Gearbox incremental fault diagnosis method and system based on lifelong learning

Abstract

The invention discloses a gearbox incremental fault diagnosis method and system based on lifelong learning, and the method comprises the following steps: S101, collecting the vibration data of a gearbox, constructing an incremental health state data set, and dividing the incremental health state data set into fault diagnosis tasks of different stages; s102, using an original ResNet-32 network to learn a fault diagnosis task in an initial stage, and constructing an initial stage diagnosis model; s103, initializing a ResNet-32 double-branch aggregation network by using the initial stage diagnosis model, and increasing the number of neurons of a classification layer according to the number of newly added fault types; s104, jointly training the diagnosis model of the stage through the selected example and the fault diagnosis task data of the stage, and after training is completed, selecting the example of the fault diagnosis task data of the stage; and S105, repeating the steps S103 to S104 in a subsequent increment stage to obtain a final fault diagnosis model, and performing fault diagnosis. The problem that an existing fault diagnosis model based on deep learning and transfer learning cannot diagnose actual accidental faults of the gearbox is solved.

Description

technical field [0001] The invention relates to the technical field of mechanical fault diagnosis, in particular to a method and system for incremental fault diagnosis of a gearbox based on lifelong learning. Background technique [0002] With the rapid development of modern industrialization, the precision and importance of rotating machinery and equipment are getting higher and higher. Rotating machinery equipment has become one of the most widely used industrial machinery equipment, and people's requirements for its reliability are getting higher and higher. Rotating machinery is used in many fields, such as aviation, navigation, machinery, chemical industry, energy, electric power and other fields, and its service conditions are becoming more and more complex, and performance degradation or even failure will inevitably occur during operation, resulting in Huge economic losses lead to higher and higher operation and maintenance costs, and even lead to catastrophic casual...

AI Technical Summary

Problems solved by technology

[0007] The purpose of the present invention is to provide a gearbox incremental fault diagnosis method and system based on lifelong learning to solve the problem that the existing fault diagnosis model based on deep learning and transfer learning cannot diagnose the actual gearbox accidental fault

Images