Key points are not available for this paper at this time.
Based upon the analysis of load signatures, this paper presents a nonintrusive load monitoring (NILM) technique. With a characterizing response associated with a transient energy signature, a reliable and accurate recognition result can be obtained. In this paper, artificial neural networks, in combination with turn-on transient energy analysis, are used to improve recognition accuracy and computational speed of NILM results. To minimize the distortion phenomenon in current measurements from the hysteresis of traditional current transformer (CT) iron cores, a coreless Hall CT is adopted to accurately detect nonsinusoidal waves to improve NILM accuracy. The experimental results indicate that the incorporation of turn-on transient energy algorithm into NILM significantly improve the recognition accuracy and the computational speed.
Chang et al. (Thu,) studied this question.