Attention-embedded Quadratic Network (Qttention) for Effective and Interpretable Bearing Fault Diagnosis

TL;DR

This paper introduces Qttention, a quadratic neuron-based neural network with an embedded attention mechanism, enhancing interpretability and effectiveness in bearing fault diagnosis using noisy data.

Contribution

It proposes a novel quadratic neuron-based network with an interpretable attention mechanism called qttention for fault diagnosis.

Findings

Effective fault classification on public and proprietary datasets.

Enhanced interpretability of the neural network model.

Robustness to noisy bearing data.

Abstract

Bearing fault diagnosis is of great importance to decrease the damage risk of rotating machines and further improve economic profits. Recently, machine learning, represented by deep learning, has made great progress in bearing fault diagnosis. However, applying deep learning to such a task still faces a major problem. A deep network is notoriously a black box. It is difficult to know how a model classifies faulty signals from the normal and the physics principle behind the classification. To solve the interpretability issue, first, we prototype a convolutional network with recently-invented quadratic neurons. This quadratic neuron empowered network can qualify the noisy bearing data due to the strong feature representation ability of quadratic neurons. Moreover, we independently derive the attention mechanism from a quadratic neuron, referred to as qttention, by factorizing the learned quadratic function in analogue to the attention, making the model with quadratic neurons inherently interpretable. Experiments on the public and our datasets demonstrate that the proposed network can facilitate effective and interpretable bearing fault diagnosis.