Regularization sparse filtering method suitable for gear fault diagnosis under variable rotating speed

Abstract

The invention discloses a regularization sparse filtering method suitable for gear fault diagnosis under variable rotating speed, and relates to the field of fault diagnosis of rotating machinery vibration signals. The method comprises the following steps of firstly, obtaining time-varying rotating speed vibration signals of a gear box under different fault types; secondly, establishing a sparse filtering model (L1 / 2-sparse filtering) based on L1 / 2 norm regularization, directly inputting a vibration signal into the model for training, and extracting features; and finally, inputting the extracted features into a Softmax classifier for intelligent diagnosis. According to the regularization method disclosed by the invention, the feature extraction capability of sparse filtering is improved, and the intelligent fault diagnosis of the gear box under the time-varying rotating speed is accurately and reliably realized.

Description

technical field [0001] The invention relates to the field of fault diagnosis of rotating machinery vibration signals, in particular to a regularized sparse filtering method suitable for gear fault diagnosis at variable speeds. Background technique [0002] Mechanical equipment widely used in aerospace, rail transit, engineering vehicles and other fields is evolving towards high speed, automation, multi-function and precision, which makes the structure of mechanical equipment increasingly complex, and the hidden danger of failure continues to rise. The gear is an important mechanism to realize the power transmission and motion conversion of these mechanical equipment, and it is also the main research object of mechanical fault diagnosis. However, most of the traditional fault diagnosis methods are carried out at a constant speed, and there are few researches on the fault diagnosis at a variable speed. The speed of the gears often changes greatly during the working process. F...

AI Technical Summary

Problems solved by technology

However, under variable speed conditions, the mapping between signals and fault types is no longer so simple, which brings severe challenges to mechanical fault diagnosis

[0004] To sum up, the vibration signal generated by the gear at variable speed is an extremely complex non-stationary signal, which not only makes the traditional fault diagnosis method unable to deal with the frequency modulation phenomenon and statistical characteristic parameters between samples under the same health condition changes, but also reduces the generalization ability of many popular data-driven models

Images