Complexity and Entropy Representation for Machine Component Diagnostics

Published

July 9, 2019

Author(s)

Srinivasan Radhakrishnan, Yung-Tsun Lee, Sudarsan Rachuri, Sagar Kamarthi

Abstract

The Complexity-entropy causality plane (CECP) is a parsimonious representation space for time series. It has two dimensions: normalized permutation entropy (Hs) and Jensen-Shannon complexity (Cjs) of a time series. The representation can be used for both predictive analytics and visual monitoring of changes in component condition. This method requires minimal pre- processing of raw signals. Furthermore, it is insensitive to noise, stationarity, and trends. These desirable properties make CECP a good candidate for machine condition monitoring and fault diagnostics. In this work we demonstrate the effectiveness of CECP on three rotary component condition assessment applications. We use CECP representation of vibration signals to differentiate various machine component health conditions. The results confirm that the CECP representation is able to detect, with high accuracy, changes in underlying dynamics of machine component degradation states.

Citation

PLoS One

Volume

14

Issue

7

Pub Type

Journals

Download Paper

https://doi.org/10.1371/journal.pone.0217919

Local Download

Keywords

complexity-entropy plane, permutation entropy, support vector machine, machine fault diagnostics, component condition visualization

Citation

Radhakrishnan, S. , Lee, Y. , Rachuri, S. and Kamarthi, S. (2019), Complexity and Entropy Representation for Machine Component Diagnostics, PLoS One, [online], https://doi.org/10.1371/journal.pone.0217919, https://tsapps.nist.gov/publication/get_pdf.cfm?pub_id=927518 (Accessed December 5, 2024)