Research of bus protection based on artificial neural network

Bus is one of the most important parts in power plants and transformer substations. The research on the high-reliability and high-intelligence bus protection will be quite important both in theory and practice. An ANN (artificial neural network) is set up to replace the physical object of bus protection in this paper, which presents a new bus protection method based on approximation ability of function on ANN. Various types of fault results collected in practice are used as sample data. Applying this model, bus protection failures are analyzed and compared in two different improved algorithms of neural networks. And two simulation results are acquired. The result shows that the trained ANN model could not only approximates the normal bus operation precisely and reflects all types of the inner failures but also satisfies precision of protection.