Neural network based saturation model for round rotor synchronous generator

This paper presents an artificial neural network (ANN) based technique to model saturation for a round rotor synchronous generator. The effects of excitation level, rotor angle, and real power generation on generator saturation are included in the modeling process. To illustrate the technique, small excitation disturbance tests are conducted on a 7.5 kVA, 240 V, 60 Hz round rotor synchronous generator at various levels of excitation and loading. The small excitation disturbance responses are processed by a recursive maximum likelihood algorithm to yield estimates of mutual inductances L/sub ad/ and L/sub aq/ at each operating condition. By developing a suitable training pattern, variables representative of generator operating condition are mapped to mutual inductances L/sub ad/ and L/sub aq/. The developed models are validated with measurements not used in the training process and with large disturbance responses.