Gearbox multi-type concurrent fault diagnosis method based on hierarchical machine learning

Abstract

The invention relates to a gearbox multi-type concurrent fault diagnosis method based on hierarchical machine learning, and the method proposes a brand-new hierarchical machine learning model on the basis of traditional machine learning, the model comprises two layers, the first layer is a traditional machine learning model with a simple structure and is used for identifying a single fault type of which the features are easy to distinguish and filtering multi-type concurrent fault samples which cannot be accurately identified to a second layer, and correct classification is carried out by a second layer model. The second layer adopts an extreme learning machine to establish a classification model, the extreme learning machine is a single-layer feedforward neural network, gradient calculation in the negative feedback adjustment process of a traditional neural network is overcome by adopting least square fitting, and adjustment of model parameters can be rapidly achieved. And fault diagnosis is carried out through hierarchical machine learning, so that the accuracy of fault identification can be improved, and the training efficiency can be greatly improved.

Description

technical field [0001] The invention belongs to the field of fault diagnosis of rotating mechanical equipment, in particular to a multi-type concurrent fault diagnosis method for gearboxes based on hierarchical machine learning. Background technique [0002] Gearbox is the most widely used type of rotating mechanical equipment in industrial equipment, especially as an important transmission component, it plays a pivotal role in aviation equipment. The research on gearbox fault diagnosis can improve the reliability of gearbox and ensure the normal operation of equipment. Usually, the operating conditions of rotating machinery are complex, and the performance will gradually degrade during continuous long-term operation, and failures are prone to occur, which may reduce product quality or cause production stoppage, and cause huge property losses and casualties. The gearbox plays a key role in the power transmission and motion conversion process of mechanical equipment, and is ...

AI Technical Summary

Problems solved by technology

[0005] The technical problem solved by the present invention is: In order to avoid the inefficiency of modeling existing in the prior art and the inability to effectively diagnose multiple types of concurrent faults, the present invention proposes a multi-type concurrent fault diagnosis method for gearboxes based on hierarchical machine learning

Images