Transform-based fault diagnosis method

Abstract

The invention provides a fault diagnosis method based on Transform, and belongs to the technical field of fault diagnosis. According to the method, multiple layers of Transform Encoder are adopted as a feature extraction module, Dense connection is added between Encoder layers to enhance the model feature multiplexing capability, a Dropout layer is added in front of the feature extraction module to improve the generalization capability of the model, a multi-channel convolutional neural network layer is added to generate a sample matrix, and a full connection layer is adopted to perform fault classification. According to the method, a Transform Encoder structure is adopted and improved, the Transform Encoder structure is applied to fault diagnosis of mechanical equipment, time sequence features and global features between vibration signals in a long time can be well extracted, and a more accurate fault relation is obtained.

Description

technical field [0001] The invention belongs to the field of fault diagnosis, in particular to a fault diagnosis method based on Transformer. Background technique [0002] With the continuous development of modern industry, science and technology, and economy, industry has become an important criterion for measuring a country's comprehensive strength. In modern industrial society, mechanical equipment is an indispensable common component and plays a vital role in industrial production. A large number of mechanical equipment have good stability in the early stage of operation, but the complex working environment and irregular Operational processes affect the safety of industrial equipment, causing mechanical equipment to behave abnormally, and their performance can degrade or even fail over time. The effective maintenance of mechanical equipment is the basic requirement to maintain normal operation. Preventing equipment failures can reduce property losses and avoid serious a...

AI Technical Summary

Problems solved by technology

But these two types of neural networks also have their own shortcomings, and the recurrent neural network and its variants still cannot completely avoid the long-term dependency problem

The local receptive field of the convolutional neural network convolution kernel leads to the need to superimpose a large number of convolutional layers to obtain global information. There are shortcomings such as lack of capturing the relationship between targets, equal processing of all pixels, and lack of pertinence.

Images