Complex working condition bearing fault diagnosis method based on meta-learning under small sample

Abstract

The invention discloses a complex working condition bearing fault diagnosis method based on meta-learning under a small sample, and the method comprises the steps: obtaining vibration signal data of abearing under different working conditions, and carrying out normalization; converting a vibration signal into a time-frequency image by using short-time Fourier transform; dividing the time-frequency image into a meta-training set, a meta-verification set and a meta-test set according to working condition categories; constructing a meta-learning fault diagnosis model; setting hyper-parameters ofthe meta-learning fault diagnosis model under task distribution of a given working condition; randomly sampling an N-way K-shot fault classification task, supporting a subset and a query subset to respectively carry out internal and external parameter optimization, and completing meta-training and meta-verification; in the meta-verification stage, selecting a diagnosis model with the highest fault recognition rate, carrying out task sampling on meta-test set data, and evaluating performance of a model query subset by supporting a subset fine adjustment model. Rapid and accurate fault diagnosis of a bearing under the new working condition is realized, the dependence of the model on the number of samples is reduced, and the accuracy and intelligence of bearing fault diagnosis are improved.

Description

technical field [0001] The invention belongs to the technical field of bearing fault diagnosis under complex working conditions, and relates to a method for diagnosing bearing faults under complex working conditions based on meta-learning under small samples. Background technique [0002] Fault diagnosis plays a key role in the healthy operation and safe service of equipment. In recent years, with the rapid development of deep learning, fault diagnosis research based on deep learning has made great progress. Deep learning models such as deep belief networks, autoencoder networks, convolutional neural networks, and generative adversarial networks are widely used in the field of equipment fault diagnosis. The application of deep learning in the field of fault diagnosis. [0003] However, in the field of fault diagnosis, data collection and fault states in special service environments (such as toxic, high temperature, and high pressure) can cause life-threatening and major pr...

AI Technical Summary

Problems solved by technology

[0004] The technical problem to be solved by the present invention is: to provide a bearing fault diagnosis method based on meta-learning in a small sample under complex working conditions, by quickly applying the fault knowledge learned in the meta-training process to fault identification under new working conditions, overcoming It eliminates the dependence on a large number of samples in traditional fault diagnosis, and can achieve high accuracy in different complex working conditions

Images