Multiscale Representations Fusion With Joint Multiple Reconstructions Autoencoder for Intelligent Fault Diagnosis

Existing intelligent fault diagnosis methods depend mostly on single-scale vibration signals, which not only ignore the latent useful information of other different scales, but also underestimate the complementary benefits across scales. In this work, we show the advantage of learning the combination of multiscale information by aiming to automatically capture complementary and discriminative feature representations from different scales of vibration signals. Specifically, we combine the merit of different activation functions in a joint learning fashion and propose a novel joint multiple reconstructions autoencoder (JMRAE), whose training objective is to jointly optimize multiple reconstruction losses. The JMRAE aims to jointly learn discriminative and robust scale-specific feature representations. In addition, we design a new multiscale representations fusion network (MRFN) model to effectively fuse multiscale feature representations learned concurrently by per-scale JMRAE model for maximizing the discriminative capability of the scale-fused features. The objective of MRFN is to benefit all different scales from each other for improving the classification performance. Extensive experimental results demonstrate the effectiveness of the proposed method on two rolling bearing datasets. The code of the proposed method is available at https://github.com/KWflyer/mrfn.