Enhancing gearbox condition monitoring using randomized singular value decomposition and K-nearest neighbor

##plugins.themes.bootstrap3.article.main##

##plugins.themes.bootstrap3.article.sidebar##

Published Jun 27, 2024
Adel Afia Mocnef Soualhi Fawzi Gougam Walid Touzout Abdassamad Ait-Chikh Mounir Meloussi

Abstract

Efficient gear and bearing diagnosis has become a critical requirement across diverse industrial applications precisely due to their complex design and exposure to difficult operating conditions, which predispose them to frequent failure. Early fault identification remains problematic, as defects are commonly obscured by extensive background noise. Moreover, the exponential increases in gearbox data further complicate the defect classification process, confusing even the most sophisticated algorithms and significantly making the procedure time consuming. Singular Value Decomposition (SVD) has proved to be highly efficient in signal denoising, stability preservation, and feature extraction reliably under varying conditions, filtering out non-linear signals to reconstruct relevant features only. However, its considerable computation time necessitates exploring alternatives like Randomized SVD (RSVD) to mitigate processing time while maintaining classification accuracy. In this work, an intelligent algorithm for gear and bearing fault diagnosis is developed, incorporating Maximal Overlap Discrete Wavelet Packet Transform (MODWPT) and Time-Domain Features for feature extraction. RSVD is employed for signal denoising and feature reconstruction, while K-Nearest Neighbor (KNN) for feature classification. The combined techniques ensure enhanced diagnostic accuracy, addressing critical challenges in industrial maintenance and performance optimization.

How to Cite

Afia, A., Soualhi, M., Gougam, F. ., Touzout , W. ., Ait-Chikh, A. ., & Meloussi, M. . (2024). Enhancing gearbox condition monitoring using randomized singular value decomposition and K-nearest neighbor. PHM Society European Conference, 8(1), 7. https://doi.org/10.36001/phme.2024.v8i1.4108
Abstract 199 | PDF Downloads 149

##plugins.themes.bootstrap3.article.details##

Keywords

Fault diagnosis, Gearbox, Feature extraction, Rotating machines

References
Adel, A., Hand, O., Fawzi, G., Walid, T., Chemseddine, R., & Djamel, B. (2022). Gear fault detection, identification and classification using mlp neural network. In Recent advances in structural health monitoring and engineering structures: Select proceedings of shm and es 2022 (pp. 221–234). Springer.

Afia, A., Gougam, F., Rahmoune, C., Touzout, W., Ouelmokhtar, H., & Benazzouz, D. (2023). Gearbox fault diagnosis using remd, eo and machine learning classifiers. Journal of Vibration Engineering & Technologies, 1–25.

Afia, A., Gougam, F., Rahmoune, C., Touzout, W., Ouelmokhtar, H., & Benazzouz, D. (2024). Intelligent fault classification of air compressors using harris hawks optimization and machine learning algorithms. Transactions of the Institute of Measurement and Control, 46(2), 359–378.

Afia, A., Gougam, F., Touzout, W., Rahmoune, C., Ouelmokhtar, H., & Benazzouz, D. (2023). Spectral proper orthogonal decomposition and machine learning algorithms for bearing fault diagnosis. Journal of the Brazilian Society of Mechanical Sciences and Engineering, 45(10), 550.

Anggoro, D. A., & Kurnia, N. D. (2020). Comparison of accuracy level of support vector machine (svm) and k-nearest neighbors (knn) algorithms in predicting heart disease. International Journal, 8(5), 1689–1694.

Benaggoune, K., Meraghni, S., Ma, J., Mouss, L., & Zerhouni, N. (2020). Post prognostic decision for predictive maintenance planning with remaining useful life uncertainty. In 2020 prognostics and health management conference (phm-besanc¸on) (pp. 194–199).

Chakraborty, S., Chatterjee, S., Dey, N., Ashour, A. S., & Hassanien, A. E. (2017). Comparative approach between singular value decomposition and randomized singular value decomposition-based watermarking. Intelligent techniques in signal processing for multimedia security, 133–149.

de Azevedo, H. D. M., Ara´ujo, A. M., & Bouchonneau, N. (2016). A review of wind turbine bearing condition monitoring: State of the art and challenges. Renewable and Sustainable Energy Reviews, 56, 368–379.

Gilles, J. (2013). Empirical wavelet transform. IEEE transactions on signal processing, 61(16), 3999–4010.

Gougam, F., Afia, A., Aitchikh, M., Touzout, W., Rahmoune, C., & Benazzouz, D. (2024). Computer numerical control machine tool wear monitoring through a data-driven approach. Advances in Mechanical Engineering, 16(2), 16878132241229314.

Gougam, F., Afia, A., Soualhi, A., Touzout, W., Rahmoune, C., & Benazzouz, D. (2024). Bearing faults classification using a new approach of signal processing combined with machine learning algorithms. Journal of the Brazilian Society of Mechanical Sciences and Engineering, 46(2), 65.

Gougam, F., Rahmoune, C., Benazzouz, D., Zair, M. I., & Afia, A. (2018). Early bearing fault detection under different working conditions using singular value decomposition (svd) and adaptatif neuro fuzzy inference system (anfis). In International conference on advanced mechanics and renewable energy (icamre). p (pp. 28–29).

Halko, N., Martinsson, P.-G., & Tropp, J. A. (2011). Finding structure with randomness: Probabilistic algorithms for constructing approximate matrix decompositions. SIAM review, 53(2), 217–288.

Song, P., Trzasko, J. D., Manduca, A., Qiang, B., Kadirvel, R., Kallmes, D. F., & Chen, S. (2017). Accelerated singular value-based ultrasound blood flow clutter filtering with randomized singular value decomposition and randomized spatial downsampling. IEEE transactions on ultrasonics, ferroelectrics, and frequency control, 64(4), 706–716.

Soualhi, M., Nguyen, K. T., & Medjaher, K. (2020). Pattern recognition method of fault diagnostics based on a new health indicator for smart manufacturing. Mechanical Systems and Signal Processing, 142, 106680.

Soualhi, M., Nguyen, K. T., Soualhi, A., Medjaher, K., & Hemsas, K. E. (2019). Health monitoring of bearing and gear faults by using a new health indicator extracted from current signals. Measurement, 141, 37–51.

Syed, S. H., & Muralidharan, V. (2022). Feature extraction using discrete wavelet transform for fault classification of planetary gearbox–a comparative study. Applied Acoustics, 188, 108572.

Tahi, M., Miloudi, A., Dron, J., & Bouzouane, B. (2020). Decision tree and feature selection by using genetic wrapper for fault diagnosis of rotating machinery. Australian Journal of Mechanical Engineering.

Too, J., Abdullah, A. R., Mohd Saad, N., & Tee, W. (2019). Emg feature selection and classification using a pbestguide binary particle swarm optimization. Computation, 7(1), 12.

Too, J., Abdullah, A. R., & Saad, N. M. (2019). Classification of hand movements based on discrete wavelet transform and enhanced feature extraction. International Journal of Advanced Computer Science and Applications, 10(6).

Touzout, W., Benazzouz, D., Gougam, F., Afia, A., & Rahmoune, C. (2020). Hybridization of time synchronous averaging, singular value decomposition, and adaptive neuro fuzzy inference system for multi-fault bearing diagnosis. Advances in Mechanical Engineering, 12(12), 1687814020980569.
Section
Technical Papers