A lifetime prediction model based on two-path convolution with attention mechanism and bidirectional long short-term memory network

Abstract

With the continuous progress of technology, the structure of modern industrial equipment is becoming increasingly complex. Complex industrial processes often have multivariable, nonlinear, variable operating conditions and intense noise, making it a challenging research direction to establish accurate residual service life prediction models.
This paper constructs a life prediction model based on two-way convolution, attention mechanisms, and a two-way short-term memory network. The front end of the model uses a two-way convolution scale and attention module to mine critical fault information of bearings, improve the anti-noise ability of the model, and use adaptive batch normalization (AdaBN) and Meta-Aconc activation function to adaptively adjust neurons to enhance the generalization ability of the model, At the back end of the model, the bidirectional long-term and short-term memory network is used to memorize the degradation information of the bearing and the residual service life of the bearing is predicted.
Finally, it has a high prediction accuracy in noise interference and condition migration scenarios using the root mean square error (RMSE), average absolute error (MAE), and other prediction indicators.
This model provides a method reference for predicting the lifespan of rotating machinery under intense noise and variable operating conditions.