Intelligent fault diagnosis method and system of unbalanced rolling bearings, equipment and application

Abstract

The invention belongs to the technical field of intelligent fault diagnosis of mechanical equipment, and discloses an intelligent fault diagnosis method and system for unbalanced rolling bearings, equipment and application. The method comprises the steps of: collecting a vibration signal of a rolling bearing, carrying out Zscore standardization on an original signal, and carrying out segmentation on the signal through a moving time window; constructing a conditional generative adversarial network CGAN in which a generator and a discriminator are combined; for the established conditional generative adversarial network, carrying out network parameter optimization in a cyclic adversarial training mode until training is finished, enabling a generator directionally to generate samples of a category with a small data volume to carry out training set data enhancement, thereby relieving the category imbalance phenomenon of an original data set; constructing a fault diagnosis model based on a deep convolutional neural network; and training the established fault diagnosis model by using the CGAN optimized training data set to realize intelligent diagnosis of unknown label samples. With the intelligent fault diagnosis method and system of the unbalanced rolling bearings, the equipment and the application of the invention adopted, the reliability of rolling bearing state recognition can be enhanced, cost low, simplicity and high practicability are realized.

Description

technical field [0001] The invention belongs to the technical field of intelligent fault diagnosis of mechanical equipment, and in particular relates to an intelligent fault diagnosis method, system, equipment and application of a kind of unbalanced rolling bearing. Background technique [0002] At present: Rolling bearings are one of the basic components of mechanical equipment, an important part of mechanical transmission systems, and an indispensable part of modern industrial equipment. The operating status and health of rolling bearings directly affect the normal operation of mechanical equipment and enterprises. safe production. The failure of rolling bearings may lead to the collapse of the entire transmission system, resulting in unpredictable economic losses and even personal injuries. Therefore, it is of great significance to the safe production and cost saving of enterprises to study effective fault diagnosis methods for rolling bearings, arrange and formulate mai...

AI Technical Summary

Problems solved by technology

[0005] (1) The existing intelligent diagnosis methods based on vibration signals are highly dependent on high-quality data sets, which limits their industrial application capabilities

[0006] (2) The normal data monitored by the existing intelligent diagnosis model is far more than the fault data, resulting in the category imbalance of the data set, which leads to the poor recognition effect of the intelligent diagnosis model on small categories (such as faults), which limits its Generalization

Although the traditional up-sampling and down-sampling methods can superficially achieve the effect of class balance, the redundancy or information attenuation caused by it will limit the training effect of the intelligent diagnosis model; the data enhancement method based on adding noise cannot guarantee the consistency of the expanded data will also limit the effect of the model

Images