Elaris Computing Nexus
Wavelet Transformer Hybrid Model for Real Time Industrial Fault Detection
Elaris Computing Nexus
Received On : 18 June 2026
Revised On : 30 July 2026
Accepted On : 28 August 2026
Published On : 05 September 2026
Volume 02, 2026
Pages : 177-189
Abstract
The fault detection of reliable industrial acoustic signal processing is a challenging problem because non-stationary noise, complicated vibration patterns, and the flaws of traditional signal analysis methods make the detection of harmful noise difficult. The conventional machine learning and classical signal processing methods can be very weak at capturing both the local time-frequency features and the global temporal patterns in acoustic fault signals. Additionally, the current deep learning models are either spectral feature-based or time-dependent models, which leads to poor diagnostic quality and low resilience to changing industrial settings. To fill this research gap, this paper suggests Adaptive Wavelet -Transformer Hybrid Model (AWTHM) in detecting faults in industrial machines on real time. The framework proposed is a combination of discrete wavelet transform (DWT) used to extract multi resolution time-frequency features and a lightweight transformer architecture to learn long-range associations of acoustic signals. Adaptive attention mechanism is also included to improve discriminative feature learning and noise artifact rejection. The model is tested on a benchmark industrial acoustic fault dataset of various machine operating conditions as well as fault categories. The experimental validation is done in a Python based deep learning environment with cross-validation and comparative benchmarking with conventional CNN, LSTM and SVM classifiers. The proposed AWTHM is classified with accuracy of 97.8%, precision of 97.2%, recall of 96.9% and the ability of the method to detect faults 22% better than the existing techniques. The key value of this work is that it succeeds in integrating effectively wavelet-based signal decomposition and transformer-based temporal learning to achieve robust and scalable acoustic fault diagnosis.
Keywords
Acoustic Signal Processing, Fault Detection, Discrete Wavelet Transform, Transformer Networks, Industrial Condition Monitoring, Hybrid Deep Learning Model.
- J. Ren, C. Hu, Z. Shang, Y. Li, Z. Zhao, and R. Yan, “Learning interpretable and transferable representations via wavelet-constrained transformer for industrial acoustic diagnosis,” IEEE Trans. Instrum. Meas., vol. 74, pp. 1–12, 2025, doi: 10.1109/TIM.2025.3544700.
- S. Zhao, L. Pan, and B. Li, “The study of transformer fault acoustic signal processing based on HHT and wavelet contour,” in Proc. 2009 WRI Global Congr. Intell. Syst., 2009, pp. 262–266, doi: 10.1109/GCIS.2009.330.
- Ali, W. Xinhua, and I. Razzaq, “Optimizing acoustic signal processing for localization of precise pipeline leakage using acoustic signal decomposition and wavelet analysis,” Digit. Signal Process., vol. 157, p. 104890, Feb. 2025, doi: 10.1016/j.dsp.2024.104890.
- Abbate, J. Koay, J. Frankel, S. C. Schroeder, and P. Das, “Signal detection and noise suppression using a wavelet transform signal processor: Application to ultrasonic flaw detection,” IEEE Trans. Ultrason., Ferroelectr., Freq. Control, vol. 44, no. 1, pp. 14–26, Jan. 1997, doi: 10.1109/58.585186.
- A. Kuznetsov, A. V. Ponomarev, A. V. Gorlov, and M. A. Volchanina, “Application of wavelet transform for recognition of acoustic signals of various defects of power transformers,” Mod. Transp. Syst. Technol., vol. 10, no. 4, pp. 504–516, Dec. 2024, doi: 10.17816/transsyst637451.
- R. Wang, Z. Chen, B. Wang, Z. Ba, and K. Ren, “AWaveFormer: Audio wavelet transformer network for generalized audio deepfake detection,” IEEE Trans. Audio, Speech, Lang. Process., vol. 33, pp. 4020–4032, 2025, doi: 10.1109/TASLPRO.2025.3611229.
- Y. Song, F. Liu, and T. Shen, “Method of underwater acoustic signal denoising based on dual-path transformer network,” IEEE Access, vol. 12, pp. 81483–81494, 2024, doi: 10.1109/ACCESS.2022.3224752.
- S. Wang, Q. Xu, S. Zhu, and B. Wang, “Making transformer hear better: Adaptive feature enhancement based multi-level supervised acoustic signal fault diagnosis,” Expert Syst. Appl., vol. 264, p. 125736, Mar. 2025, doi: 10.1016/j.eswa.2024.125736.
- M. N. Ali, E.-S. A. El-Dahshan, and A. H. Yahia, “Denoising of heart sound signals using discrete wavelet transform,” Circuits, Syst., Signal Process., vol. 36, no. 11, pp. 4482–4497, Nov. 2017, doi: 10.1007/s00034-017-0524-7.
- Macia-Sanahuja and H. Lamela-Rivera, “Wavelet analysis of partial discharges acoustic waves obtained using an optical fibre interferometric sensor for transformer applications,” in Proc. 2003 IEEE Int. Symp. Ind. Electron. (Cat. No. 03TH8692), vol. 2, 2003, pp. 1071–1076, doi: 10.1109/ISIE.2003.1267972.
- Z. K. Peng and F. L. Chu, “Application of the wavelet transform in machine condition monitoring and fault diagnostics: A review with bibliography,” Mech. Syst. Signal Process., vol. 18, no. 2, pp. 199–221, Mar. 2004, doi: 10.1016/S0888-3270(03)00075-X.
- X. Yu, W. Liang, L. Zhang, H. Jin, and J. Qiu, “Dual-tree complex wavelet transform and SVD based acoustic noise reduction and its application in leak detection for natural gas pipeline,” Mech. Syst. Signal Process., vol. 72–73, pp. 266–285, May 2016, doi: 10.1016/j.ymssp.2015.10.034.
- G. Wang, Y. Wang, Y. Min, and W. Lei, “Blind source separation of transformer acoustic signal based on sparse component analysis,” Energies, vol. 15, no. 16, p. 6017, Aug. 2022, doi: 10.3390/en15166017.
- Y. Dong, H. Jiang, M. Mu, and X. Wang, “A trustworthy lightweight multi-expert wavelet transformer for rotating machinery fault diagnosis,” Mech. Syst. Signal Process., vol. 235, p. 112945, Jul. 2025, doi: 10.1016/j.ymssp.2025.112945.
- X. Hou, Y. Qian, and Y. Che, “Denoising method for transformer acoustic signal based on CEEMDAN-SVD-wavelet threshold,” J. Phys.: Conf. Ser., vol. 3087, no. 1, p. 012031, Aug. 2025, doi: 10.1088/1742-6596/3087/1/012031.
- T. Choudhary, V. Goyal, and A. Bansal, “WTASR: Wavelet transformer for automatic speech recognition of Indian languages,” Big Data Min. Anal., vol. 6, no. 1, pp. 85–91, Mar. 2023, doi: 10.26599/BDMA.2022.9020017.
CRediT Author Statement
The author reviewed the results and approved the final version of the manuscript.
Acknowledgements
The authors thank the Department for providing the necessary infrastructure and academic support for this study.
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
Dataset: MIMII Dataset: Sound Dataset for Malfunctioning Industrial Machine Investigation and Inspection Repository: Zenodo DOI: 10.5281/zenodo.3384388 Access: https://zenodo.org/records/3384388?utm_source=chatgpt.com
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
Rights and permissions
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
Vivienne Sze, “Wavelet Transformer Hybrid Model for Real Time Industrial Fault Detection”, Elaris Computing Nexus, pp. 177-189, 2026, doi: 10.65148/ECN/2026015.
Copyright
© 2026 Vivienne Sze. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.