Online machine health prognostics based on modified duration-dependent hidden semi-Markov model and high-order particle filtering

Xiao, Qili; Fang, Yilin; Liu, Quan; Zhou, Shujuan

doi:10.1007/s00170-017-0916-7

Cited by 29 publications

(17 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They built a multi-state degradation Non-Homogeneous HSMM and proposed a Bayesian networks approach to estimate the distribution of RUL (Loutas et al, 2017). Similar to Wang et al (2014), Xiao et al (2018) integrated the HSMM and high-order particle filter method to estimate RUL, where the emitting probability is state and duration-dependent. For solving the high computational complexity of HSMM, Liu et al (2012) further utilized the sequential Monte Carlo method to approximate posterior probability in training and decoding.…”

Section: Literature Reviewmentioning

confidence: 99%

A method for degradation prediction based on Hidden semi-Markov models with mixture of Kernels

Yang

Zheng

2020

Computers in Industry

View full text Add to dashboard Cite

Section: Literature Reviewmentioning

confidence: 99%

A method for degradation prediction based on Hidden semi-Markov models with mixture of Kernels

Yang

Zheng

2020

Computers in Industry

View full text Add to dashboard Cite

“…Despite the ease of implementing a PF and the possibilities of obtaining improved results with MPF as exemplified with the works of different authors [22,24,35], there is also room for improvement. This is the reason why it is important to improve the results that are obtained from the MPF via an optimization framework, which can be provided by the GA via evolutionary theory-based new estimations.…”

Section: Framework For Optimal Multi-level Particle Filter (Opmpf) Esmentioning

confidence: 99%

Prognosis and Remaining Useful Life Estimation of Lithium-Ion Battery with Optimal Multi-Level Particle Filter and Genetic Algorithm

Ossai¹

2018

Batteries

View full text Add to dashboard Cite

Prognosis and remaining useful life (RUL) estimation of components and systems (C&S) are vital for intelligent asset-integrity management. The implementation of the traditional multi-level particle filter (TRMPF) has improved prognosis when compared with the one-step traditional particle filter that depended on the first-order state equation. However, despite this improvement, the need to enhance the accuracy of fault prognosis, diagnosis and detection cannot be overemphasized. To this end, an optimal multi-level particle filter (OPMPF) algorithm that combines genetic algorithm (GA) optimization and multi-level particle filter (MPF) techniques is used to predict the RUL of the C&S in order to enhance the accuracy of the estimation at different forms of deterioration in operation. A 9-fold cross-validation ensemble MPF that utilized lithium-ion (Li +) batteries' charge capacity decay to test the developed OPMPF algorithm showed an improvement of over 200% in the estimated RUL when compared with the TRMPF estimation.

show abstract

“…The predicted degradation state is, then, compared with a failure criterion (failure threshold) representative of the degradation state beyond the which the equipment fails performing its required functions. Examples of modeling techniques used in degradation-based approaches are Wiener Processes (WP) [4], Gamma Processes (GP) [5], Inverse Gaussian Processes (IGP) [6], Semi-Markov Models (SMM) [7], Hidden Semi-Markov Models (HSMM) [8], General Path Models (GPM) [9] and fuzzy transition models [10] based on Mamdani models [11].…”

Section: Introductionmentioning

confidence: 99%

An evidential similarity-based regression method for the prediction of equipment remaining useful life in presence of incomplete degradation trajectories

Cannarile

Baraldi

Zio

2019

Fuzzy Sets and Systems

View full text Add to dashboard Cite

Data-driven methods for direct prognostic map the relationship between monitored parameters and equipment Remaining Useful Life (RUL). They typically require the availability of a set of run-to-failure degradation trajectories for model training. Yet, in many industrial applications, equipment is often replaced before they fail to avoid catastrophic consequences on production and safety. Then also, incomplete degradation trajectories are available. In this work, we develop a method for predicting equipment RUL, and the related uncertainty based on both complete and incomplete degradation trajectories. The method is based on the combined use of a similarity measure and Evidence Theory (EvT). Application of the method on two case studies shows that it provides accurate RUL predictions, also in comparison with a similarity-based regression method of literature.

show abstract

Online machine health prognostics based on modified duration-dependent hidden semi-Markov model and high-order particle filtering

Cited by 29 publications

References 36 publications

A method for degradation prediction based on Hidden semi-Markov models with mixture of Kernels

A method for degradation prediction based on Hidden semi-Markov models with mixture of Kernels

Prognosis and Remaining Useful Life Estimation of Lithium-Ion Battery with Optimal Multi-Level Particle Filter and Genetic Algorithm

An evidential similarity-based regression method for the prediction of equipment remaining useful life in presence of incomplete degradation trajectories

Contact Info

Product

Resources

About