Abstract:
The automatic identification of different electric loads using
the current waveform at the time of switching, is analysed in
this paper. The time variation of the harmonics at the time of
switching is modelled using the Hidden Markov Model with
Gaussian Mixture Models representing the probabilities.
Short Time Fourier Transform (STFT) and Wavelet
Transform (WT) based features are compared at their
optimum configurations. The STFT based feature gave an
accuracy of 97.9% while the WT features provided an
accuracy of 93.75% in a cross fold validation experiment.
