diagnosis of Analog Circuits Based on Wavelet Packets[A]. TENCON 2004 IEEE Region 10 Conference[C], Chiang Mai, Thailand, 2004: 267-270.
[12] A.Wang, J.Liu, et al. Algorithms Comparison of Feature Extraction and Multi-class Classification for Fault Diagnosis of Analog Circuit[A]. Proceedings of 2007 International Conference on Wavelet Analysis and Pattern Recognition[C], Beijing, China, 2007: 566-572.
[13]万九卿,李行善.基于诊断信息量的测点选择方法[J].电子测量与仪器学报,2005,19(5):1-5.
[14]袁海英,陈光礻禹.基于最大故障信息量二元树的模拟电路诊断法[J].仪器仪表学报,2006,27(12):1679-1682.
[15]郭双冰.基于小波和分形理论的调制信号特征提取方法研究[J].信号处理,2005,21(3):316-318.
[16]李伟,李天伟,王桂军,易成涛.分析特征的模拟电路故障诊断[J].中国测试,2010,36(2):14-17.
[17] C.Li, D.Hu. A Fault Diagnosis Expert System Base on Artificial Neural[A]. The Eighth International Conference on Electronic Measurement and Instruments[C], Xian, China, 2007: 3-611-3-614.
[18]李征光.无线通信设备故障诊断专家系统的研究与设计[D].电子科技大学硕士学位论文,2008.
[19] R.Spina, S.Upadhyaya. Linear Circuit Fault Diagnosis Using Neuromorphic Analyzers[J]. IEEE Trans. Circuits Syst. II, Analog Digit. Signal Process., 1997, 44(3): 188-196.
[20] Y.He, Y.Deng, Y.Sun. Fault Diagnosis of Analog Circuits with Tolerances Using Artificial Neural Networks[A]. Proc. IEEE APCCAS[C], Tianjin, China, 2000: 292-295.
[21] F.Aminian , M.Aminian . Analog Fault Diagnosis of Actual Circuits Using Neural Networks[J].Trans. Instrum. Measur,2002:544-550.
[22] S.Yin, G.Chen, Y.Xie. Wavelet Neural Network Based Fault Diagnosis in Nonlinear Analog Circuits[J]. J.Syst.Eng.Electron., 2006, 17(3): 521-526.
[23] Yan X. A Reviews of Evolutionary Artificial Neural Networks[J]. International Journal of Intelligent Systems, 1993, 8: 539～567.
[24]杨立儒.基于神经网络的电路故障诊断的研究与实现[D].信息工程大学硕士学位论文,2010.
[25] W.Li, D.Wang, N.Ding. Research on BP Neural Network Optimal Method Based on Improved Ant Colony Algorithm[A]. Second International Conference on Computer Engineering and Applications[C], Bali Island, Indonesia, 2010: 117-121.
[26]何尔利,翟正军.基于退火BP神经网络的模拟电路故障诊断方法[J].计算机测量与控制,2010,18(1):67-69.
[27]唐磊.BP网络结构确定算法的研究及仿真[D].中国石油大学硕士学位论文,2008.
[28]韩宝如.模拟电路故障诊断的小波与模糊神经网络方法研究[D].燕山大学硕士学位论文,2007.
[29]高泽涵.电子电路故障诊断技术[M].西安:西安电子科技大学出版社,2000:8-12.
[30]张贤达.现代信号处理(第二版)[M].北京:清华大学出版社,2004:281-282.
[31] Aapo Hyvarinen, Juha Karhunen, Erkki Oja著.周宗潭等译.独立成分分析[M].北京:电子工业出版社, 2007: 25-28.
[32]周成光.概率密度分析法评判往复泵的故障状态[J].声学技术,2003,z2:423-426.
[33] T.Deliyannis, Y.Sun, J.K.Fidler. Continuous-Time Active Filter Design[J]. Boca Raton, FL: CRC Press, 1999: 69-73.
[34]从宏寿,李绍铭.电子设计自动化—Multisim在电子电路与单片机中的应用[M].北京:清华大学出版社,2008:99-101.
[35] Z.Yao, J.Jia. L,Ni, Y.Tan, X,He. The Largest Amount of Fault Information in Analog Circuit Fault Diagnosis Based on Multisim Circuit Simulation[A]. International Conference onMeasuring Technology and Mechatronics Automation[C], Changsha, China, 2010: 893-895.
[36]葛哲学,孙志强.神经网络理论与MATALAB 2007实现[M].北京:电子工业出版社,2007:46-55.
[37] Ashouri M. R. Fault Detection of Analog Circuits Using Neural Networks and MonteCarlo Analysis[J]. IEEE Proceedings of MWSCAS, 2001, 2: 700~704.
[38]李瀚荪.电路分析基础(第三版)(中册)[M].北京:高等教育出版社,2004:127-151.
[39]王志刚.现代电子线路(上册)[M].北京:北方交通大学出版社,2003:307-315.
[40]高隽.人工神经网络原理及仿真实例[M].北京:机械工业出版社,2007:45-53.
[41] Patton R J. Fault Diagnosis in Nonlinear Dynamic Systems via Neural Networks[J], IEEE Conference Publication, 1994: 21-24.
[42]王雪.测试智能信息处理[M].北京:清华大学出版社,2008:91-93.
[43] Liang Gechao, He Yigang. A Fault Identification Approach for Analog Circuits Using Fuzzy Neural Network Mixed with Genetic Algorithms[J]. IEEE Proc. Intelligent Systems and Signal Processing, 2003, 2: 1267-1272.
[44]周明,孙树栋.遗传算法原理及应用[M].北京:国防工业出版社,1999:32-54.
[45]杨梅,卿晓霞,王波.基于改进遗传算法的神经网络优化方法[J].计算机仿真,2009,5:198-201.
[46]刘美容,何仪刚,方葛丰,尹新,齐绍忠.遗传小波神经网络在模拟电路故障诊断中的应用[J].湖南大学学报,2009,3:40-44.
[47] Z.米凯利维茨著,周家驹,何险峰译.演化程序—遗传算法和数据编码的结合[M].北京:科学出版社,2000:73-79.
[48]王小平,曹立明.遗传算法—理论、应用与软件实现[M].西安:西安交通大学出版社,2002:30-49.
[49]张志涌等.精通MATALAB 6.5版[M].北京:北京航空航天大学出版社,2003:468-495.
[50]吴昊等.Matlab与Pspice的数据接口技术[J].电气电子教学学报,2005:33-35.
[2] J.W.Bandler, A.Salama. Fault Diagnosis of Analog Circuits[J]. Proc. IEEE ISCAS, 1985: 1279-1325.
[3] Feng Li, Peng-Yung Woo. Fault Detection for Linear Analog IC-the Method of Short-circuit Admittance Parameters[J]. IEEE Transactions on Circuits and Systems 1: Fundamental Theory and Application, 2002, 49(1): 105-108.
[4] F.Aminian , M.Aminian . Analog Fault Diagnosis of Actual Circuits Using Neural Networks[J].Trans. Instrum. Measur,2002:544-550.
[5]王承,陈光礻禹,谢永乐.基于主元分析与神经网络的模拟电路故障诊断[J].电子测量与仪器学报,2005,19(5):14-17.
[6] J.Wan, X.Li, S.Qin. Kernel-based Nonlinear Feature Extractor and its Application in Electronic Circuit Fault Diagnosis[A]. Proceedings of the 5th World Congress on Intelligent Control and Automation[C], Hangzhou, China, 2004: 1775-1779.
[7] Y.Sun, G.Chen, H.Li. Analog Circuits Fault Diagnosis Using Support Vector Machine[A]. International Conference on Communications, Circuits and Systems[C], Kokura, Japan, 2007: 1003-1006.
[8] W.Su, Y.Su, H.Zhao, et al. Integration of Rough Set and Neural Network for Application of Generator Fault Diagnosis[A]. Proceedings of RSCTC[C], Uppsala, Sweden, 2004: 549-553.
[9] M.Aminian, F.Aminian. Neural-network Based Analog-circuit Fault Diagnosis Using Wavelet Transform as Preprocessor[J]. IEEE Transaction on Circuits and System II: Analog and Digital Signal Processing, 2000, 47(2): 151-156.
[10]谭阳红,叶佳卓.模拟电路故障诊断的小波方法[J].电子与信息学报,2006,28(9):1748-1751.
[11] Y.He, Y.Tan, Y.Sun. Fault Diagnosis of Analog Circuits Based on Wavelet Packets[A]. TENCON 2004 IEEE Region 10 Conference[C], Chiang Mai, Thailand, 2004: 267-270.
[12] A.Wang, J.Liu, et al. Algorithms Comparison of Feature Extraction and Multi-class Classification for Fault Diagnosis of Analog Circuit[A]. Proceedings of 2007 International Conference on Wavelet Analysis and Pattern Recognition[C], Beijing, China, 2007: 566-572.
[13]万九卿,李行善.基于诊断信息量的测点选择方法[J].电子测量与仪器学报,2005,19(5):1-5.
[14]袁海英,陈光礻禹.基于最大故障信息量二元树的模拟电路诊断法[J].仪器仪表学报,2006,27(12):1679-1682.
[15]郭双冰.基于小波和分形理论的调制信号特征提取方法研究[J].信号处理,2005,21(3):316-318.
[16]李伟,李天伟,王桂军,易成涛.分析特征的模拟电路故障诊断[J].中国测试,2010,36(2):14-17.
[17] C.Li, D.Hu. A Fault Diagnosis Expert System Base on Artificial Neural[A]. The Eighth International Conference on Electronic Measurement and Instruments[C], Xian, China, 2007: 3-611-3-614.
[18]李征光.无线通信设备故障诊断专家系统的研究与设计[D].电子科技大学硕士学位论文,2008.
[19] R.Spina, S.Upadhyaya. Linear Circuit Fault Diagnosis Using Neuromorphic Analyzers[J]. IEEE Trans. Circuits Syst. II, Analog Digit. Signal Process., 1997, 44(3): 188-196.
[20] Y.He, Y.Deng, Y.Sun. Fault Diagnosis of Analog Circuits with Tolerances Using Artificial Neural Networks[A]. Proc. IEEE APCCAS[C], Tianjin, China, 2000: 292-295.
[21] F.Aminian , M.Aminian . Analog Fault Diagnosis of Actual Circuits Using Neural Networks[J].Trans. Instrum. Measur,2002:544-550.
[22] S.Yin, G.Chen, Y.Xie. Wavelet Neural Network Based Fault Diagnosis in Nonlinear Analog Circuits[J]. J.Syst.Eng.Electron., 2006, 17(3): 521-526.
[23] Yan X. A Reviews of Evolutionary Artificial Neural Networks[J]. International Journal of Intelligent Systems, 1993, 8: 539～567.
[24]杨立儒.基于神经网络的电路故障诊断的研究与实现[D].信息工程大学硕士学位论文,2010.
[25] W.Li, D.Wang, N.Ding. Research on BP Neural Network Optimal Method Based on Improved Ant Colony Algorithm[A]. Second International Conference on Computer Engineering and Applications[C], Bali Island, Indonesia, 2010: 117-121.
[26]何尔利,翟正军.基于退火BP神经网络的模拟电路故障诊断方法[J].计算机测量与控制,2010,18(1):67-69.
[27]唐磊.BP网络结构确定算法的研究及仿真[D].中国石油大学硕士学位论文,2008.
[28]韩宝如.模拟电路故障诊断的小波与模糊神经网络方法研究[D].燕山大学硕士学位论文,2007.
[29]高泽涵.电子电路故障诊断技术[M].西安:西安电子科技大学出版社,2000:8-12.
[30]张贤达.现代信号处理(第二版)[M].北京:清华大学出版社,2004:281-282.
[31] Aapo Hyvarinen, Juha Karhunen, Erkki Oja著.周宗潭等译.独立成分分析[M].北京:电子工业出版社, 2007: 25-28.
[32]周成光.概率密度分析法评判往复泵的故障状态[J].声学技术,2003,z2:423-426.
[33] T.Deliyannis, Y.Sun, J.K.Fidler. Continuous-Time Active Filter Design[J]. Boca Raton, FL: CRC Press, 1999: 69-73.
[34]从宏寿,李绍铭.电子设计自动化—Multisim在电子电路与单片机中的应用[M].北京:清华大学出版社,2008:99-101.
[35] Z.Yao, J.Jia. L,Ni, Y.Tan, X,He. The Largest Amount of Fault Information in Analog Circuit Fault Diagnosis Based on Multisim Circuit Simulation[A]. International Conference onMeasuring Technology and Mechatronics Automation[C], Changsha, China, 2010: 893-895.
[36]葛哲学,孙志强.神经网络理论与MATALAB 2007实现[M].北京:电子工业出版社,2007:46-55.
[37] Ashouri M. R. Fault Detection of Analog Circuits Using Neural Networks and MonteCarlo Analysis[J]. IEEE Proceedings of MWSCAS, 2001, 2: 700~704.
[38]李瀚荪.电路分析基础(第三版)(中册)[M].北京:高等教育出版社,2004:127-151.
[39]王志刚.现代电子线路(上册)[M].北京:北方交通大学出版社,2003:307-315.
[40]高隽.人工神经网络原理及仿真实例[M].北京:机械工业出版社,2007:45-53.
[41] Patton R J. Fault Diagnosis in Nonlinear Dynamic Systems via Neural Networks[J], IEEE Conference Publication, 1994: 21-24.
[42]王雪.测试智能信息处理[M].北京:清华大学出版社,2008:91-93.
[43] Liang Gechao, He Yigang. A Fault Identification Approach for Analog Circuits Using Fuzzy Neural Network Mixed with Genetic Algorithms[J]. IEEE Proc. Intelligent Systems and Signal Processing, 2003, 2: 1267-1272.
[44]周明,孙树栋.遗传算法原理及应用[M].北京:国防工业出版社,1999:32-54.
[45]杨梅,卿晓霞,王波.基于改进遗传算法的神经网络优化方法[J].计算机仿真,2009,5:198-201.
[46]刘美容,何仪刚,方葛丰,尹新,齐绍忠.遗传小波神经网络在模拟电路故障诊断中的应用[J].湖南大学学报,2009,3:40-44.
[47] Z.米凯利维茨著,周家驹,何险峰译.演化程序—遗传算法和数据编码的结合[M].北京:科学出版社,2000:73-79.
[48]王小平,曹立明.遗传算法—理论、应用与软件实现[M].西安:西安交通大学出版社,2002:30-49.
[49]张志涌等.精通MATALAB 6.5版[M].北京:北京航空航天大学出版社,2003:468-495.
[50]吴昊等.Matlab与Pspice的数据接口技术[J].电气电子教学学报,2005:33-35.