| 模拟电路故障诊断的小波神经网络方法 |
| |
| 引用本文： | 阳辉,罗琨,何怡刚.模拟电路故障诊断的小波神经网络方法[J].微电子学,2010,40(1). |
| |
| 作者姓名： | 阳辉 罗琨 何怡刚 |
| |
| 作者单位： | 湖南大学,电气与信息工程学院,长沙,410082 |
| |
| 基金项目： | 国家自然科学基金资助项目(50677014,60876022);;高校博士点基金资助项目(20060532002);;国家高技术研究发展(863)计划基金资助项目(2006AA04A104);;湖南省科技计划项目资助(2008Gk2022) |
| |
| 摘 要： | 利用小波和改进型BP神经网络相结合的方法,进行模拟电路故障诊断;通过分析被测电路的冲激响应,来识别电路中的故障元件;用小波对冲激响应信号进行多尺度分解,进行归一化后,提取特征信息作为神经网络的输入而进行分类。该方法减少了神经网络的输入、简化了其结构、并缩短了训练和处理时间。实验仿真结果表明:该方法能准确实现故障定位且准确率高。
|
| 关 键 词： | 模拟电路 故障诊断 小波变换 神经网络 |
Fault Diagnosis of Analog Circuit Based on Wavelet and Neural Network |
| |
| YANG Hui,LUO Kun,HE Yigang.Fault Diagnosis of Analog Circuit Based on Wavelet and Neural Network[J].Microelectronics,2010,40(1). |
| |
| Authors: | YANG Hui LUO Kun HE Yigang |
| |
| Affiliation: | College of Electric and Information Engineering/a>;Hunan University/a>;Changsha 410082/a>;P.R.China |
| |
| Abstract: | Fault diagnosis of analog circuit was accomplished based on improved BP Neural Network (BPNN) combined with wavelet transform.Faulty components were identified by analyzing impulse response of circuit under test.After multi-scale decomposition and normalization of impulse response signal,feature information was extracted and categorized as BPNN input.This method reduces the number of inputs to neural network,simplifies its architecture and minimizes training and processing time.Simulation results showed tha... |
| |
| Keywords: | Analog circuit Fault diagnosis Wavelet transform Neural network |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
|
