49 / 2025-05-13 17:27:59
Multimodal Acoustic Feature Fusion with Hybrid Deep Networks for Industrial Equipment Fault Detection
acoustic signal processing,fault diagnosis,deep learning,industrial machines,health monitoring
全文待审
旭 王 / College of Mechanical and Electrical Engineering, Hohai University
诙 周 / Beijing Science and Technology Achievements Transformation Service Center;The Department of Industrial Engineering, Tsinghua University
延杰 许 / The State Key Laboratory of Tribology in Advanced Equipment;The Department of Mechanical Engineering, Tsinghua University
映桃 张 / College of Mechanical and Electrical Engineering, Hohai University
振国 聂 / The State Key Laboratory of Tribology in Advanced Equipment;The Department of Mechanical Engineering, Tsinghua University
Early detection of malfunctions in industrial machinery is critical for minimizing downtime and ensuring production efficiency. Although deep learning approaches based on acoustic signals have shown promising results, many existing models rely on single-feature inputs or lack robustness in noisy environments—limiting their effectiveness in real-world factory settings. In this study, we propose AFT-Net (Acoustic Fusion Transformer Network), a deep learning framework that integrates convolutional, recurrent, and attention-based components to robustly detect machine faults from acoustic signals under varying noise conditions. To enhance feature diversity and improve discriminative capability, AFT-Net fuses three complementary audio representations: Mel spectrograms, MFCCs, and spectral contrast. These features respectively capture perceptual frequency energy distributions, spectral envelope structures, and harmonic–noise patterns. The fused multimodal representation is processed through a hierarchical architecture composed of convolutional encoders for local time–frequency pattern extraction, a bidirectional LSTM for sequential dependency modeling, and a Transformer encoder to capture global contextual relationships via self-attention. This design significantly improves the model’s ability to detect subtle and temporally extended fault anomalies. Experimental results demonstrate that the method achieves high classification accuracy and remains robust across diverse machine sound anomalies, confirming its practicality for real-world industrial applications.
重要日期
  • 会议日期

    08月01日

    2025

    08月04日

    2025

  • 06月15日 2025

    初稿截稿日期

主办单位
中国机械工程学会设备智能运维分会
承办单位
新疆大学
移动端
在手机上打开
小程序
打开微信小程序
客服
扫码或点此咨询