摘要
This paper provides a novel diagnosis technique using multi-scale wavelet transform and Hopfield neural network for soft fault diagnosis in analog electronic circuits. The proposed method extracts the original signals from the output terminals of the circuits under test (CUTs) by a data acquisition board. The actual signals and the ideal signals are decomposed with three layer using wavelet transform. The energy of corresponding wavelet coefficients are calculated as fault feature parameters. The features are encoded and then fed to the Hopfield neural network for fault classification. The numerical experiments about Sallen-Key bandpass filter verify the effectiveness of the proposed method.
- 出版日期2012
- 单位输配电装备及系统安全与新技术国家重点实验室