Information Technology Reference
In-Depth Information
Fig. 5 K
-
L divergence in the case of real motors. The blue dots are the mean, the blue bars are
the four times standard deviation and the red asterisks are the classification output. a Healthy
motor. b Motor with cracked rotor. c Motor with wrong rotor
horizontal edges are the 4 times standard deviation. The
figures show the results
with n
grid
¼
64 points and the acquisition time, for the benchmark and real
motors, equals to 0.3 and 0.7 s respectively. This algorithm parameter setting
guarantees better results for these cases taking into account
64
cation
accuracy and the processing time. In the real motor the algorithm takes about 2.5 s
for the classi
the classi
cation output (Eq.
12
): about 1 s to acquire the current signals, of
which 0.25 s in transient state and 0.7 s in steady-state, and about 1.45 s to evaluate
the PDF and the classi
cation output (Eq.
12
). Setting n
grid
¼
32
32 points, the
processing time is reduced to 1.5 s but decreasing the classi
cation accuracy as
Search WWH ::
Custom Search