Intelligent Diagnosis of Bearing Faults Using Feature Selection Based on Minimum Redundancy Maximum Relevance and Neural Network Optimization with Particle Swarm Method
DOI:
https://doi.org/10.31185/wjes.Vol14.Iss2.768Keywords:
Condition monitoring, metaheuristic, feature ranking, PSOAbstract
Rolling element bearings play a crucial supporting role in rotating machines in many manufacturing processes. The failure of rolling bearings can result in catastrophic damage and human casualties, and their condition has a direct impact on the safe functioning of rotating machinery. Numerous bearing detection techniques have been designed to prevent such outcomes and avoid unplanned downtime. Techniques that have no dependence on the manual selection of attributes or the classifier parameters are still required. In order to meet this requirement, the current method incorporates the following algorithms: Max Relevance Min Redundancy (mRMR) for automated feature ranking, Artificial Neural Network (ANN) for bearing condition categorization, and Particle Swarm Optimization (PSO) for tuning the ANN hyperparameters, including the hidden layer size, the number of neurons in each layer, and the learning rate. The performance of three training algorithms was compared, and the Scaled Conjugate Gradient algorithm was selected based on its high results. The mRMR utilizes the statistical characteristics extracted from the time domain to organize bearing categories according to their relevance, and the PSO adjusts the ANN classifier's hyperparameters to improve its performance. The outcomes demonstrate that this approach successfully ranks the features, adjusts the hyperparameters, and improves classification performance with high accuracy.
References
A. K. S. Jardine, D. Lin, and D. Banjevic, “A review on machinery diagnostics and prognostics implementing condition-based maintenance,” Oct. 2006. doi: 10.1016/j.ymssp.2005.09.012.
L. Ciabattoni, F. Ferracuti, A. Freddi, and A. Monteriu, “Statistical Spectral Analysis for Fault Diagnosis of Rotating Machines,” IEEE Transactions on Industrial Electronics, vol. 65, no. 5, pp. 4301–4310, May 2018, doi: 10.1109/TIE.2017.2762623.
V. Tra, J. Kim, S. A. Khan, and J. M. Kim, “Bearing fault diagnosis under variable speed using convolutional neural networks and the stochastic diagonal levenberg-marquardt algorithm,” Sensors (Switzerland), vol. 17, no. 12, Dec. 2017, doi: 10.3390/s17122834.
X. Zhang, Q. Miao, H. Zhang, and L. Wang, “A parameter-adaptive VMD method based on grasshopper optimization algorithm to analyze vibration signals from rotating machinery,” Mech Syst Signal Process, vol. 108, pp. 58–72, Aug. 2018, doi: 10.1016/j.ymssp.2017.11.029.
M. Cerrada et al., “A review on data-driven fault severity assessment in rolling bearings,” Jan. 15, 2018, Academic Press. doi: 10.1016/j.ymssp.2017.06.012.
D. Wang and K. L. Tsui, “Statistical modeling of bearing degradation signals,” IEEE Trans Reliab, vol. 66, no. 4, pp. 1331–1344, Dec. 2017, doi: 10.1109/TR.2017.2739126.
V. F. Rodriguez-Galiano, J. A. Luque-Espinar, M. Chica-Olmo, and M. P. Mendes, “Feature selection approaches for predictive modelling of groundwater nitrate pollution: An evaluation of filters, embedded and wrapper methods,” Science of the Total Environment, vol. 624, pp. 661–672, May 2018, doi: 10.1016/j.scitotenv.2017.12.152.
S. E. Pandarakone, Y. Mizuno, and H. Nakamura, “A comparative study between machine learning algorithm and artificial intelligence neural network in detecting minor bearing fault of induction motors,” Energies (Basel), vol. 12, no. 11, 2019, doi: 10.3390/en12112105.
K. H. Hui, C. S. Ooi, M. H. Lim, M. S. Leong, and S. M. Al-Obaidi, “An improved wrapper-based feature selection method for machinery fault diagnosis,” PLoS One, vol. 12, no. 12, Dec. 2017, doi: 10.1371/journal.pone.0189143.
M. Peña et al., “Feature engineering based on ANOVA, cluster validity assessment and KNN for fault diagnosis in bearings,” in Journal of Intelligent and Fuzzy Systems, IOS Press, 2018, pp. 3451–3462. doi: 10.3233/JIFS-169525.
P. Shunmugapriya and S. Kanmani, “A hybrid algorithm using ant and bee colony optimization for feature selection and classification (AC-ABC Hybrid),” Swarm Evol Comput, vol. 36, pp. 27–36, Oct. 2017, doi: 10.1016/j.swevo.2017.04.002.
A. Sharma, M. Amarnath, and P. K. Kankar, “Feature extraction and fault severity classification in ball bearings,” JVC/Journal of Vibration and Control, vol. 22, no. 1, pp. 176–192, Jan. 2016, doi: 10.1177/1077546314528021.
X. Yan and M. Jia, “A novel optimized SVM classification algorithm with multi-domain feature and its application to fault diagnosis of rolling bearing,” Neurocomputing, vol. 313, pp. 47–64, Nov. 2018, doi: 10.1016/j.neucom.2018.05.002.
M. Imane, C. Rahmoune, and D. Benazzouz, “Rolling bearing fault feature selection based on standard deviation and random forest classifier using vibration signals,” Advances in Mechanical Engineering, vol. 15, no. 4, Apr. 2023, doi: 10.1177/16878132231168503.
X. Liang, J. Yao, W. Zhang, and Y. Wang, “A Novel Fault Diagnosis of a Rolling Bearing Method Based on Variational Mode Decomposition and an Artificial Neural Network,” Applied Sciences (Switzerland), vol. 13, no. 6, Mar. 2023, doi: 10.3390/app13063413.
Y. Keshun, Q. Guangqi, and G. Yingkui, “Optimizing prior distribution parameters for probabilistic prediction of remaining useful life using deep learning,” Reliab Eng Syst Saf, vol. 242, p. 109793, 2024.
J. Zhou, K. Zhou, G. Zhang, F. Neri, W. Shen, and W. Jin, “A data-driven optimisation method for a class of problems with redundant variables and indefinite objective functions,” Inf Sci (N Y), vol. 656, p. 119899, 2024.
M. Unal, M. Onat, M. Demetgul, and H. Kucuk, “Fault diagnosis of rolling bearings using a genetic algorithm optimized neural network,” Measurement (Lond), vol. 58, pp. 187–196, Dec. 2014, doi: 10.1016/j.measurement.2014.08.041.
D. Kolar, D. Lisjak, M. Pajak?, and M. Gudlin, “Intelligent fault diagnosis of rotary machinery by convolutional neural network with automatic hyper-parameters tuning using bayesian optimization,” Sensors, vol. 21, no. 7, Apr. 2021, doi: 10.3390/s21072411.
J. F. Chen, Q. H. Do, and H. N. Hsieh, “Training artificial neural networks by a hybrid PSO-CS Algorithm,” Algorithms, vol. 8, no. 2, pp. 292–308, 2015, doi: 10.3390/a8020292.
B. D. Center, “Case western reserve university bearing data,” 2013.
W. Shen, M. Xiao, Z. Wang, and X. Song, “Rolling Bearing Fault Diagnosis Based on Support Vector Machine Optimized by Improved Grey Wolf Algorithm,” Sensors, vol. 23, no. 14, Jul. 2023, doi: 10.3390/s23146645.
V. K. Verma, K. Saxena, and U. Banodha, “Analysis Effect of K Values Used in K Fold Cross Validation for Enhancing Performance of Machine Learning Model with Decision Tree,” in International Advanced Computing Conference, Springer, 2023, pp. 374–396.
T. Gao, J. Yang, W. Wang, and X. Fan, “A domain feature decoupling network for rotating machinery fault diagnosis under unseen operating conditions,” Reliab Eng Syst Saf, vol. 252, p. 110449, 2024.
A. Alhams, A. Abdelhadi, Y. Badri, S. Sassi, and J. Renno, “Enhanced Bearing Fault Diagnosis Through Trees Ensemble Method and Feature Importance Analysis,” Journal of Vibration Engineering and Technologies, Dec. 2024, doi: 10.1007/s42417-024-01405-0.
H. Al Bugharbee, H. Samaka, and S. L. Zubaidi, “Diagnosis of air compressor condition using minimum redunduncy maximum relevance (mrmr) algorithim and distance metric based classification,” Diagnostyka, vol. 22, no. 4, pp. 25–32, 2021, doi: 10.29354/diag/143762.
U. Parmar and D. H. Pandya, “Experimental investigation of cylindrical bearing fault diagnosis with SVM,” in Materials Today: Proceedings, Elsevier Ltd, 2021, pp. 1286–1290. doi: 10.1016/j.matpr.2020.11.327.
N. Ketkar, J. Moolayil, N. Ketkar, and J. Moolayil, “Convolutional neural networks,” Deep learning with Python: learn best practices of deep learning models with PyTorch, pp. 197–242, 2021.
X. Wang, Y. Liu, and H. Xin, “Bond strength prediction of concrete-encased steel structures using hybrid machine learning method,” Structures, vol. 32, pp. 2279–2292, Aug. 2021, doi: 10.1016/j.istruc.2021.04.018.
D. Kolar, D. Lisjak, M. Pajak?, and M. Gudlin, “Intelligent fault diagnosis of rotary machinery by convolutional neural network with automatic hyper-parameters tuning using bayesian optimization,” Sensors, vol. 21, no. 7, Apr. 2021, doi: 10.3390/s21072411.
J. Kennedy and R. Eberhart, “Particle swarm optimization,” in Proceedings of ICNN’95-international conference on neural networks, ieee, 1995, pp. 1942–1948.
M. Süpürtülü, A. Hatipoğlu, and E. Yılmaz, “An Analytical Benchmark of Feature Selection Techniques for Industrial Fault Classification Leveraging Time-Domain Features,” Applied Sciences (Switzerland), vol. 15, no. 3, Feb. 2025, doi: 10.3390/app15031457.
F. Althobiani, “A Novel Framework for Robust Bearing Fault Diagnosis: Preprocessing, Model Selection, and Performance Evaluation,” IEEE Access, vol. 12, pp. 59018–59036, 2024, doi: 10.1109/ACCESS.2024.3390234.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Mohammed Mutar Alaidi, Hussein Al-Bugharbee
This work is licensed under a Creative Commons Attribution 4.0 International License.
