Signal Based Fault Detection and Diagnosis for Rotating Electrical Machines: Issues and Solutions - Complex System Modelling and Control Through Intelligent Soft Computations - page 300

Table 5 Average
classi cation accuracy
of fan end bearing fault
with fault diameter of
0.007 in.

Acquisition time s
0.1 0.2 0.3 0.5 0.7

%

L 1 73.61 82.50 89.43 93.04 94.31

2 74.76 84.11 90.44 95.02 95.15

3 83.08 92.54 94.82 98.49 98.60

4 84.41 91.62 95.37 99.22 99.28

5 84.41 90.73 95.56 98.90 98.76

6 84.41 93.14 96.76 99.39 99.31

time of 0.3 s can be chosen to diagnose effectively this fault. Table 5 shows the
classi

cation accuracy at different wavelet decomposition level L and acquisition
time of faults occurred at fan end bearing with fault diameter of 0.007 in. The
classi 3 and acquisition time higher

0.5 s, so a wavelet decomposition level of 3 and acquisition time of 0.3 s can be
chosen to diagnose effectively this fault.

cation accuracy is over 98 % for level L ¼

6 Summary and Conclusions

This chapter addresses the modelling and diagnosis issues of rotating electrical
machines by signal based solutions. With attention to real systems, two case studies
related to rotating electrical machines are discussed. The first FDD solution uses

PCA in order to reduce the three-phase current space in two dimensions. The PDFs
of PCA-transformed signals are estimated by KDE. PDFs are the models that can be
used to identify each fault. Diagnosis has been carried out using the K

-

L diver-
gence, which measures the difference between two probability distributions. This
divergence is used as a distance between signatures obtained by KDE. The second
FDD solution uses MSPCA, KDE and PCA contributions to identify and diagnose
the faults. Several experimentations on real motors are carried out in order to verify
the effectiveness of the proposed methodologies. The first solution, based on current

signals, has been tested on a motor modelled by FEM and real induction motors in
order to diagnose broken rotor bars, broken connector, cracked and wrong rotor.
The second solution, based on vibration signals, has been tested on a real induction
motors in order to diagnose bearings faults: inner raceway, rolling element (i.e. ball)
and outer raceway faults with different fault severities (i.e. diameter of 0.007 and
0.021 in.). Results show that the signal based solutions are able to model the fault
dynamics and diagnose the motor conditions (i.e. healthy and faulty) and identify
the faults.