Deep Residual Networks With Adaptively Parametric Rectifier Linear Units for Fault Diagnosis

Vibration signals under the same health state often have large differences due to changes in operating conditions. Likewise, the differences among vibration signals under different health states can be small under some operating conditions. Traditional deep learning methods apply fixed nonlinear transformations to all the input signals, which have a negative impact on the discriminative feature learning ability, i.e., projecting the intraclass signals into the same region and the interclass signals into distant regions. Aiming at this issue, this article develops a new activation function, i.e., adaptively parametric rectifier linear units, and inserts the activation function into deep residual networks to improve the feature learning ability, so that each input signal is trained to have its own set of nonlinear transformations. To be specific, a subnetwork is inserted as an embedded module to learn slopes to be used in the nonlinear transformation. The slopes are dependent on the input signal, and thereby the developed method has more flexible nonlinear transformations than the traditional deep learning methods. Finally, the improved performance of the developed method in learning discriminative features has been validated through fault diagnosis applications.

Automated summary

A new activation function, adaptively parametric rectifier linear units, is developed and inserted into deep residual networks to improve feature learning ability, enabling each input signal to have its own set of nonlinear transformations. The method utilizes an embedded module to learn slopes for nonlinear transformation, resulting in more flexible nonlinear transformations compared to traditional deep learning methods. The improved performance of the method has been validated through fault diagnosis applications.