In this paper, an approach to detect stator winding short-circuit faults in squirrel-cage induction motors based on Random Forest and Park's Vector is proposed. This is accomplished by scoring the unbalance in the current and voltage waveforms as well as in Park's Vector, both for current and voltage. To score the unbalance in the d-q space, a Principal Component Analysis is applied to Park's Vector and with the first two principal components the eccentricity is calculated, while the first principal component is used to determine the phase in short-circuit. The proposed strategy has been experimentally tested on a special 400-V, 50-Hz, 4-pole, 2.2-kW induction motor with reconfigurable stator windings in which it was possible to emulate different types of inter-turn short-circuits. The results are quite promising, even only using 1-kHz sampling frequency to acquire the current and voltage waveforms in the three phases, and the use of the Fast Fourier Transform is avoided. The developed solution may be used for tele-monitoring of the motor condition and to implement advanced predictive maintenance strategies.
Unlike monotone single-valued functions, multivalued mappings may have zero, one, or (possibly infinitely) many minimal fixed-points. The contribution of this work is twofold. First, we overview and investigate the existence and computation of minimal fixed-points of multivalued mappings, whose domain is a complete lattice and whose range is its power set. Second, we show how these results are applied to a general form of logic programs, where the truth space is a complete lattice. We show that a multivalued operator can be defined whose fixed-points are in one-to-one correspondence with the models of the logic program.