Gear operation classification method based on Fisher discriminant dictionary learning model

Abstract

The invention discloses a gear operation classification method based on a Fisher discrimination dictionary learning model, and the method comprises the steps: respectively collecting vibration signals of gears in different health states, and dividing the vibration signals into training data and test data which are not overlapped; decomposing the gear vibration signal based on wavelet packet transformation, and calculating the L-kurtosis value of the coefficient of each sub-band after wavelet packet decomposition; selecting a decomposition coefficient corresponding to the sub-band with the L-kurtosis value of the first 25%, and constructing a low-dimensional multi-scale sample YLM; carrying out fisher discrimination dictionary learning on the basis of the low-dimensional multi-scale sample YLM to obtain a structured dictionary D with intra-class representation capability and inter-class discrimination performance; and solving a sparse coding coefficient of the test sample on the dictionary D by adopting an iterative projection method, calculating a reconstruction error of each class corresponding to the test sample, and judging the running state of the gear according to the minimum error.

Description

technical field [0001] The present disclosure belongs to the field of mechanical fault diagnosis, in particular to a gear operation classification method based on a Fisher discriminant dictionary learning model. Background technique [0002] Gears are key components of mechanical systems such as aero-engines and helicopters, and their operating status is directly related to the performance of the entire system. However, due to the complex structure and extreme service environment of the gear transmission system itself, gear failure is one of the main reasons for the failure of rotating machinery, which can lead to catastrophic accidents and huge economic losses. Because sparse representation classification has good data mining ability and clear mathematical statistical significance, it is widely used in the field of mechanical fault diagnosis. FDDL is an effective image classification method with double the classification ability, but there are still some shortcomings when ...

AI Technical Summary

Problems solved by technology

FDDL is an effective image classification method, which has double the classification ability, but there are still some shortcomings when it is directly applied to the gear operation classification, such as the dictionary learning scale is single, the algorithm is not real-time, and the noise points and noise points in the signal are not considered. Outliers, affecting model robustness, etc.

Images