Variable working condition planetary gearbox sun gear fault diagnosis method based on multi-attribute convolutional neural network

Abstract

The invention discloses a variable working condition planetary gearbox sun gear fault diagnosis method based on a multi-attribute convolutional neural network, and belongs to the technical field of mechanical fault diagnosis. The method comprises the steps of firstly acquiring vibration data of a planetary gearbox of a planetary gearbox sun gear under different fault types, different rotation speeds and different loading working conditions, multiple sample points are created from the vibration data, corresponding multi-attribute labels are endowed with, the multi-attribute convolutional neural network is built and trained, during a test, the multiple data sample points are created from the vibration data of the planetary gearbox to be diagnosed, the trained multi-attribute convolutional neural network is utilized to diagnose test sample points, and variable working condition planetary gearbox sun gear fault diagnosis is completed. The variable working condition planetary gearbox sun gear fault diagnosis method based on the multi-attribute convolutional neural network can automatically extract characteristics and is high in accuracy and high in generalization performance, the method is simple and easy to understand, fault diagnosis under variable conditions can be achieved, the rotation speeds can be predicated simultaneously, and the method is simple in engineering popularization.

Description

Technical field: [0001] The invention belongs to the technical field of mechanical fault diagnosis, and in particular relates to a method for diagnosing sun gear faults of a planetary gearbox with variable working conditions based on a multi-attribute convolutional neural network. Background technique: [0002] Planetary gearboxes have many advantages such as light weight, small size, large transmission ratio, strong bearing capacity, and high transmission efficiency, so they have been widely used in wind power, aviation, ships, metallurgy, petrochemicals, mining, cranes and other industries. Machinery drivetrain. Planetary gearboxes usually work in the harsh environment of low speed and heavy load, and the speed and load fluctuate to a certain extent. Therefore, serious wear and fatigue cracks of key components such as sun gear, planetary gear, ring gear and planet carrier occur from time to time. Once these large and complex mechanical equipment fails, the direct and indi...

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to provide a method for diagnosing sun gear faults of planetary gearboxes under variable working conditions based on multi-attribute convolutional neural networks, so as to solve the problem of the poor diagnostic effect of traditional sun gear fault diagnosis methods of planetary gearboxes and the inability to realize diagnosis under variable working conditions. , a technical problem that is difficult to use in practice

Images