Enhancing Predictive Maintenance Accuracy for Rotary Machine Vibration Signals with XGBoost-RFE Based Feature Selection
Received: 11 August 2025 | Revised: 13 September 2025 | Accepted: 6 October 2025 | Online: 7 December 2025
Corresponding author: Magdy Abd Elghany M. Metwaly
Abstract
This study proposes a model of a rotary machine's fault diagnosis system based on vibration signal analysis under Improved eXtreme Gradient Boosting-Recursive Feature Elimination (XGBoost-RFE). A 3D dataset of vibration signals is collected from healthy and faulty induction motors. The Empirical Mode Decomposition (EMD) technique is used to perform signal conditioning. The de-noised signals are obtained to extract the multi-domain features. Finally, multiple classifiers, including K-Nearest Neighbor (KNN), Support Vector Machine (SVM), and eXtreme Gradient Boosting (XGBoost), are performed with different kernel settings at the classification step. The results indicate that a hybrid approach that combines time and frequency domain features and classifies them using XGBoost with a Gaussian kernel achieves the highest accuracy (99%) with the lowest error rate <1.3%.
Keywords:
SP, vibration-based sensor, sensor fusion, GXBoost, AI, ML, PCA, SVM, KNN, DLDownloads
References
S. Kar and V. Mukherjee, "Acoustic Signal Enhancement Using Deep Neural Networks," Engineering, Technology & Applied Science Research, vol. 15, no. 4, pp. 24259–24264, Aug. 2025. DOI: https://doi.org/10.48084/etasr.10571
B. P. Ho Thi and H. M. Dang, "An Experimental Study on the Bond Strength of Old and New Cementitious Materials," Engineering, Technology & Applied Science Research, vol. 15, no. 4, pp. 24265–24269, Aug. 2025. DOI: https://doi.org/10.48084/etasr.11056
A. Ibrahim Mansour, "Fault Detection in Underground Cables by Using Wavelet Technique (WT)," Journal of Al-Azhar University Engineering Sector, vol. 13, no. 48, pp. 1004–1014, July 2018. DOI: https://doi.org/10.21608/auej.2018.18978
S. Mohamed and M. Rohaim, "Multi-Class Intrusion Detection System using Deep Learning," Journal of Al-Azhar University Engineering Sector, vol. 18, no. 69, pp. 869–883, Oct. 2023. DOI: https://doi.org/10.21608/auej.2023.213003.1375
S. N. E. Ali, H. M. Sherif, S. M. Hassan, and A. A. E. R. El Marakby, "Long Bones X-Ray Fracture Classification Using Machine Learning," Journal of Al-Azhar University Engineering Sector, vol. 0, no. 0, pp. 121–133, July 2024. DOI: https://doi.org/10.21608/auej.2024.259630.1577
A. Mallak and M. Fathi, "Sensor and Component Fault Detection and Diagnosis for Hydraulic Machinery Integrating LSTM Autoencoder Detector and Diagnostic Classifiers," Sensors, vol. 21, no. 2, Jan. 2021, Art. no. 433. DOI: https://doi.org/10.3390/s21020433
F. Arellano-Espitia, M. Delgado-Prieto, A.-D. Gonzalez-Abreu, J. J. Saucedo-Dorantes, and R. A. Osornio-Rios, "Deep-Compact-Clustering Based Anomaly Detection Applied to Electromechanical Industrial Systems," Sensors, vol. 21, no. 17, Aug. 2021, Art. no. 5830. DOI: https://doi.org/10.3390/s21175830
H. Jin, A. Titus, Y. Liu, Y. Wang, and Z. Han, "Fault Diagnosis of Rotary Parts of a Heavy-Duty Horizontal Lathe Based on Wavelet Packet Transform and Support Vector Machine," Sensors, vol. 19, no. 19, Sept. 2019, Art. no. 4069. DOI: https://doi.org/10.3390/s19194069
Z. Zhu, L. Wang, G. Peng, and S. Li, "WDA: An Improved Wasserstein Distance-Based Transfer Learning Fault Diagnosis Method," Sensors, vol. 21, no. 13, June 2021, Art. no. 4394. DOI: https://doi.org/10.3390/s21134394
S. Safavi, M. A. Safavi, H. Hamid, and S. Fallah, "Multi-Sensor Fault Detection, Identification, Isolation and Health Forecasting for Autonomous Vehicles," Sensors, vol. 21, no. 7, Apr. 2021, Art. no. 2547. DOI: https://doi.org/10.3390/s21072547
J. R. Huerta-Rosales et al, "Short-Circuited Turn Fault Diagnosis in Transformers by Using Vibration Signals, Statistical Time Features, and Support Vector Machines on FPGA," Sensors, vol. 21, no. 11, May 2021, Art. no. 3598. DOI: https://doi.org/10.3390/s21113598
A. Moosavian, H. Ahmadi, and A. Tabatabaeefar, "814. Fault Diagnosis of Main Engine Journal Bearing Based on Vibration Analysis Using Fisher Linear Discriminant, K-nearest Neighbor and Support Vector Machine," Journal of Vibroengineering, vol. 14, no. 2, June 2012.
V. Martínez-Martínez, F. J. Gomez-Gil, J. Gomez-Gil, and R. Ruiz-Gonzalez, "An Artificial Neural Network Based Expert System Fitted with Genetic Algorithms for Detecting the Status of Several Rotary Components in Agro-Industrial Machines Using a Single Vibration Signal," Expert Systems with Applications, vol. 42, no. 17–18, pp. 6433–6441, Oct. 2015. DOI: https://doi.org/10.1016/j.eswa.2015.04.018
F.-C. Gu, J.-Y. Bian, C.-L. Hsu, H.-C. Chen, and S.-D. Lu, "Rotor Fault Identification of Induction Motor Based on Discrete Fractional Fourier Transform," in 2018 International Symposium on Computer, Consumer and Control (IS3C), Taichung, Taiwan, Dec. 2018, pp. 205–208. DOI: https://doi.org/10.1109/IS3C.2018.00059
R. S. Gunerkar and A. K. Jalan, "Classification of Ball Bearing Faults Using Vibro-Acoustic Sensor Data Fusion," Experimental Techniques, vol. 43, no. 5, pp. 635–643, Oct. 2019. DOI: https://doi.org/10.1007/s40799-019-00324-0
C.-J. Lin, W.-L. Chu, C.-C. Wang, C.-K. Chen, and I.-T. Chen, "Diagnosis of Ball-Bearing Faults Using Support Vector Machine Based on the Artificial Fish-swarm Algorithm," Journal of Low Frequency Noise, Vibration and Active Control, vol. 39, no. 4, pp. 954–967, Dec. 2020. DOI: https://doi.org/10.1177/1461348419861822
J. Lu, W. Qian, S. Li, and R. Cui, "Enhanced K-Nearest Neighbor for Intelligent Fault Diagnosis of Rotating Machinery," Applied Sciences, vol. 11, no. 3, Jan. 2021, Art. no. 919. DOI: https://doi.org/10.3390/app11030919
S. Paudyal, M. S. A. Atique, and C. X. Yang, "Local Maximum Acceleration Based Rotating Machinery Fault Classification Using KNN," in 2019 IEEE International Conference on Electro Information Technology (EIT), Brookings, SD, USA, May 2019, pp. 219–224. DOI: https://doi.org/10.1109/EIT.2019.8833788
Q. Wang, S. Wang, B. Wei, W. Chen, and Y. Zhang, "Weighted K-NN Classification Method of Bearings Fault Diagnosis with Multi-Dimensional Sensitive Features," IEEE Access, vol. 9, pp. 45428–45440, 2021. DOI: https://doi.org/10.1109/ACCESS.2021.3066489
C. Li, R.-V. Sánchez, G. Zurita, M. Cerrada, and D. Cabrera, "Fault Diagnosis for Rotating Machinery Using Vibration Measurement Deep Statistical Feature Learning," Sensors, vol. 16, no. 6, June 2016, Art. no. 895. DOI: https://doi.org/10.3390/s16060895
S. Aziz, M. Ahmed, S. Z. H. Naqvi, M. U. Khan, A. Imtiaz, and A. Waseem, "Machine Bearing Fault Diagnosis System using Tri-Axial Accelerometer," in 2020 International Conference on Electrical, Communication, and Computer Engineering (ICECCE), Istanbul, Turkey, June 2020, pp. 1–6. DOI: https://doi.org/10.1109/ICECCE49384.2020.9179326
Z. Shen, X. Chen, X. Zhang, and Z. He, "A Novel Intelligent Gear Fault Diagnosis Model Based on EMD and Multi-class TSVM," Measurement, vol. 45, no. 1, pp. 30–40, Jan. 2012. DOI: https://doi.org/10.1016/j.measurement.2011.10.008
Ghanshyam and P. Pandey, "A KNN-Based Intrusion Detection System for Enhanced Anomaly Detection in Industrial IoT Networks," International Journal of Innovative Research in Technology and Science, vol. 12, no. 6, pp. 1–7, 2024.
A. Kafeel et al., "An Expert System for Rotating Machine Fault Detection Using Vibration Signal Analysis," Sensors, vol. 21, no. 22, Nov. 2021, Art. no. 7587. DOI: https://doi.org/10.3390/s21227587
S. Kumar, A. Kumari, S. Priya, N. Bharti, D. Nandani, and M. Kumar, "Efficient Fault Classification in Rotating Machinery Using the K-Nearest Neighbor Algorithm," in 2024 IEEE International Conference on Smart Power Control and Renewable Energy (ICSPCRE), Rourkela, India, July 2024, pp. 1–4. DOI: https://doi.org/10.1109/ICSPCRE62303.2024.10675069
R. Tiwari, S. Bhalerao, S. Sahu, and K. Gupta, "A Hybrid System for Anomaly Detection in Industrial Big Data," in Advanced Signal Processing for Industry 4.0, Volume 2, I. A. Ansari and V. Bajaj, Eds. IOP Publishing, 2023, pp. 1-10. DOI: https://doi.org/10.1088/978-0-7503-5658-9ch10
S. K. Venkata and S. Rao, "Fault Detection of a Flow Control Valve Using Vibration Analysis and Support Vector Machine," Electronics, vol. 8, no. 10, Sept. 2019, Art. no. 1062. DOI: https://doi.org/10.3390/electronics8101062
M. Seera, M. L. D. Wong, and A. K. Nandi, "Classification of Ball Bearing Faults using a Hybrid Intelligent Model," Applied Soft Computing, vol. 57, pp. 427–435, Aug. 2017. DOI: https://doi.org/10.1016/j.asoc.2017.04.034
B. Li, M.-Y. Chow, Y. Tipsuwan, and J. C. Hung, "Neural-network-based Motor Rolling Bearing Fault Diagnosis," IEEE Transactions on Industrial Electronics, vol. 47, no. 5, pp. 1060–1069, Oct. 2000. DOI: https://doi.org/10.1109/41.873214
A. Nandy, "Statistical Methods for Analysis of Parkinson’s Disease Gait Pattern and Classification," Multimedia Tools and Applications, vol. 78, no. 14, pp. 19697–19734, July 2019. DOI: https://doi.org/10.1007/s11042-019-7310-4
W. Caesarendra and T. Tjahjowidodo, "A Review of Feature Extraction Methods in Vibration-Based Condition Monitoring and Its Application for Degradation Trend Estimation of Low-Speed Slew Bearing," Machines, vol. 5, no. 4, Sept. 2017, Art. no. 21. DOI: https://doi.org/10.3390/machines5040021
L. Marshall and D. Jensen, "Dataset of Single and Double Faults Scenarios using Vibration Signals from a Rotary Machine," Data in Brief, vol. 49, Aug. 2023, Art. no. 109358. DOI: https://doi.org/10.1016/j.dib.2023.109358
Downloads
How to Cite
License
Copyright (c) 2025 Magdy Abd Elghany M. Metwaly, Abd Elhady A. Ammar, Ghazal A. Fahmy, Mohamed Yasin I. Afifi
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain the copyright and grant the journal the right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) after its publication in ETASR with an acknowledgement of its initial publication in this journal.
