Hybrid Approach for Bearing Fault Diagnosis in Induction Motors Based on Isolation Forest and Ensemble Learning
Article Sidebar
Main Article Content
Abstract
Rolling element bearings are fundamental parts of rotating machinery, and their sudden breakdown may cause abnormal vibrations, an unplanned production halt, and higher maintenance costs. To address this problem, this paper presents a hybrid data-driven approach for the automatic diagnosis and classification of bearing faults using vibration signals from the IMS dataset. The proposed method first divides the raw vibration signals into fixed-length windows and computes seven statistical features to characterise the signals. An unsupervised Isolation Forest technique is then used to detect anomalous signal segments, providing an early warning of potential faults. Thus, it does not require prior knowledge of the normal condition for fault detection. Subsequently, the detected anomalies are classified using two ensemble-based supervised learning models: Extra Trees and XGBoost. The experimental results indicate that the tree-based ensemble classifiers outperform the other models tested. Specifically, XGBoost achieves an F1 score of 97. 41%, whereas Extra Trees achieves an F1 score of nearly 97%, indicating its high potential for accurately detecting different types of bearing faults. The results confirm that the proposed hybrid two-stage model is an efficient and reliable tool for bearing fault diagnosis, supporting early fault detection, and enhancing system reliability in industrial settings.
Downloads
Article Details
Section
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
How to Cite
References
G A Machine Learning Framework for Bearing Fault Detection in Three-Phase Induction Motors, 2024.
DOI: http://doi.org//10.1109/SGRE59715.2024.10429024
Supervised Contrastive Learning for Electric Motor Bearing Fault Detection, 2024. DOI: http://doi.org//10.1109/ICEM60801.2024.10700325
AI-Based Speed Adaptive Fault Diagnosis in Induction Motors Using Vibration Signal, 2024. DOI: http://doi.org//10.1109/FIT63703.2024.10838415
Comparative Analysis of Machine Learning Techniques for Bearing Fault Classification, 2023.DOI: https://doi.org//10.24874/ti.1749.09.24.12
Detection of Simultaneous Bearing Faults Fusing Cross Correlation with Multikernel SVM, 2023. DOI: https://doi.org//10.1109/JSEN.2023.3276022
Low-Complexity Vibration-Based Condition Monitoring for Rolling Bearings, 2025. DOI: http://doi.org//10.1109/OJIM.2025.3589700
R. Hussain, M. Alshaikh Saleh and S. S. Refaat, "Various Faults Classification of Industrial Application of Induction Motors Using Supervised Machine Learning: A Comprehensive Review," in IEEE Access, vol. 13, pp. 146649-146675, 2025,DOI: https://doi.org//10.1109/ACCESS.2025.3600570
S. Djaballah et al., “A hybrid LSTM random forest model with grey wolf optimization for enhanced detection of multiple bearing faults,” Sci. Rep., vol. 14, no. 23997, pp. 1–17, Oct. 2024,DOI: https://doi.org//10.1038/s41598-024-75174-x
G. Xu, M. Liu, Z. Jiang, D. Soffker, and W. Shen, “Bearing fault diagnosis method based on deep convolutional neural network and random forest ensemble learning,” Sensors, vol. 19, no. 5, Art. no. 1088, Mar. 2019, DOI: https://doi.org//10.3390/s19051088
Z. Xiong, C. Shen, and K. Zhang, “A hybrid deep-learning model for fault diagnosis of rolling bearings,” Measurement, vol. 169, p. 108502, Feb. 2021, DOI: https://doi.org//10.1016/j.measurement.2020.108502
Y. Wang, F. Liu, and A. Zhu, “Bearing fault diagnosis based on a hybrid classifier ensemble approach and the improved Dempster-Shafer theory,” Sensors, vol. 19, no. 9, p. 2097, May 2019,
DOI: https://doi.org//10.3390/s19092097
L. C. Brito, G. A. Susto, J. N. Brito, and M. A. V. Duarte, “Fault detection of bearing: An unsupervised machine learning approach exploiting feature extraction and dimensionality reduction,” Informatics, vol. 8, no. 4, p. 85, Nov. 2021, DOI: https://doi.org//10.3390/informatics8040085
S. Zhang, R. Yan, Z. Chen, K. Mao, P. Wang, and R. X. Gao, “Insights into modern machine learning approaches for bearing fault classification: A systematic literature review,” Results Eng., vol. 23, p. 102700, Sep. 2024, DOI: https://doi.org//10.1016/j.rineng.2024.102700
K. Kim, "Fuzzy anomaly scores for Isolation Forest," Applied Soft Computing, vol. 166, p. 112193, 2024, DOI: https://doi.org/10.1016/j.asoc.2024.112193
A. El Bilali, T. Abdeslam, N. Ayoub, H. Lamane, M. A. Ezzaouini, and A. Elbeltagi, "An interpretable machine learning approach based on DNN, SVR, Extra Tree, and XGBoost models for predicting daily pan evaporation," J. Environ. Manage., vol. 327, p. 116890, Feb. 2023, DOI: http://doi.org//10.1016/j.jenvman.2022.116890
T. Chen and C. Guestrin, "XGBoost: A scalable tree boosting system," in Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Francisco, CA, USA, 2016, pp. 785-794, DOI: https://doi.org//10.1145/2939672.2939785
J. Guo, Q. He, D. Zhen, and F. Gu, “Intelligent fault detection for rotating machinery using cyclic morphological modulation spectrum and hierarchical Teager permutation entropy,” IEEE Transactions on Industrial Informatics, vol. 19, no. 4, pp. 6196–6208, Apr. 2023. DOI: http://doi.org//10.1109/TII.2022.3185293
J. Li, W. Luo, and M. Bai, "Review of research on signal decomposition and fault diagnosis of rolling bearing based on vibration signal," Measurement Science and Technology, vol. 35, no. 9, p. 092001, Sep. 2024, DOI: http://doi.org//10.1088/1361-6501/ad4eff
J. Lee, H. Qiu, G. Yu, and J. Lin, "IMS Bearing Data Set," NASA Open Data Portal, NASA Ames Research Centre, Moffett Field, CA, USA, 2007 (Updated 2024). Available: data.nasa.gov (Accessed: August 2025).