Fault test of networked synchronization control system by the combination of RBF neural network and particle swarm optimization

Networked synchronization control has very high technology level, which includes network technology and synchronization control technology, etc. Fault diagnosis of the devices in networked synchronization control system has a great importance for ensuring the normal operation. The radial basis function neural network with particle swarm optimization algorithm is developed. The combination method of RBF neural network and particle swarm optimization is applied to fault diagnosis of networked synchronization control system. The test results indicate that the combination model of RBF neural network and particle swarm optimization can almost entirely recognize each state of the device in networked synchronization control system. The diagnostic accuracy of the combination model of RBF neural network and particle swarm optimization is greater than that of normal RBF neural network.