RBF neural net for the AIRIX HV generators diagnosis

The AIRIX facility is a high current linear accelerator (2-3.5 kA) used for flash-radiography at the CEA of Moronvilliers (France). The general background of this study is the diagnosis and the predictive maintenance of the AIRIX components. We are interested in the performance of the HV generators, which furnish the energy to accelerate the beam. In the first part, we present a tool for fault diagnosis based on pattern recognition using an artificial neural network. We use an original approach to construct a RBF neural net based classifier. In the second part we briefly describe the experiments carried out to improve the synchronization of the generators to obtain the best acceleration performance. We calculate an absolute time basis to compare the signals of the beam and of the generators to determine the delay to apply to the trigger.