Abstract
Acoustic-based machine condition monitoring (MCM) provides an improved alternative to conventional MCM approaches, including vibration analysis and lubrication monitoring, among others. Several challenges arise in anomalous machine operating sound classification, as it requires effective 2D acoustic signal representation. This paper explores this question. A baseline convolutional neural network (CNN) is implemented and trained with rolling element bearing acoustic fault data. Three representations are considered, such as log-spectrogram, short-time Fourier transform and log-Mel spectrogram. The results establish log-Mel spectrogram and log-spectrogram, as promising candidates for further exploration.
Original language | English |
---|---|
Pages | 1-2 |
Number of pages | 2 |
Publication status | Published - 12 Apr 2022 |
Event | PECS 2022 Physics, Engineering and Computer Science Research conference, University of Hertfordshire - University of Hertfordshire, School of Physics, Engineering and Computer Science (online), Hatfield, United Kingdom Duration: 12 Apr 2022 → 12 Apr 2022 |
Conference
Conference | PECS 2022 Physics, Engineering and Computer Science Research conference, University of Hertfordshire |
---|---|
Country/Territory | United Kingdom |
City | Hatfield |
Period | 12/04/22 → 12/04/22 |
Keywords
- Machine Condition Monitoring
- Detection and Classification of Anomalous Machine Operating Sound
- Industrial Sound Analysis
- Machine Hearing