yang xing-lin, wang hua-cen, chen nan, et al. Fault diagnosis and performance evaluation for high current LIA based on radial basis function neural network[J]. High Power Laser and Particle Beams, 2006, 18.
Citation:
yang xing-lin, wang hua-cen, chen nan, et al. Fault diagnosis and performance evaluation for high current LIA based on radial basis function neural network[J]. High Power Laser and Particle Beams, 2006, 18.
yang xing-lin, wang hua-cen, chen nan, et al. Fault diagnosis and performance evaluation for high current LIA based on radial basis function neural network[J]. High Power Laser and Particle Beams, 2006, 18.
Citation:
yang xing-lin, wang hua-cen, chen nan, et al. Fault diagnosis and performance evaluation for high current LIA based on radial basis function neural network[J]. High Power Laser and Particle Beams, 2006, 18.
High current linear induction accelerator(LIA) is a complicated experimental physics device. It is difficult to evaluate and predict its performance. This paper presents a method which combines wavelet packet transform and radial basis function(RBF) neural network to build fault diagnosis and performance evaluation in order to improve reliability of high current LIA. The signal characteristics vectors which are extracted based on energy parameters of wavelet packet transform can well present the temporal and steady features of pulsed power signal, and reduce data dimensions effectively. The fault diagnosis system for accelerating cell and the trend classification system for the beam current based on RBF networks can perform fault diagnosis and evaluation, and provide predictive information
DownLoad: