Radar Circuit Fault Diagnosis Based on Improved Wavelet Neural Network

Abstract:

In order to improve the diagnosis rate of wavelet neural network algorithm for the radar circuit, for the network during operation there is poor convergence, the training error and shortcomings easy to fall into local minimum, the network is unable to continue training and testing, proposing a new algorithm of increasing the momentum of the wavelet adaptive neural network, can make the network run more stable, faster learning rate; By the Matlab simulation experiments show that the diagnosis rate of the improved algorithm is much higher than the ordinary one.

• Periodical: Applied Mechanics and Materials (Volumes 651-653)
• Pages: 1084-1087
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.651-653.1084
• Online since: September 2014
• Authors: Fang Jun He*, Yong Hai Wang, Gui Qiang Ding, Yue Zhen Fei
• Keywords: Fault Diagnosis, Radar, Wavelet Neural Networks

References

[1] Tan Jie. Based on Wavelet Neural Network Analog Circuits Fault Diagnosis of Research [D]. HuNan University 2008. 5~7.

[2] Q. Zhang. Using Wavelet Network in Nonparametric Estimation[J]. IEEE Trans On Neural Network. 1997, 8(2): 227~236.

DOI: 10.1109/72.557660

[3] Han Baoru. Wavelet and Neural Networks analog circuit fault diagnosis [D]. YanShan University, 2007: 27~56.

[4] Zhang Wei, Shi Yibing. Wavelet neural network classifier based on improved PSO algorithm [J]. Chinese Journal of Scientific Instrument，2010. 10：3~5.

[5] Li Yinjun Zhang Yanbin. Changeable circuit unit modules fault diagnosis based on wavelet neural network [J]. Foreign Electronic Measurement Technology，2010. 8：29~32.