Fault diagnosis of Gear box is one of the core research areas in the
field of condition monitoring of rotating machines. A total of twenty four classes are classified using statistical features of eighth scale
Morlet wavelet coefficients and multiclass proximal support vector
machine is used in further classification of features. An error of
27.541% is obtained in classifying a total of twenty four classes
(given in Table 3) all-at-once. It is found that the classification using
the multiclass proximal support vector machine gives good results
for large classes of data in less time. There exists better result than
obtained one if it is possible to find the better kernel parameters.