skip to main content
10.1145/3592307.3592352acmotherconferencesArticle/Chapter ViewAbstractPublication PagesiceccConference Proceedingsconference-collections
research-article

Mel-spectrogram based Approach for Fault Detection in Ball Bearing using Convolutional Neural Network

Published: 14 August 2023 Publication History

Abstract

A rotating machine consists of many components, and the bearing is one of the key components in it. The health condition of the bearing directly affects the safe operation of the rotating machine and also inhibits the catastrophic loss to other components. To receive high-quality goods and services from these machines, their proper functioning requires intelligent and effective bearing diagnosis. Sound signal heard by a human is an important indicator of the faults in various components of the bearing. In the present work, a Head and Torso Simulator (HATS) has been used to capture the sound signal data from various conditions of fault in the bearing to mimic the natural hearing of human beings. After that, the acquired sound signal data was processed to get the Mel spectrogram of different bearing conditions and then put as input to a designed Convolutional Neural Network (CNN) for the intelligent diagnosis. The accuracy range of 97.11 % - 99.93 % is obtained in the case of left ear data, and this range for right ear data is 97.43 % - 99.97 %. The obtained results signify the robustness of the proposed method in the intelligent diagnosis of faults in the bearing at different speeds and load conditions.

References

[1]
Mishra, R. K., Choudhary, A., Fatima, S., Mohanty, A. R., & Panigrahi, B. K. (2022). A self-adaptive multiple-fault diagnosis system for rolling element bearings. Measurement Science and Technology, 33(12), 125018.
[2]
Choi, S., Haque, M. S., Tarek, M. T. B., Mulpuri, V., Duan, Y., Das, S., ... & Toliyat, H. A. (2018). Fault diagnosis techniques for permanent magnet AC machine and drives—A review of current state of the art. IEEE Transactions on Transportation Electrification, 4(2), 444-463.
[3]
Li, C., De Oliveira, J. V., Cerrada, M., Cabrera, D., Sánchez, R. V., & Zurita, G. (2018). A systematic review of fuzzy formalisms for bearing fault diagnosis. IEEE Transactions on Fuzzy Systems, 27(7), 1362-1382.
[4]
Xu, Y., Yan, X., Sun, B., & Liu, Z. (2022). Deep Coupled Visual Perceptual Networks for Motor Fault Diagnosis Under Nonstationary Conditions. IEEE/ASME Transactions on Mechatronics.
[5]
Jamil, T., & Mohammed, I. (2015). Simulation of VICTOR Algorithm for Fault-Diagnosis of Digital Circuits. International Journal of Computer Theory and Engineering, 7(2), 103.
[6]
Mian, T., Choudhary, A., & Fatima, S. (2022). Vibration and infrared thermography based multiple fault diagnosis of bearing using deep learning. Nondestructive Testing and Evaluation, 1-22.
[7]
Vanni, R. K., Botura Jr, G., Lemos, M. A., Marques, M. A., & Rosa, L. C. (2012). Expert System to Detect Incipient Faults in Rotating Machines Using Fuzzy Logic and Virtual Instrumentation. International Journal of Computer Theory and Engineering, 4(6), 1011.
[8]
Mian, T., Choudhary, A., & Fatima, S. (2022). An efficient diagnosis approach for bearing faults using sound quality metrics. Applied Acoustics, 195, 108839.
[9]
Janssens, O., Loccufier, M., & Van Hoecke, S. (2018). Thermal imaging and vibration-based multisensor fault detection for rotating machinery. IEEE transactions on industrial informatics, 15(1), 434-444.
[10]
Qu, Y., Zhu, J., He, D., Qiu, B., & Bechhoefer, E. (2013, June). Development of a new acoustic emission based fault diagnosis tool for gearbox. In 2013 IEEE Conference on Prognostics and Health Management (PHM) (pp. 1-9). IEEE.
[11]
Purushotham, V., Narayanan, S., & Prasad, S. A. (2005). Multi-fault diagnosis of rolling bearing elements using wavelet analysis and hidden Markov model based fault recognition. Ndt & E International, 38(8), 654-664.
[12]
Tran, T., & Lundgren, J. (2020). Drill fault diagnosis based on the scalogram and mel spectrogram of sound signals using artificial intelligence. IEEE Access, 8, 203655-203666.
[13]
Dehestani, D. (2013). Hvac model based fault detection by incremental online support vector machine. International Journal of Computer Theory and Engineering, 5(3), 472.
[14]
Liu, R., Yang, B., Zio, E., & Chen, X. (2018). Artificial intelligence for fault diagnosis of rotating machinery: A review. Mechanical Systems and Signal Processing, 108, 33-47.
[15]
Hoang, D. T., & Kang, H. J. (2019). A survey on deep learning based bearing fault diagnosis. Neurocomputing, 335, 327-335.
[16]
Choudhary, A., Mian, T., & Fatima, S. (2021). Convolutional neural network based bearing fault diagnosis of rotating machine using thermal images. Measurement, 176, 109196.
[17]
Liu, H., Li, L., & Ma, J. (2016). Rolling bearing fault diagnosis based on STFT-deep learning and sound signals. Shock and Vibration, 2016.
[18]
Tang, S., Zhu, Y., & Yuan, S. (2022). A novel adaptive convolutional neural network for fault diagnosis of hydraulic piston pump with acoustic images. Advanced Engineering Informatics, 52, 101554.
[19]
Park, C. H., Kim, H., Suh, C., Chae, M., Yoon, H., & Youn, B. D. (2022). A health image for deep learning-based fault diagnosis of a permanent magnet synchronous motor under variable operating conditions: Instantaneous current residual map. Reliability Engineering & System Safety, 226, 108715.
[20]
Dabeer, S., Khan, M. M., & Islam, S. (2019). Cancer diagnosis in histopathological image: CNN based approach. Informatics in Medicine Unlocked, 16, 100231.
[21]
Choudhary, A., Fatima, S., & Panigrahi, B. K. (2022, August). Passive Thermal Imaging-based Fault Detection in Induction Motor Under Varying Speed Conditions. In 2022 IEEE 2nd International Conference on Sustainable Energy and Future Electric Transportation (SeFeT) (pp. 1-6). IEEE.
[22]
Cocoma-Ortega, J. A., & Martinez-Carranza, J. (2022). A compact CNN approach for drone localisation in autonomous drone racing. Journal of Real-Time Image Processing, 19(1), 73-86.
[23]
Choudhary, A., Mian, T., Fatima, S., & Panigrahi, B. K. (2022). Passive Thermography Based Bearing Fault Diagnosis using Transfer Learning with Varying Working Conditions. IEEE Sensors Journal.

Cited By

View all
  • (2023)Intelligent Diagnosis of Bearing Fault Based on Voiceprint2023 5th International Conference on Machine Learning, Big Data and Business Intelligence (MLBDBI)10.1109/MLBDBI60823.2023.10481918(347-350)Online publication date: 15-Dec-2023

Index Terms

  1. Mel-spectrogram based Approach for Fault Detection in Ball Bearing using Convolutional Neural Network

    Recommendations

    Comments

    Information & Contributors

    Information

    Published In

    cover image ACM Other conferences
    ICECC '23: Proceedings of the 2023 6th International Conference on Electronics, Communications and Control Engineering
    March 2023
    316 pages
    ISBN:9798400700002
    DOI:10.1145/3592307
    Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].

    Publisher

    Association for Computing Machinery

    New York, NY, United States

    Publication History

    Published: 14 August 2023

    Permissions

    Request permissions for this article.

    Check for updates

    Author Tags

    1. Fault diagnosis
    2. Mel frequency
    3. acoustic signal
    4. deep learning
    5. human hearing

    Qualifiers

    • Research-article
    • Research
    • Refereed limited

    Conference

    ICECC 2023

    Contributors

    Other Metrics

    Bibliometrics & Citations

    Bibliometrics

    Article Metrics

    • Downloads (Last 12 months)25
    • Downloads (Last 6 weeks)5
    Reflects downloads up to 17 Feb 2025

    Other Metrics

    Citations

    Cited By

    View all
    • (2023)Intelligent Diagnosis of Bearing Fault Based on Voiceprint2023 5th International Conference on Machine Learning, Big Data and Business Intelligence (MLBDBI)10.1109/MLBDBI60823.2023.10481918(347-350)Online publication date: 15-Dec-2023

    View Options

    Login options

    View options

    PDF

    View or Download as a PDF file.

    PDF

    eReader

    View online with eReader.

    eReader

    HTML Format

    View this article in HTML Format.

    HTML Format

    Figures

    Tables

    Media

    Share

    Share

    Share this Publication link

    Share on social media