BEARING FAULT DETECTION BY USING AUTOENCODER CONVOLUTIONAL NEURAL NETWORK

Authors

  • M. K. Kysarin State University of Trade and Economics, Kyiv, Ukraine, Ukraine

DOI:

https://doi.org/10.15588/1607-3274-2025-2-10

Keywords:

bearing fault, autoencoder, convolutional neural network, zero-shot learning, binary classification

Abstract

Context. Bearings are an important part for the functioning of various means of transportation. They have the property of wear and failure, which requires high-quality and timely detection of faults. Failures are not always easy to detect, so the use of traditional detection methods may not be effective enough. The use of machine learning methods well-suited to the task can effectively solve the problem of detecting bearing faults. The object of study is the process of non-destructive diagnosis of bearings. The subject of study is methods of selecting hyperparameters and other optimization for building a diagnostic model based on a neural network according to observations.
Objective. The goal of the work is to create a model based on a neural network for detecting bearing faults based on the ZSL.
Method. A proposed filter smooths the data, preserving key characteristics such as peaks and slopes, and eliminates noise without significantly distorting the signal. A normalization method vibration data is proposed, which consists of centering the data and distributing the amplitude within optimal limits, contributing to the correct processing of this data by the model architecture. A model based on a neural network is proposed to detect bearing faults by data processing and subsequent binary classification of their vibrations. The proposed model works by compressing the vibration data into a latent representation and its subsequent recovery, calculating the error between the recovered and original data, and determining the difference between the errors of healthy and faulty bearing vibration data. The Zero-Shot Learning machine learning method involves training, validating the model only on healthy vibration data, and testing the model only on faulty vibration data. Due to the proposed machine learning method, the model based on a neural network is able to detect faulty bearings present in the investigated fault class and theoretically new fault classes, that is, the model can detect different classes of data that it did not see during training. The architecture of the model is built on the convolutional and max-pooling layers of the encoder, and the reverse convolutional layers for the decoder. The best hyperparameters of the model are selected using a special method.
Results. Using the Pytorch library, a model capable of binary classification of healthy and faulty bearings was obtained through training, validation, and testing in the Kaggle software environment.
Conclusions. Testing of the constructed model architecture confirmed the model's ability to classify healthy and fault bearings binaryly, allowing it to be recommended for use in practice to detect bearing faults. Prospects for further research may include testing the model through integration into predictive maintenance systems for timely fault detection

Author Biography

M. K. Kysarin, State University of Trade and Economics, Kyiv, Ukraine

Student of the Faculty of Information Technologies

References

Mao W., He J., Li Y. et al. Bearing fault diagnosis with auto-encoder extreme learning machine: a comparative study [Electronic resource], Journal of Mechanical Engineering Science, 2017, Vol. 231, № 8, pp. 1560–1578. Mode of access: https://journals.sagepub.com/doi/10.1177/0954406216675896

Huang Z., Song X., Liao Z. et al. Bearing fault feature enhancement and diagnosis based on Savitzky-Golay filtering Gramian angular field [Electronic resource], IEEE Access, 2024, Vol. 12, pp. 87991–88005. Mode of access: https://ieeexplore.ieee.org/document/10570176

Chen X., Guo Y., Na J. Encoder signal-based optimized Savitzky-Golay and adaptive spectrum editing for feature extraction of rolling element bearing under low-speed and variable-speed conditions [Electronic resource], ISA Transactions, 2024, Vol. 154, pp. 371–388. Mode of access: https://www.sciencedirect.com/science/article/abs/pii/S0019057824003677?via%3Dihub

Wang Y., Li D., Li L. et al. A novel deep learning framework for rolling bearing fault diagnosis enhancement using VAE-augmented CNN model [Electronic resource], Heliyon, 2024, Vol. 10, № 15. Mode of access: https://doi.org/10.1016/j.heliyon.2024.e35407

Wang M., Yu J., Leng H.et al. Bearing fault detection by using graph autoencoder and ensemble learning [Electronic resource], Scientific Reports, 2024, Vol. 14, № 1, pp. 1–15. Mode of access: https://www.nature.com/articles/s41598-024-55620-6#citeas

Toma R. N., Piltan F., Kim J.-M. A deep autoencoder-based convolution neural network framework for bearing fault classification in induction motors [Electronic resource], Sensors, 2021, Vol. 21, № 24. Mode of access: https://www.mdpi.com/1424-8220/21/24/8453

Zhao Y., Hao H., Chen Y. et al. Novelty detection and fault diagnosis method for bearing faults based on the hybrid deep autoencoder network [Electronic resource], Electronics, 2023,Vol. 12, № 13. Mode of access: https://www.mdpi.com/2079–9292/12/13/2826

Toma R. N., Piltan F., Im K. et al. A bearing fault classification framework based on image encoding techniques and a convolutional neural network under different operating conditions [Electronic resource], Sensors, 2022, Vol. 22, № 13. Mode of access: https://www.mdpi.com/1424-8220/22/13/4881

Yuan F., Xun P., Wang W. et al. Bearing fault diagnosis based on auto-encoder combined with CNN [Electronic resource], Fuzzy Systems and Data Mining IX : Proceedings of the Fuzzy Systems and Data Mining Conference, 18–20 November 2023 : proceedings. Xiamen, IOS Press, 2023, Vol. 354, pp. 334–344. Mode of access: https://ebooks.iospress.nl/doi/10.3233/FAIA231039

Rao C. A survey of autoencoder and convolutional neural network based methods for fault diagnosis [Electronic resource], Advances in Engineering Technology Research, 2024, Vol. 11, № 1, pp. 516–528. Mode of access: https://madisonproceedings.com/index.php/aetr/article/view/2529

Zhang S., Zhang S., Wang B.et al. Deep learning algorithms for bearing fault diagnostics – a comprehensive review [Electronic resource], IEEE Access, 2020, Vol. 8, pp. 29857–29881. Mode of access: https://ieeexplore.ieee.org/document/8988271

Gholamy A., V. Kreinovich, O. Kosheleva Why 70/30 or 80/20 relation between training and testing sets: a pedagogical explanation [Electronic resource], Mode of access: https://api.semanticscholar.org/CorpusID:7467506

Lee D. H. Choo, J. Jeong GCN-based LSTM Autoencoder with self-attention for bearing fault diagnosis [Electronic resource], Sensors, 2024, Vol. 24, № 15. Mode of access: https://www.mdpi.com/1424-8220/24/15/4855

Sohaib M., Kim J.-M. Reliable fault diagnosis of rotary machine bearings using a stacked sparse autoencoder-based deep neural network [Electronic resource], Shock and Vibration, 2018, Vol. 2018, № 1. Mode of access: https://onlinelibrary.wiley.com/doi/10.1155/2018/2919637

Gu Y., Cao J., Song X.et al. A denoising autoencoder-based bearing fault diagnosis system for time-domain vibration signals [Electronic resource], Wireless Communications and Mobile Computing, 2021, Vol. 2021, № 1. Mode of access: https://onlinelibrary.wiley.com/doi/10.1155/2021/9790053

Althubaiti A., Elasha F., Teixeira J. A. Fault diagnosis and health management of bearings in rotating equipment based on vibration analysis – a review [Electronic resource], Journal of Vibroengineering, 2021, Vol. 24, № 1, pp. 46–74. Mode of access: https://www.extrica.com/article/22100

Downloads

Published

2025-06-29

How to Cite

Kysarin, M. K. (2025). BEARING FAULT DETECTION BY USING AUTOENCODER CONVOLUTIONAL NEURAL NETWORK. Radio Electronics, Computer Science, Control, (2), 116–125. https://doi.org/10.15588/1607-3274-2025-2-10

Issue

Section

Neuroinformatics and intelligent systems