Causal Disentanglement Hidden Markov Model for Fault Diagnosis

TL;DR

This paper introduces a novel causal disentanglement hidden Markov model for fault diagnosis that effectively captures fault-relevant features from time-series data, improving robustness and adaptability across environments.

Contribution

The paper proposes a new causal disentanglement HMM that leverages unsupervised domain adaptation for fault diagnosis, enhancing feature extraction and transferability.

Findings

Outperforms existing methods on CWRU and IMS datasets.

Effectively disentangles fault-relevant and irrelevant factors.

Demonstrates robustness across different working environments.

Abstract

In modern industries, fault diagnosis has been widely applied with the goal of realizing predictive maintenance. The key issue for the fault diagnosis system is to extract representative characteristics of the fault signal and then accurately predict the fault type. In this paper, we propose a Causal Disentanglement Hidden Markov model (CDHM) to learn the causality in the bearing fault mechanism and thus, capture their characteristics to achieve a more robust representation. Specifically, we make full use of the time-series data and progressively disentangle the vibration signal into fault-relevant and fault-irrelevant factors. The ELBO is reformulated to optimize the learning of the causal disentanglement Markov model. Moreover, to expand the scope of the application, we adopt unsupervised domain adaptation to transfer the learned disentangled representations to other working environments. Experiments were conducted on the CWRU dataset and IMS dataset. Relevant results validate the superiority of the proposed method.