Autoregressive Hidden Markov Models with partial knowledge on latent space applied to aero-engines prognostics

TL;DR

This paper introduces an Autoregressive Partially-hidden Markov Model (ARPHMM) for fault detection and prognostics in equipment, integrating prior knowledge into the learning process to improve remaining useful life estimation from sensor data.

Contribution

It proposes a novel modification to the ARPHMM learning algorithm that incorporates prior knowledge about the latent structure, enhancing prognostics accuracy.

Findings

Effective estimation of remaining useful life using the model.

Demonstrated applicability on CMAPSS datasets.

Improved fault detection accuracy.

Abstract

[This paper was initially published in PHME conference in 2016, selected for further publication in International Journal of Prognostics and Health Management.] This paper describes an Autoregressive Partially-hidden Markov model (ARPHMM) for fault detection and prognostics of equipments based on sensors' data. It is a particular dynamic Bayesian network that allows to represent the dynamics of a system by means of a Hidden Markov Model (HMM) and an autoregressive (AR) process. The Markov chain assumes that the system is switching back and forth between internal states while the AR process ensures a temporal coherence on sensor measurements. A sound learning procedure of standard ARHMM based on maximum likelihood allows to iteratively estimate all parameters simultaneously. This paper suggests a modification of the learning procedure considering that one may have prior knowledge about the structure which becomes partially hidden. The integration of the prior is based on the Theory of Weighted Distributions which is compatible with the Expectation-Maximization algorithm in the sense that the convergence properties are still satisfied. We show how to apply this model to estimate the remaining useful life based on health indicators. The autoregressive parameters can indeed be used for prediction while the latent structure can be used to get information about the degradation level. The interest of the proposed method for prognostics and health assessment is demonstrated on CMAPSS datasets.