Poincaré Images Extracted from Vibration Signals are Useful Features for Fault Classification in a Reciprocating Compressor

Producción científica: Capítulo del libro/informe/acta de congresoCapítulorevisión exhaustiva

2 Citas (Scopus)

Resumen

Fault classification is an essential tool for Prognostics and Health Management (PHM), whose goal is the assessment of the health condition of a machine and its components. In this research, we propose using Poincaré Images (PI) as features for fault classification using Convolutional Neural Networks (CNN). The approach is validated for classifying 17 valve faults in a reciprocating compressor (RC). The proposed approach attained an averaged classification accuracy of 94.97% which represents an improvement of about 15% concerning using discrete features extracted from the Poincaré plot for classifying faults with Random Forest models. Additionally, results show that the classification performance with PI is comparable to using spectrograms as alternative input images to CNN-based fault classifiers.

Idioma originalInglés
Título de la publicación alojadaStudies in Systems, Decision and Control
EditorialSpringer Science and Business Media Deutschland GmbH
Páginas119-128
Número de páginas10
DOI
EstadoPublicada - 2023

Serie de la publicación

NombreStudies in Systems, Decision and Control
Volumen464

Nota bibliográfica

Publisher Copyright:
© 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Huella

Profundice en los temas de investigación de 'Poincaré Images Extracted from Vibration Signals are Useful Features for Fault Classification in a Reciprocating Compressor'. En conjunto forman una huella única.

Citar esto