Interpolation of measured data based on neural network to model overcurrent relays in power systems

This paper presents a new method for the interpolation of industrial measured data to determine the operation times of overcurrent (OC) relays used in a power system. The proposed technique is based on feed forward multilayer perceptron neural network. The proposed method is simple and efficient to store measured data to find unsampled data, especially when the relation between sampled data is not linear and the operation area is unknown. The application of the new method is used to find the operation times of OC relays for various time dial settings (TDS) or time multiplier settings (TMS).