ANN based pattern classification of synchronous generator stability and loss of excitation

The paper presents a novel artificial intelligence-based neural network (ANN) pattern classification and online detection scheme for a single machine infinite bus system. The proposed online relay and dynamic pattern classifier utilizes specific frequency spectra of the hyperplane discriminant vector of machine rotor angle, speed, accelerating power, instantaneous power, voltage, and current using either a perceptron single layer detection scheme or a two layer feedforward ANN for online classification and detection of fault condition causing first swing transient stability or loss of excitation. Other relay binary outputs include fault type and allowable clearing time identification. The detection accuracy is improved by utilizing the cross spectra of discriminant vector input variables correlations. The proposed pattern classification technique can be extended to interconnected multimachine power systems by using relative rotor angles, frequency deviations, tie-line powers, and their cross spectra variables