Variable-working-condition rolling bearing sectional type fault diagnosis method and system

Abstract

The invention provides a variable-working-condition rolling bearing sectional fault diagnosis method and system, and belongs to the field of bearing fault diagnosis, and the diagnosis method comprises the steps: inputting training data of a known working condition into a transfer learning neural network, taking the minimum total loss of the transfer learning neural network as a benchmark, determining the parameters of the transfer learning neural network, and obtaining the fault of a bearing; completing the training of the transfer learning neural network; inputting a part of known original signals of a to-be-diagnosed working condition capable of representing the working state of the bearing into the transfer learning neural network, and outputting all fault signals of the to-be-diagnosed working condition; two different working conditions are represented in the field, feature information learned from known working conditions is migrated to unknown working conditions, and the problem of insufficient variable working condition data is well solved.

Description

technical field [0001] The invention belongs to the field of bearing fault diagnosis, and more particularly, relates to a segmented fault diagnosis method and system of a rolling bearing with variable working conditions. Background technique [0002] In the industrial production system, as a key component of the mechanical system, rolling bearings play an irreplaceable role. With the long-term operation of machinery and changes in the working environment, the performance of important components gradually deteriorates, resulting in various failures of components. In the long run, it may have a great impact on the overall operating status of the unit, and even lead to serious safety accidents. Therefore, it is of great significance to carry out real-time monitoring and fault diagnosis of the working state of rolling bearings to ensure the safe and reliable operation of the equipment. [0003] The traditional fault diagnosis process is generally divided into four stages: sign...

AI Technical Summary

Problems solved by technology

[0007] In view of the defects of the prior art, the purpose of the present invention is to provide a segmented fault diagnosis method and system for rolling bearings under variable working conditions, aiming to solve the problem that in actual engineering, most of the bearings are in normal working state, and the fault data is very scarce, which leads to the diagnosis The problem of imprecise fault category

Images