【作者】 尹玉波；

【导师】 韩庆大；

【作者基本信息】 东北大学 ， 机械电子工程， 2008， 硕士

【摘要】 本课题是东北大学设备诊断工程中心与军队针对防化车电路板故障诊断的实际需求,联合研发的一个实际项目的深入研究。模拟电路故障诊断是一个十分必要且有意义的课题。本文把小波神经网络的算法应用在模拟电路故障诊断中,并做了讨论和研究,在模拟电路下对该算法进行了仿真,取得了较好的诊断效果。小波神经网络是小波分析理论与人工神经网络理论结合的产物,它兼容了小波与神经网络的优越性,一方面,充分利用了小波变换的时频局部化特性；另一方面,充分发挥了神经网络的自学习能力,从而具有较强的逼近与容错能力。由于其优越的特性,小波神经网络被广泛用于信号处理、函数拟合、数据预测、系统辨识、故障诊断和自动控制等多个方面。应用LABVIEW及MATLAB软件设计了小波神经网络的故障诊断程序,对进行仿真实验,并与普通的BP网络算法对比,证明了小波神经网络可以并更适合处理防化车模拟电路故障。本文在实际项目的基础上,取得的了一些成果,但还存在一些需要解决的问题及难点,望以后能一一得到解决。更多还原

【Abstract】 This is a practical subject co-developed by Northeastern University Equipment Diagnosis Center and military Region to meet the need of reality.In this paper, an algorithm using wavelet neural network for fault diagnosis in analog circuit witholerance is proposed, and is simulated on the direct circuit and the alternating circuit andreceives better result.Wavelet neural network is the combination of Wavelet Analysistheory and Artificial Neural Networks theory. It not only possesses the wavelet transform’s time-frequency localizationability, but also makes full use of the property of self-learning of Artificial Neural Networks, which enables Wavelet neural network to have better ability of approximation and better fault-tolerance capacity. Because of its particular merits, Wavelet neural network is widely used in many fields, such as signal processing, functionapproximation, data forecast, system identification and patternrec-ognition.At last, corresponding programs are designed for training the general BP neural network and wavelet neural network by MATLAB, LABVIEW and simulation analysis proved that wavelet neuralnetwork is adaptive in complex pattern classifying.In this paper, some results are obtained, but there is also some difference from thepractical application, and it still should be studied in the future.更多还原