No abstract

Abstract:In electric power systems, there are always power quality disturbances (PQDs). Usually, noise contamination interferes with their detection and classification. Common methods perform frequency or time-frequency analyses on the power distribution signal for detecting and classifying a limited number of PQDs with some difficulties at low signal-to-noise ratio (SNR). In this regard, recently proposed methodologies for PQD detection estimate several parameters and apply distinct signal processing techniques to improve the detection of PQD. In this work, a novel methodology that merges empirical mode decomposition (EMD), the moments of a random variable, and an artificial neural network (ANN) is proposed for detecting and classifying different PQD. The proposed method estimates skewness, kurtosis, and Shannon entropy from the EMD of one-phase voltage/current signal. Then, an ANN is in charge of classifying the input signal into one of nine different classes for PQD, receiving these parameters as inputs. The effectiveness of the proposed method was verified through computer simulations and experimentation with real data. Obtained results demonstrate its high effectiveness reaching an outstanding 100% of accuracy in detecting and classifying all treated PQD through a few number of parameters, outperforming most of previously proposed approaches.

No abstract

No abstract

Induction motors (IM) are susceptible to mechanical failures with severe consequences for production lines; hence, detection and classification of IM faults have been of great interest for researchers in last years. Broken rotor bars (BRB) are one of the most difficult faults to detect, since this fault does not give any indication of deterioration increasing significantly the production costs; hence, it is quite important to detect them in early states. Several methodologies have been proposed to extract information about the motor condition relying on motor-current-signature analysis (MCSA); however, they usually require highcomputational-complexity algorithms to reach trustworthy result. In this work, a novel methodology for early detection and classification of BRB faults in IM is proposed. This methodology consists of obtaining two spectrograms using fixed-width windows, which are segmented through Otsu algorithm to visualize the time evolution of fault frequencies. The fault severity classification is performed through Kurtosis computation from non-stationary components. Obtained results from real experimentation validate the proposed-method high efficiency, reaching an overall 100% accuracy on detecting and classifying half, one, two BRBs, and healthy condition.