Cargando…

Fault detection on fluid machinery using Hidden Markov Models

A fault detection method exploiting Hidden Markov Models (HMMs) is proposed for fluid machinery without adequate a priori information about faulty conditions. The method is trained only on data acquired during normal machine operation. For anomaly detection, typical quantities measured in monitoring...

Descripción completa

Detalles Bibliográficos
Autores principales: Arpaia, P, Cesaro, U, Chadli, M, Coppier, H, De Vito, L, Esposito, A, Gargiulo, F, Pezzetti, M
Lenguaje:eng
Publicado: 2020
Acceso en línea:https://dx.doi.org/10.1016/j.measurement.2019.107126
http://cds.cern.ch/record/2704706
_version_ 1780964720368418816
author Arpaia, P
Cesaro, U
Chadli, M
Coppier, H
De Vito, L
Esposito, A
Gargiulo, F
Pezzetti, M
author_facet Arpaia, P
Cesaro, U
Chadli, M
Coppier, H
De Vito, L
Esposito, A
Gargiulo, F
Pezzetti, M
author_sort Arpaia, P
collection CERN
description A fault detection method exploiting Hidden Markov Models (HMMs) is proposed for fluid machinery without adequate a priori information about faulty conditions. The method is trained only on data acquired during normal machine operation. For anomaly detection, typical quantities measured in monitoring fluid machines, namely 3-axis acceleration, electric power consumption, temperature, inlet and outlet pressure, are monitored. Principal Component Analysis is exploited for features extraction. Then, data is clustered and an HMM is trained. Finally, the trained model is employed together with a goodness-of-fit test to detect faulty states by processing online data. The method was tested and validated at CERN on screw compressors for cryogenic cooling.
id oai-inspirehep.net-1770235
institution Organización Europea para la Investigación Nuclear
language eng
publishDate 2020
record_format invenio
spelling oai-inspirehep.net-17702352020-01-10T08:48:17Zdoi:10.1016/j.measurement.2019.107126http://cds.cern.ch/record/2704706engArpaia, PCesaro, UChadli, MCoppier, HDe Vito, LEsposito, AGargiulo, FPezzetti, MFault detection on fluid machinery using Hidden Markov ModelsA fault detection method exploiting Hidden Markov Models (HMMs) is proposed for fluid machinery without adequate a priori information about faulty conditions. The method is trained only on data acquired during normal machine operation. For anomaly detection, typical quantities measured in monitoring fluid machines, namely 3-axis acceleration, electric power consumption, temperature, inlet and outlet pressure, are monitored. Principal Component Analysis is exploited for features extraction. Then, data is clustered and an HMM is trained. Finally, the trained model is employed together with a goodness-of-fit test to detect faulty states by processing online data. The method was tested and validated at CERN on screw compressors for cryogenic cooling.oai:inspirehep.net:17702352020
spellingShingle Arpaia, P
Cesaro, U
Chadli, M
Coppier, H
De Vito, L
Esposito, A
Gargiulo, F
Pezzetti, M
Fault detection on fluid machinery using Hidden Markov Models
title Fault detection on fluid machinery using Hidden Markov Models
title_full Fault detection on fluid machinery using Hidden Markov Models
title_fullStr Fault detection on fluid machinery using Hidden Markov Models
title_full_unstemmed Fault detection on fluid machinery using Hidden Markov Models
title_short Fault detection on fluid machinery using Hidden Markov Models
title_sort fault detection on fluid machinery using hidden markov models
url https://dx.doi.org/10.1016/j.measurement.2019.107126
http://cds.cern.ch/record/2704706
work_keys_str_mv AT arpaiap faultdetectiononfluidmachineryusinghiddenmarkovmodels
AT cesarou faultdetectiononfluidmachineryusinghiddenmarkovmodels
AT chadlim faultdetectiononfluidmachineryusinghiddenmarkovmodels
AT coppierh faultdetectiononfluidmachineryusinghiddenmarkovmodels
AT devitol faultdetectiononfluidmachineryusinghiddenmarkovmodels
AT espositoa faultdetectiononfluidmachineryusinghiddenmarkovmodels
AT gargiulof faultdetectiononfluidmachineryusinghiddenmarkovmodels
AT pezzettim faultdetectiononfluidmachineryusinghiddenmarkovmodels