|
|
论文:2013,Vol:31,Issue(1):44-48 |
|
|
引用本文： |
|
|
郭阳明, 冉从宝, 姬昕禹, 马捷中. 基于组合优化BP神经网络的模拟电路故障诊断[J]. 西北工业大学 |
|
|
Guo Yangming, Ran Congbao, Ji Xinyu, Ma Jiezhong. Fault Diagnosis in Analog Circuits Based on Combined-Optimization BP Neural Networks[J]. Northwestern polytechnical university |
|
|
|
|
|
|
|
| 基于组合优化BP神经网络的模拟电路故障诊断 |
|
| 郭阳明, 冉从宝, 姬昕禹, 马捷中 |
|
| 西北工业大学 计算机学院, 陕西 西安 710072 |
| 摘要: |
| 电子系统的可靠性已成为影响系统正常运行的关键,因此电路故障的诊断越来越受到重视。基于BP神经网络的诊断方法是目前实现模拟电路故障诊断的有效方法之一。文章针对已有BP神经网络模拟电路故障诊断技术的不足,提出了一种组合优化的诊断方案。该方案采用遗传算法优化确定BP神经网络的初始权值,以规避BP神经网络易陷入局部极小值的不足,然后应用L-M方法在这个局部解空间里对BP神经网络进行精调,搜索出最优解或者近似最优解。该方案发挥了BP神经网络的广泛映射能力和遗传算法的全局搜索能力,加快了网络的学习速度,综合提高了整个学习过程中的逼近能力和泛化能力,有效提升了基于BP神经网络模拟电路故障诊断的性能。 |
| 关键词:
模拟电路
故障诊断
BP神经网络
遗传算法
L-M方法
|
|
| Fault Diagnosis in Analog Circuits Based on Combined-Optimization BP Neural Networks |
|
| Guo Yangming, Ran Congbao, Ji Xinyu, Ma Jiezhong |
|
| Department of Computer Science and Engineering,Northwestern Polytechnical University,Xi'an 710072,China |
| Abstract: |
| The electronic system's reliability becomes the key of the normal operation of whole system; so circuitfault diagnosis has attracted more and more attention.The method based on BP neural networks is an effective ap-proach of analog circuit fault diagnosis.In this paper, aiming at the drawbacks of fault diagnosis methods based onBP neural networks for analog circuit, a combinatorial optimization diagnosis scheme is proposed.First, the initialweights of BP neural networks are optimized by genetic algorithm(GA) to avoid local minima in the scheme, andthen the BP neural networks is finely tuned with Levenberg-Marquardt (L-M) method in the local solution space tolook for the optimum solution or approximate optimal solutions.The scheme makes good use of the mapping capabil-ities of BP neural networks and the global search ability of GA; it also accelerates the networks’learning speed.Experimental results show preliminarily that the scheme comprehensively improves the whole learning process ap-proximation and generalization ability, and effectively promotes analog circuit fault diagnosis performance based onBP neural networks. |
| Key words:
analog circuits
backpropagation
combinatiorial optimization
genetic algorithms
neural networks;fault diagnosis
Levenberg-Marquardt (L-M)
|
|
| 收稿日期: 2012-04-15
修回日期:
|
| DOI: |
| 基金项目: 国家自然科学基金(61001023、61101004);国家重点基础研究发展计划(973计划);航空科学基金(2010ZD53039);陕西省自然科学基础研究计划(2010JQ8005)资助 |
| 通讯作者:
Email： |
| 作者简介: 郭明阳(1978-)，西北工业大学副教授，主要从事故障诊断、系统可靠性设计等的研究。
|
|
|
|
|
|
|
|
参考文献: |
|
|
[1] 杜 鑫,唐大全,杨应成.模拟电路故障诊断技术的发展.测控技术,2003,(7):1-3,10Du Xin,Tang Daquan,Yang Yingcheng.Development of the Fault Diagnosis Technology of Analogue Circuit.Measurement andControl Technology,2003,(7):1－3,10 (in Chinese)
[2] 韩力群.人工神经网络的理论、 设计及应用.北京:化学工业出版社,2002Han Liqun.Artificial Neural Network Theory,Design and Application.Beijing,Chemical Industry,2002 (in Chinese)
[3] 王 承.基于神经网络的模拟电路故障诊断方法研究: [博士学位论文] .成都: 电子科技大学,2005Wang Cheng.Research of Analog Circuit Fault Diagnosis Method Based on Neural Network.Ph.D.Thesis,Electronic Scienceand Technology University,Chengdu,2005 (in Chinese)
[4] 厉 芸.基于神经网络和遗传算法模拟电路故障诊断方法研究: [硕士学位论文] .长沙: 湖南大学,2005Li Yun.The Research on Fault Diagnosis Methods in the Analog Circuit Based on Neural Network and Genetic Algorithm.Mas-ter Degree Dissertation,Changsha,Hunan University,2005 (in Chinese)
[5] Darrell Whitley.The Genitor Algorithm and Selection Pressure: Why Rank-Based Allocation of Reproductive Trial is Best.Proc3rd Int Conf Genetic Algorithms,1989
[6] 何怡刚,梁戈超.模拟电路故障诊断的 BP 神经网络方法.湖南大学学报(自然科学版),2003,30(5): 35-39He Yigang,Liang Gechao.A Method for Fault Diagnosis of Analog Circuit by BP Neural Network.Journal of Hunan University (Natural Sciences),2003,30(5)35-39 (in Chinese)
[7] 杨士元.模拟系统的故障诊断与可靠性设计.北京:清华大学出版社,1993Yang Shiyuan.Fault Diagnosis and Reliability Design of Simulation System.Beijing,Tsinghua University Press,1993 (in Chi-nese) |
|
|
|
相关文献: |
|
|
1．李伟, 何鹏举, 杨恒, 陈明.基于粗糙集和改进遗传算法优化BP神经网络的算法研究[J]. 西北工业大学, 2012,30(4): 601-606 |
|
|
|
|
|
|
