Open AccessAnalogue circuit fault diagnosis based on convolution neural network
Author(s) -
Du Tao,
Zhang Hao,
Wang Ling
Publication year - 2019
Publication title -
electronics letters
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.375
H-Index - 146
eISSN - 1350-911X
pISSN - 0013-5194
DOI - 10.1049/el.2019.2892
Subject(s) - fault (geology) , convolutional neural network , stuck at fault , convolution (computer science) , computer science , process (computing) , artificial neural network , fault indicator , feature extraction , pattern recognition (psychology) , fault detection and isolation , engineering , electronic engineering , artificial intelligence , seismology , geology , actuator , operating system
In order to simplify the process of analogue circuit fault diagnosis under the premise of improving the fault diagnosis rate of analogue circuit, and to deeply mine the fault characteristics of the output signal, a fault diagnosis method based on convolutional neural network (CNN) is proposed. The output signals in different fault states are directly input into CNN for fault feature extraction and fault classification. By optimising the CNN model and its parameters, the 100% fault diagnosis rate of Sallen‐Key circuit can be achieved. The experimental results indicate that the CNN‐based analogue circuit fault diagnosis method simplifies the fault diagnosis process and improves the fault diagnosis rate.