- Title
- Belt Conveyor Idlers Fault Detection Using Acoustic Analysis and Deep Learning Algorithm with the YAMNet Pretrained Network
- Creator
- Alharbi, Fahad; Luo, Suhuai; Zhao, Sipei; Yang, Guang; Wheeler, Craig; Chen, Zhiyong
- Relation
- IEEE Sensors Journal Vol. 24, Issue 19, p. 31379-31394
- Publisher Link
- http://dx.doi.org/10.1109/JSEN.2024.3439509
- Publisher
- Institute of Electrical and Electronics Engineers (IEEE)
- Resource Type
- journal article
- Date
- 2024
- Description
- Belt conveyor systems are essential in industries like automotive, aerospace, power generation, and heavy machinery, with idlers playing a crucial role in ensuring the smooth movement of materials. However, constant operation in noisy environments accelerates wear and tear on idlers and obscures early signs of malfunction, such as grinding or rattling from loose parts. This challenge makes early fault detection difficult, increasing downtime and maintenance costs. Therefore, timely and accurate fault detection is vital to prevent severe system issues, ensure optimal performance, and avoid unexpected breakdowns and costly production interruptions. Intelligent fault detection (IFD) using artificial intelligence (AI) methods has emerged as a solution, with machine learning techniques like convolutional neural networks (CNNs) proving effective. This study uses Yet another Audio Mobilenet Network (YAMNet), initially designed for sound event detection (SED), to identify faults in belt conveyor idlers by analyzing their unique acoustic signatures. We enhance detection capabilities by extracting temporal features from YAMNet-generated embeddings using bidirectional long-term memory (BiLSTM) and bidirectional gated recurrent units (BiGRUs), augmented with a soft attention mechanism. These features are evaluated using extreme gradient boosting (XGBoost), achieving an impressive 90% accuracy in fault detection across idler test sets. Our approach was rigorously compared to the VGGish model and validated on the publicly available malfunctioning industrial machine investigation and inspection (MIMII) dataset, where it demonstrated superior performance with AUC scores of 0.8355 for fans, 0.9414 for pumps, 0.9265 for valves, and 0.9703 for sliders. These results significantly improve over baseline scores, with increases of 19.36% for fans, 38.44% for pumps, 67.26% for valves, and 38.61% for sliders. This advancement represents a significant step forward in conveyor system diagnostics, providing a robust solution for enhancing industrial safety and operational efficiency.
- Subject
- acoustic analysis; attention mechanism; belt conveyor idlers; bidirectional gated recurrent unit (BiGRU); biodirectional long-term memory (BiLSTM); deep learning
- Identifier
- http://hdl.handle.net/1959.13/1517684
- Identifier
- uon:57151
- Identifier
- ISSN:1530-437X
- Language
- eng
- Reviewed
- Hits: 4
- Visitors: 4
- Downloads: 0
| Thumbnail | File | Description | Size | Format |
|---|