Causal Disentanglement Hidden Markov Model for Fault Diagnosis
This addresses fault diagnosis for industrial predictive maintenance, presenting an incremental improvement through a novel method for known bottlenecks in representation learning.
The paper tackles fault diagnosis in industrial systems by proposing a Causal Disentanglement Hidden Markov Model (CDHM) to learn causality in bearing faults, achieving more robust representations through disentangling vibration signals into fault-relevant and irrelevant factors, with experiments on CWRU and IMS datasets validating its superiority.
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.