Rolling bearing residual life prediction method based on deep generative adversarial network

Abstract

The invention discloses a rolling bearing residual life prediction method based on a deep generative adversarial network. The method comprises the following steps: collecting an original vibration signal of a rolling bearing; acquiring characteristic parameters of the original vibration signal; dividing the feature parameters into a training set and a prediction set; sending the training set intoa generator long short-term memory network for training; predicting the degradation process of the rolling bearing, and generating a prediction result; building an automatic encoder model as a discriminator, and discriminating whether a prediction result is from real historical data or not; enabling a generator long short-term memory network and a discriminator automatic encoder to carry out adversarial training to seek an optimal solution; and outputting a rolling bearing residual life prediction result. According to the method, the degradation process of the rolling bearing is predicted through long-term and short-term memory network learning, the prediction result of the long-term and short-term memory network is judged through the automatic encoder, the two methods conduct adversariallearning till the precision requirement is met, the prediction error superposition problem of a traditional method is reduced, and the prediction accuracy is improved.

Description

technical field [0001] The invention relates to the fields of fault diagnosis and bearing life prediction, in particular to a method for predicting the remaining life of a rolling bearing based on a deep generative confrontation network. Background technique [0002] Rolling bearings play an important role in rotating machinery such as high-speed railways, induction motors and wind turbine drive trains. The harsh working environment of rotating machinery exposes rolling bearings to high and low temperature, high pressure, and humid working environments, which will soon cause damage to rolling bearings. Any failure of rolling bearings will lead to failure of the entire machine, which will lead to high repair costs. If rolling bearing failures can be predicted in advance, the downtime of the entire rotating machinery caused by bearing failures can be avoided. Therefore, the remaining useful life (RUL) prediction of rolling bearings has received more and more attention in rec...

AI Technical Summary

Problems solved by technology

However, the existing model-based rolling bearing RUL prediction methods mainly have two defects: 1) If the physical or mathematical model of the rolling bearing transmission system is not simplified enough, and even the mechanical principle of the rotating machinery itself is an extremely complex system, then the model-based The RUL prediction method may fail in this case

But this method has a shortcoming that still hasn't been solved - the problem of superposition of forecast errors, which means that previous forecast errors will be accumulated into the next forecast

This is caused by the method itself, and it also limits the application of data-driven methods

Images