A lightweight evidence-guided acoustic diagnostic network for automotive component fault detection in maintenance scenarios
Authors:
- 25 September 2026
- journal article
- research article
- Published by SAGE Publications in Proceedings of the Institution of Mechanical Engineers, Part D: Journal of Automobile Engineering
Abstract
Non-contact acoustic diagnosis is attractive for automotive maintenance because abnormal sounds can be recorded without installing additional sensors on compact or inaccessible components. Practical service recordings, however, are affected by low-frequency dominance, transient impacts, device differences, propagation paths, and background noise. This study proposes a lightweight evidence-guided convolutional neural network (CNN)-graph convolutional network (GCN) for 12-class automotive component acoustic fault detection. Long-window short-time Fourier transform (STFT), short-window STFT, and log-Mel spectrograms are combined as a three-channel time-frequency representation to preserve low-frequency spectral details, impact-related temporal changes, and perceptual acoustic information. A dual-branch network is then used: the CNN branch extracts local time-frequency textures, while the GCN branch treats temporal frames as graph nodes and constructs a sample-adaptive Top-K graph to model non-local temporal relations. To reduce dependence on noise-related shortcuts, a frequency-band attribution-prior loss is introduced using class-specific fault-sensitive bands estimated from the training data. Under a source-group-level evaluation protocol, the proposed model achieves 0.9749 segment-level accuracy, 0.9749 macro- F 1, and 0.9976 macro-AUC on an independent test set. Ablation, noise robustness, and prototype deployment tests indicate the value of the proposed representation, local-global architecture, and evidence-guided loss for maintenance-oriented acoustic diagnosis.Keywords
Funding Information
- National Key Research and Development Program of China (2023YFC2809804)
- National Natural Science Foundation of China (52571377)
- Fundamental Research Funds for the Central Universities (3132023513)
- Fundamental Research Funds for the Central Universities (3132025120)
This publication has 27 references indexed in Scilit:
- Acoustic fault diagnosis method for rotating machinery based on improved spectral subtraction and CNN-TCN modelMeasurement, 2025
- Enhancing vehicle fault diagnosis through multi-view sound analysis: integrating scalograms and spectrograms in a deep learning frameworkSignal, Image and Video Processing, 2025
- Making transformer hear better: Adaptive feature enhancement based multi-level supervised acoustic signal fault diagnosisExpert Systems with Applications, 2024
- A survey of mechanical fault diagnosis based on audio signal analysisMeasurement, 2023
- A review of the application of deep learning in intelligent fault diagnosis of rotating machineryMeasurement, 2022
- Rolling element bearing fault diagnosis using convolutional neural network and vibration imageCognitive Systems Research, 2019
- Rolling element bearing diagnostics—A tutorialMechanical Systems and Signal Processing, 2011
- An expert system for fault diagnosis in internal combustion engines using wavelet packet transform and neural networkExpert Systems with Applications, 2009
- A review on machinery diagnostics and prognostics implementing condition-based maintenanceMechanical Systems and Signal Processing, 2006
- Support-vector networksMachine Learning, 1995