Rotating part fault diagnosis model construction method and application

Abstract

The invention discloses a rotating part fault diagnosis model construction method and application, and the method comprises the steps: S1, selecting n vibration data segments from collected vibration data of a rotating part in different states as sample signals, and forming a sample set; s2, training a sparse filtering model by adopting the sample set, respectively inputting each sample signal in the sample set into the trained sparse filtering model, and performing activation function processing on an obtained result to obtain learning features of each sample signal; s3, enabling the learning features of the sample signals to be in one-to-one correspondence with the health conditions of the corresponding rotating parts, and forming a training sample set; and S4, inputting the training sample set into a machine learning model for training to obtain a rotating part fault diagnosis model. According to the method, the sparse filtering model is adopted to carry out unsupervised learning on the features, dependence on priori knowledge and manpower is low, only one hyper-parameter needs to be adjusted in the feature learning process, the feature learning effect is good, and the fault diagnosis accuracy is high.

Description

technical field [0001] The invention belongs to the field of fault diagnosis of rotating equipment, and more particularly relates to a method for constructing a fault diagnosis model of a rotating part and its application. Background technique [0002] In modern industry, machines are more automated, precise and efficient than ever before, which can make monitoring their health even more difficult. Among many mechanical equipment, rotating equipment plays a pivotal role in many fields, and once a failure occurs, it will cause huge losses. Rotating components such as rolling bearings and gears are widely used in rotating equipment, and whether they can operate safely and reliably is largely related to the safe use of the entire rotating equipment. [0003] Traditionally, the framework of intelligent fault diagnosis includes three main steps: 1) signal acquisition; 2) feature extraction and selection; 3) fault classification. Traditional fault diagnosis methods are eigenvect...

AI Technical Summary

Problems solved by technology

[0006] In view of the above defects or improvement needs of the prior art, the present invention provides a method for constructing a fault diagnosis model of r

Images