Abstract
Induction motors are widely employed across various industries, which necessitates the development of an effective fault diagnosis system to prevent unplanned downtime. Lately, there has been a notable emphasis on deep learning techniques, primarily attributed to their capacity for directly extracting features from unprocessed data. In this study, we collected multisensory signals (vibration, current, voltage, and speed) from an induction motor test stand under diverse operating conditions, including healthy, outer bearing fault, and shaft misalignment. Seven combinations of the multisensory data were employed to train 1D and 2D Convolutional Neural Network (CNN) architectures for motor fault classification. A comparative analysis was undertaken to evaluate the diagnostic accuracy, number of parameters, and computational time of the 1D and 2D CNN models. The results reveal that the best performance was achieved when the 1D and 2D CNN models were trained solely on the motor’s vibration signals. Additionally, the 2D CNN model slightly outperformed the 1D CNN in terms of its overall validation accuracy under different multisensory signal combinations.
Original language | English |
---|---|
Title of host publication | Proceedings of the UNIfied Conference of DAMAS, IncoME and TEPEN Conferences (UNIfied 2023) - Volume 2 |
Editors | Andrew D. Ball, Huajiang Ouyang, Jyoti K. Sinha, Zuolu Wang |
Publisher | Springer, Cham |
Pages | 1125-1135 |
Number of pages | 11 |
Volume | 152 |
ISBN (Electronic) | 9783031494215 |
ISBN (Print) | 9783031494208, 9783031494239 |
DOIs | |
Publication status | Published - 29 May 2024 |
Event | The UNIfied Conference of DAMAS, InCoME and TEPEN Conferences - Huddersfield, United Kingdom, Huddersfield, United Kingdom Duration: 29 Aug 2023 → 1 Sep 2023 https://unified2023.org/ |
Publication series
Name | Mechanisms and Machine Science |
---|---|
Publisher | Springer |
Volume | 152 MMS |
ISSN (Print) | 2211-0984 |
ISSN (Electronic) | 2211-0992 |
Conference
Conference | The UNIfied Conference of DAMAS, InCoME and TEPEN Conferences |
---|---|
Abbreviated title | UNIfied 2023 |
Country/Territory | United Kingdom |
City | Huddersfield |
Period | 29/08/23 → 1/09/23 |
Internet address |