بحث بعنوان Gear Fault Feature Extraction Based on Fuzzy Function and Improved Hu Invariant Moments

بحث بعنوان
Gear Fault Feature Extraction Based on Fuzzy Function and Improved Hu Invariant Moments
Chun Lv , Peilin Zhang , and Dinghai Wu
Department of Vehicle and Electrical Engineering, Army Engineering University, Shijiazhuang 050003, China
This work was supported in part by the National Natural Science Foundation of China (NSFC) under Grant 51305454.
ABSTRACT To intelligently identify gear fault types on the basis of gear vibration signals, due to the nonlinear and non-stationary characteristics of gear vibration signals, a fuzzy function is used to represent the
gear vibration signals in different states as two-dimensional time-frequency images. To solve the problem
that the recognition effect of discontinuity area in the image by traditional Hu invariant moments is not ideal,
improved Hu invariant moments are proposed, and the feature parameters of time-frequency images of gear
vibration signals are extracted based on the improved Hu invariant moments. Different intelligent classifiers
are used to recognize the gear vibration signals in different states. The recognition accuracy is higher by
improved Hu invariant moments than by traditional Hu invariant moments, which shows that the method of
gear fault feature extraction based on a fuzzy function and improved Hu invariant moments is quite ideal,
and can be used in intelligent diagnosis of gear faults.
VI. CONCLUSION
The theory of fuzzy function is studied, and gear vibration
signals are transformed into two-dimensional time-frequency
images (fuzzy domain representations). It is found that the
time-frequency images of gear vibration signals in different
states have obvious differences, which can be used as the
basis of gear fault classification.
Based on the improved Hu invariant moments, seven feature parameters are extracted from the fuzzy domain representations of gear vibration signals. The feature parameters
of the fuzzy domain representation of gear vibration signals
in the same state are nearly the same; the feature parameters
of the fuzzy domain representation of gear vibration signals
in different states are obviously different, which shows that
the extracted feature parameters are effective.
The feature parameters extracted based on the improved
Hu invariant moments are used as the input of intelligent
classifiers. SVM, BPNN, and NBC are used to classify gear
vibration signals in different states. The results are compared
with those based on the traditional Hu invariant moments.
It is found that the recognition accuracy of the three classifiers based on the improved Hu invariant moments is generally higher than that based on the traditional Hu invariant
moments. The gear fault feature parameters extracted based
on fuzzy function and improved Hu invariant moments are
quite ideal and suitable for gear fault diagnosis.
In the future, the parameter optimization of intelligent
classifiers is researched to further improve the accuracy of
gear fault diagnosis.
كلمة سر فك الضغط : books-world.net
The Unzip Password : books-world.net