Fault Classification in a Reciprocating Compressor and a Centrifugal Pump Using Non-Linear Entropy Features

Medina, Ruben; Cerrada, Mariela; Yang, Shuai; Cabrera, Diego; Estupiñan, Edgar; Sánchez, René-Vinicio

doi:10.3390/math10173033

Open AccessArticle

Fault Classification in a Reciprocating Compressor and a Centrifugal Pump Using Non-Linear Entropy Features

by

Ruben Medina

^1,*

,

Mariela Cerrada

²

,

Shuai Yang

³

,

Diego Cabrera

²

,

Edgar Estupiñan

⁴

and

René-Vinicio Sánchez

^2,*

¹

CIBYTEL-Engineering School, University of Los Andes, Mérida 5101, Venezuela

²

GIDTEC, Universidad Politécnica Salesiana, Cuenca 010105, Ecuador

³

National Research Base of Intelligent Manufacturing Service, Chongqing Technology and Business University, 19# Xuefu Avenue, Nan’an District, Chongqing 400067, China

⁴

Mechanical Engineering Department, University of Tarapaca, Arica 1130000, Chile

^*

Authors to whom correspondence should be addressed.

Mathematics 2022, 10(17), 3033; https://doi.org/10.3390/math10173033

Submission received: 30 June 2022 / Revised: 10 August 2022 / Accepted: 17 August 2022 / Published: 23 August 2022

(This article belongs to the Special Issue Applied Mathematics to Mechanisms and Machines)

Download

Browse Figures

Versions Notes

Abstract

This paper describes a comparison of three types of feature sets. The feature sets were intended to classify 13 faults in a centrifugal pump (CP) and 17 valve faults in a reciprocating compressor (RC). The first set comprised 14 non-linear entropy-based features, the second comprised 15 information-based entropy features, and the third comprised 12 statistical features. The classification was performed using random forest (RF) models and support vector machines (SVM). The experimental work showed that the combination of information-based features with non-linear entropy-based features provides a statistically significant accuracy higher than the accuracy provided by the Statistical Features set. Results for classifying the 13 conditions in the CP using non-linear entropy features showed accuracies of up to 99.50%. The same feature set provided a classification accuracy of 97.50% for the classification of the 17 conditions in the RC.

Keywords: approximate entropy; non-linear systems; phase space reconstruction; fault classification; random forest; support vector machines

Share and Cite

MDPI and ACS Style

Medina, R.; Cerrada, M.; Yang, S.; Cabrera, D.; Estupiñan, E.; Sánchez, R.-V. Fault Classification in a Reciprocating Compressor and a Centrifugal Pump Using Non-Linear Entropy Features. Mathematics 2022, 10, 3033. https://doi.org/10.3390/math10173033

AMA Style

Medina R, Cerrada M, Yang S, Cabrera D, Estupiñan E, Sánchez R-V. Fault Classification in a Reciprocating Compressor and a Centrifugal Pump Using Non-Linear Entropy Features. Mathematics. 2022; 10(17):3033. https://doi.org/10.3390/math10173033

Chicago/Turabian Style

Medina, Ruben, Mariela Cerrada, Shuai Yang, Diego Cabrera, Edgar Estupiñan, and René-Vinicio Sánchez. 2022. "Fault Classification in a Reciprocating Compressor and a Centrifugal Pump Using Non-Linear Entropy Features" Mathematics 10, no. 17: 3033. https://doi.org/10.3390/math10173033

APA Style

Medina, R., Cerrada, M., Yang, S., Cabrera, D., Estupiñan, E., & Sánchez, R.-V. (2022). Fault Classification in a Reciprocating Compressor and a Centrifugal Pump Using Non-Linear Entropy Features. Mathematics, 10(17), 3033. https://doi.org/10.3390/math10173033

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Menu

Fault Classification in a Reciprocating Compressor and a Centrifugal Pump Using Non-Linear Entropy Features

Abstract

Share and Cite

Article Metrics

Article Access Statistics

Further Information

Guidelines

MDPI Initiatives

Follow MDPI