Fan Fault Diagnosis Using Acoustic Emission and Deep Learning Methods
The modern conception of industrial production recognizes the increasingly crucial role of maintenance. Currently, maintenance is thought of as a service that aims to maintain the efficiency of equipment and systems while also taking quality, energy efficiency, and safety requirements into considera...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-02-01
|
| Series: | Informatics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2227-9709/10/1/24 |
| _version_ | 1797611078438354944 |
|---|---|
| author | Giuseppe Ciaburro Sankar Padmanabhan Yassine Maleh Virginia Puyana-Romero |
| author_facet | Giuseppe Ciaburro Sankar Padmanabhan Yassine Maleh Virginia Puyana-Romero |
| author_sort | Giuseppe Ciaburro |
| collection | DOAJ |
| description | The modern conception of industrial production recognizes the increasingly crucial role of maintenance. Currently, maintenance is thought of as a service that aims to maintain the efficiency of equipment and systems while also taking quality, energy efficiency, and safety requirements into consideration. In this study, a new methodology for automating the fan maintenance procedures was developed. An approach based on the recording of the acoustic emission and the failure diagnosis using deep learning was evaluated for the detection of dust deposits on the blades of an axial fan. Two operating conditions have been foreseen: No-Fault, and Fault. In the No-Fault condition, the fan blades are perfectly clean while in the Fault condition, deposits of material have been artificially created. Utilizing a pre-trained network (SqueezeNet) built on the ImageNet dataset, the acquired data were used to build an algorithm based on convolutional neural networks (CNN). The transfer learning applied to the images of the spectrograms extracted from the recordings of the acoustic emission of the fan, in the two operating conditions, returned excellent results (accuracy = 0.95), confirming the excellent performance of the methodology. |
| first_indexed | 2024-03-11T06:23:48Z |
| format | Article |
| id | doaj.art-252e0b324eb74aa1825787f1afffe351 |
| institution | Directory Open Access Journal |
| issn | 2227-9709 |
| language | English |
| last_indexed | 2024-03-11T06:23:48Z |
| publishDate | 2023-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Informatics |
| spelling | doaj.art-252e0b324eb74aa1825787f1afffe3512023-11-17T11:43:32ZengMDPI AGInformatics2227-97092023-02-011012410.3390/informatics10010024Fan Fault Diagnosis Using Acoustic Emission and Deep Learning MethodsGiuseppe Ciaburro0Sankar Padmanabhan1Yassine Maleh2Virginia Puyana-Romero3Department of Architecture and Industrial Design, Università degli Studi della Campania Luigi Vanvitelli, 81031 Aversa, ItalyDepartment of Electronics and Communication Engineering, Hindustan Institute of Technology and Science, Chennai 603103, TN, IndiaEcole Nationale des Sciences Appliquée (ENSA) Khouribga, Sultan Moulay Slimane University, Beni Mellal 25000, MoroccoDepartment of Sound and Acoustic Engineering, Universidad de Las Américas, Quito EC170125, EcuadorThe modern conception of industrial production recognizes the increasingly crucial role of maintenance. Currently, maintenance is thought of as a service that aims to maintain the efficiency of equipment and systems while also taking quality, energy efficiency, and safety requirements into consideration. In this study, a new methodology for automating the fan maintenance procedures was developed. An approach based on the recording of the acoustic emission and the failure diagnosis using deep learning was evaluated for the detection of dust deposits on the blades of an axial fan. Two operating conditions have been foreseen: No-Fault, and Fault. In the No-Fault condition, the fan blades are perfectly clean while in the Fault condition, deposits of material have been artificially created. Utilizing a pre-trained network (SqueezeNet) built on the ImageNet dataset, the acquired data were used to build an algorithm based on convolutional neural networks (CNN). The transfer learning applied to the images of the spectrograms extracted from the recordings of the acoustic emission of the fan, in the two operating conditions, returned excellent results (accuracy = 0.95), confirming the excellent performance of the methodology.https://www.mdpi.com/2227-9709/10/1/24deep learningtransfer learningacoustics emissionfault diagnosis |
| spellingShingle | Giuseppe Ciaburro Sankar Padmanabhan Yassine Maleh Virginia Puyana-Romero Fan Fault Diagnosis Using Acoustic Emission and Deep Learning Methods Informatics deep learning transfer learning acoustics emission fault diagnosis |
| title | Fan Fault Diagnosis Using Acoustic Emission and Deep Learning Methods |
| title_full | Fan Fault Diagnosis Using Acoustic Emission and Deep Learning Methods |
| title_fullStr | Fan Fault Diagnosis Using Acoustic Emission and Deep Learning Methods |
| title_full_unstemmed | Fan Fault Diagnosis Using Acoustic Emission and Deep Learning Methods |
| title_short | Fan Fault Diagnosis Using Acoustic Emission and Deep Learning Methods |
| title_sort | fan fault diagnosis using acoustic emission and deep learning methods |
| topic | deep learning transfer learning acoustics emission fault diagnosis |
| url | https://www.mdpi.com/2227-9709/10/1/24 |
| work_keys_str_mv | AT giuseppeciaburro fanfaultdiagnosisusingacousticemissionanddeeplearningmethods AT sankarpadmanabhan fanfaultdiagnosisusingacousticemissionanddeeplearningmethods AT yassinemaleh fanfaultdiagnosisusingacousticemissionanddeeplearningmethods AT virginiapuyanaromero fanfaultdiagnosisusingacousticemissionanddeeplearningmethods |