Maintaining both rider safety and vehicle dependability on motorbikes requires accurate problem detection. Using an improved ResNet architecture with Improved Sea Fish Optimization (ISFO) and Deep Convolutional Neural Networks (CNNs), this research proposes a sophisticated method for auditory defect identification in motorbikes. The machine ears start by gathering a wide range of audio frequency-based signal datasets from motorbike that span a range of failure scenarios and operational settings. To eliminate noise and identify distinguishing characteristics, these signals go through preprocessing. Then, to extract high-level features from the pre-processed signals, an improved ResNet architecture is used, supplemented with ISFO. By integrating both local and global information, the ResNet architecture's inclusion of ISFO makes it easier to iteratively update feature representations. To further improve the feature representations' discriminative power, Deep CNNs are used. The real-time defect detection system is designed specifically for motorbike uses the learned model. The trained model is used to interpret incoming acoustic data from motorcycle operations. This allows for the identification and categorization of various issues, such as engine misfires, irregularities in the valves, wear on the bearings, and clutch bearing failures. Experiments show that the proposed method is a good fit for precisely categorizing motorbike issues. Analyses conducted in comparison with baseline models demonstrate the superiority of the ResNet-ISFO and Deep CNN technique, demonstrating its resilience and efficiency across a range of fault situations and operational conditions. Overall, the proposed acoustic problem detection system is a potential approach for improving maintenance procedures while also assuring the safety and dependability of automobile engine. Its incorporation into standard maintenance operations can aid in proactive defect identification, reducing downtime and improving vehicle performance.
Keywords
Vehicle, Acoustic Fault Detection, ResNet, Improved Sea Fish Optimization, Deep Convolutional Neural Network.
X. Li, F. Bi, L. Zhang, X. Yang, and G. Zhang, “An Engine Fault Detection Method Based on the Deep Echo State Network and Improved Multi-Verse Optimizer,” Energies, vol. 15, no. 3, p. 1205, Feb. 2022, doi: 10.3390/en15031205.
G. Yang, Y. Wei, and H. Li, “Acoustic Diagnosis of Rolling Bearings Fault of CR400 EMU Traction Motor Based on XWT and GoogleNet,” Shock and Vibration, vol. 2022, pp. 1–12, Nov. 2022, doi: 10.1155/2022/2360067.
A. M. Terwilliger and J. E. Siegel, “Improving Misfire Fault Diagnosis with Cascading Architectures via Acoustic Vehicle Characterization,” Sensors, vol. 22, no. 20, p. 7736, Oct. 2022, doi: 10.3390/s22207736.
S. Asutkar and S. Tallur, “Deep transfer learning strategy for efficient domain generalisation in machine fault diagnosis,” Nov. 2022, doi: 10.21203/rs.3.rs-2215201/v1.
Y. Liu, J. Kang, L. Wen, Y. Bai, C. Guo, and W. Yu, “Fault Diagnosis Algorithm of Gearboxes Based on GWO-SCE Adaptive Multi-Threshold Segmentation and Subdomain Adaptation,” Processes, vol. 11, no. 2, p. 556, Feb. 2023, doi: 10.3390/pr11020556.
W. Zhang, T. Zhang, G. Cui, and Y. Pan, “Intelligent Machine Fault Diagnosis Using Convolutional Neural Networks and Transfer Learning,” IEEE Access, vol. 10, pp. 50959–50973, 2022, doi: 10.1109/access.2022.3173444.
M. Al Firdausi and S. Ahmad, “Concise convolutional neural network model for fault detection,” Communications in Science and Technology, vol. 7, no. 1, pp. 62–72, Jul. 2022, doi: 10.21924/cst.7.1.2022.746.
K. Wu, J. Tao, D. Yang, H. Xie, and Z. Li, “A Rolling Bearing Fault Diagnosis Method Based on Enhanced Integrated Filter Network,” Machines, vol. 10, no. 6, p. 481, Jun. 2022, doi: 10.3390/machines10060481.
Y. Wang and A. Vinogradov, “Improving the Performance of Convolutional GAN Using History-State Ensemble for Unsupervised Early Fault Detection with Acoustic Emission Signals,” Applied Sciences, vol. 13, no. 5, p. 3136, Feb. 2023, doi: 10.3390/app13053136.
Y. Yao, S. Zhang, S. Yang, and G. Gui, “Learning Attention Representation with a Multi-Scale CNN for Gear Fault Diagnosis under Different Working Conditions,” Sensors, vol. 20, no. 4, p. 1233, Feb. 2020, doi: 10.3390/s20041233.
X. Li, J. Li, D. He, and Y. Qu, “Gear pitting fault diagnosis using raw acoustic emission signal based on deep learning,” Eksploatacja i Niezawodność – Maintenance and Reliability, vol. 21, no. 3, pp. 403–410, Sep. 2019, doi: 10.17531/ein.2019.3.6.
C. Fu, Q. Lv, and H.-C. Lin, “Development of Deep Convolutional Neural Network with Adaptive Batch Normalization Algorithm for Bearing Fault Diagnosis,” Shock and Vibration, vol. 2020, pp. 1–10, Sep. 2020, doi: 10.1155/2020/8837958.
G. Zhang, J. Wang, B. Han, S. Jia, X. Wang, and J. He, “A Novel Deep Sparse Filtering Method for Intelligent Fault Diagnosis by Acoustic Signal Processing,” Shock and Vibration, vol. 2020, pp. 1–11, Jul. 2020, doi: 10.1155/2020/8837047.
B. Połok and P. Bilski, “Intelligent diagnostic system for the rachet mechanism faults detection using acoustic analysis,” Measurement, vol. 183, p. 109637, Oct. 2021, doi: 10.1016/j.measurement.2021.109637.
A. Parey and A. Singh, “Gearbox fault diagnosis using acoustic signals, continuous wavelet transform and adaptive neuro-fuzzy inference system,” Applied Acoustics, vol. 147, pp. 133–140, Apr. 2019, doi: 10.1016/j.apacoust.2018.10.013.
Acknowledgements
We would like to thank Reviewers for taking the time and effort necessary to review the manuscript. We sincerely appreciate all valuable comments and suggestions, which helped us to improve the quality of the manuscript.
Funding
No funding was received to assist with the preparation of this manuscript.
Ethics declarations
Conflict of interest
The authors have no conflicts of interest to declare that are relevant to the content of this article.
Availability of data and materials
Data sharing is not applicable to this article as no new data were created or analysed in this study.
Author information
Contributions
All authors have equal contribution in the paper and all authors have read and agreed to the published version of the manuscript.
Corresponding author
Sujitha Juliet D
Division of Data Science and Cyber Security, Karunya Institute of Technology and Sciences, Coimbatore, Tamil Nadu, India.
Open Access This article is licensed under a Creative Commons Attribution NoDerivs is a more restrictive license. It allows you to redistribute the material commercially or non-commercially but the user cannot make any changes whatsoever to the original, i.e. no derivatives of the original work. To view a copy of this license, visit https://creativecommons.org/licenses/by-nc-nd/4.0/
Cite this article
Debie Shajie A, Sujitha Juliet D, Kirubakaran Ezra and Blessy Annie Flora J, “Machine Ears: Audio Frequency-Based Automobile Engine Health Analysis”, Journal of Machine and Computing. doi: 10.53759/7669/jmc202505015.
