Electrical energy source with variable speed diesel engine, controlled by using the neural voltage regulator

In this paper, an artificial neural network, which realizes a reference model control idea, has been applied to the control system of a variable speed generating system. The speed is adjusted automatically as a function of the load power demand. The energy balance in the system is achieved by control of the DC-link voltage. The control system is based on an artificial neural network trained on-line. A neural emulator is designed (trained) off-line in order to apply the back propagation learning method. The number of neurons in the network structures as well as characteristic design parameters were specified a priori. The computer test results are presented to show performance of proposed neural controller