TY - GEN
T1 - Analog circuits fault diagnosis by GA-RBF neural network and virtual instruments
AU - Li, Xiang
AU - Zhang, Yang
AU - Wang, Shujuan
AU - Zhai, Guofu
PY - 2012
Y1 - 2012
N2 - Analog circuits fault diagnosis is essentially a course of pattern classification. ANN (Artificial Neural Network) has the capability of approaching nonlinear function with any accuracy and can accomplish data's processing and assorting, which makes it an ideal tool for analog circuits diagnosis and other pattern classification problems. In this paper, Genetic Algorithm is used to optimize RBF neural network, which can combine both GA's and ANN's benefits and avoid some specific problems, such as traditional BP neural network's low converge and generating local minimum. On the basis of LabVIEW, the API for analog circuits fault diagnosis is established, simulation experiments are carried out to verify the effectiveness of the method of combing GA-RBF neural network with LabVIEW. Through diagnosis results, it can be seen that the method combining GA-RBF with LabVIEW can not only show the fault diagnosis results visually and directly, but also ensure a considerable diagnosis accuracy.
AB - Analog circuits fault diagnosis is essentially a course of pattern classification. ANN (Artificial Neural Network) has the capability of approaching nonlinear function with any accuracy and can accomplish data's processing and assorting, which makes it an ideal tool for analog circuits diagnosis and other pattern classification problems. In this paper, Genetic Algorithm is used to optimize RBF neural network, which can combine both GA's and ANN's benefits and avoid some specific problems, such as traditional BP neural network's low converge and generating local minimum. On the basis of LabVIEW, the API for analog circuits fault diagnosis is established, simulation experiments are carried out to verify the effectiveness of the method of combing GA-RBF neural network with LabVIEW. Through diagnosis results, it can be seen that the method combining GA-RBF with LabVIEW can not only show the fault diagnosis results visually and directly, but also ensure a considerable diagnosis accuracy.
KW - Genetic Algorithm
KW - LabVIEW
KW - RBF neural network
KW - analog circuits fault diagnosis
UR - https://www.scopus.com/pages/publications/84869219919
U2 - 10.1109/MSNA.2012.6324557
DO - 10.1109/MSNA.2012.6324557
M3 - 会议稿件
AN - SCOPUS:84869219919
SN - 9781467324670
T3 - Proceedings - 2012 International Symposium on Instrumentation and Measurement, Sensor Network and Automation, IMSNA 2012
SP - 236
EP - 239
BT - Proceedings - 2012 International Symposium on Instrumentation and Measurement, Sensor Network and Automation, IMSNA 2012
T2 - 2012 International Symposium on Instrumentation and Measurement, Sensor Network and Automation, IMSNA 2012
Y2 - 25 August 2012 through 28 August 2012
ER -