|
CLASSIFICATION OF GEAR FAULTS USING HIGHER-ORDER STATISTICS AND SUPPORT
VECTOR MACHINES*
Lai Wuxing Zhang Guicai Shi Tielin Yang Shuzi
School
of Mechanical Science and Engineering, Huazhong University of Science
and Technology,
Wuhan 430074, China
|
Abstract: Gears
alternately mesh and detach in driving process, and then working
conditions of gears are alternately changing, so they are easy
to be spalled and worn. But because of the effect of additive
gaussian measurement noises, the signal-to-noises ratio is low;
their fault features are difficult to extract. This study aims
to propose an approach of gear faults classification, using
the cumulants and support vector machines. The cumulants can
eliminate the additive gaussian noises, boost the
signal-to-noises ratio. Generalisation of support vector
machines as classifier, which is employed structural risk
minimisation principle, is superior to that of conventional
neural networks, which is employed traditional empirical risk
minimisation principle. Support vector machines as the
classifier, and the third and fourth order cumulants as input,
gears faults are successfully recognized. The experimental
results show that the method of fault classification combining
cumulants with support vector machines is very effective.
Key words: Support
vector machine Gear Fault diagnosis Cumulant Feature
extraction
*
This
project is supported by 95 Pandeng Preselect Project (No.PD9521908) and
973 Project (No.G1998020320). Received August 14, 2001; received in
revised form December 20, 2001; accepted April 4, 2002
|