F. Filippetti et al., AI TECHNIQUES IN INDUCTION MACHINES DIAGNOSIS INCLUDING THE SPEED RIPPLE EFFECT, IEEE transactions on industry applications, 34(1), 1998, pp. 98-108
Various applications of artificial intelligence (AI) techniques (exper
t systems, neural networks, and fuzzy logic) presented in the literatu
re prove that such technologies are well suited to cope with on line d
iagnostic tasks for induction machines. The features of these techniqu
es and the improvements that they introduce in the diagnostic process
are recalled, showing that, in order to obtain indication on the fault
extent, faulty machine models are still essential, Moreover, bg the m
odels, that must trade off between simulation result effectiveness and
simplicity, it is possibly to overcome crucial points of the diagnosi
s, With reference to rotor electrical faults of induction machines, a
new and simple procedure based on a model which includes tile speed ri
pple effect is developed. This procedure leads to a new diagnostic ind
ex, independent of the machine operating condition and inertia value,
that alloys the implementation of the diagnostic system with a minimum
configuration intelligence.