A Note on the Sensitivity of Permutation Entropy to Additive Noise

Additive noise could be encountered in various mechanical systems. It could be observed as part of ongoing system degradation and defect evolution. Here, we empirically demonstrate inherent challenges of permutation entropy (PE) in remaining useful life (RUL) analysis, the analysis of time to failure or time to unacceptable wear of the system. We perform numerical experiments by adding various amounts of additive Gaussian noise to vibrational signal and investigate how the PE changes. The data or signal are often comprised of several parts such as fundamental component, noise and other components related to perturbations out of the evolving defects. Here, we gain an additional insight on what part of the signal is related to the RUL. By joining these two problems together, we can draw a practical conclusion on how robust to additive noise the PE is to a particular dataset.

Authors

Institutions

Publication Details

Journal
Fluctuation and Noise Letters
Published
2024-12-20
DOI
https://doi.org/10.1142/s0219477525500257
Primary Topic
Model Reduction and Neural Networks
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

A Note on the Sensitivity of Permutation Entropy to Additive Noise

Kamilija Jablonskaite, Mantas Landauskas, Eva-Maria Haslhofer
Fluctuation and Noise Letters
Model Reduction and Neural Networks
article

A Note on the Sensitivity of Permutation Entropy to Additive Noise

Kamilija Jablonskaite, Mantas Landauskas, Eva-Maria Haslhofer
article en

Abstract

Additive noise could be encountered in various mechanical systems. It could be observed as part of ongoing system degradation and defect evolution. Here, we empirically demonstrate inherent challenges of permutation entropy (PE) in remaining useful life (RUL) analysis, the analysis of time to failure or time to unacceptable wear of the system. We perform numerical experiments by adding various amounts of additive Gaussian noise to vibrational signal and investigate how the PE changes. The data or signal are often comprised of several parts such as fundamental component, noise and other components related to perturbations out of the evolving defects. Here, we gain an additional insight on what part of the signal is related to the RUL. By joining these two problems together, we can draw a practical conclusion on how robust to additive noise the PE is to a particular dataset.

Fluctuation and Noise LettersVol. 24(03)
Johannes Kepler University of Linz (AT), Kaunas University of Technology (LT)
Openalex Percentile: Top 78%
Model Reduction and Neural Networks
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.