Deep Learning Based Fault Diagnosis for Predictive Maintenance of Industrial Rotating Machinery Using Vibration Signals

Aditya Bagus Santoso; Rina Oktavia Sari; Rafi Alfarizi Hidayat; Maya Fitri Handayani

Authors

Aditya Bagus Santoso Universitas Indonesia Author
Rina Oktavia Sari Universitas Indonesia Author
Rafi Alfarizi Hidayat Universitas Indonesia Author
Maya Fitri Handayani Universitas Indonesia Author

Keywords:

Predictive maintenance, Rotating machinery, Vibration signal, Bearing fault diagnosis, Deep learning.

Abstract

Purpose – This study evaluates vibration-based bearing fault diagnosis using a Deep Multilayer Perceptron (Deep MLP) and compares its performance with SVM-RBF and Random Forest using identical time-domain vibration features.

Methodology – A quantitative benchmark design used 128 balanced CWRU-derived observations representing Normal, Ball Fault, Inner Race Fault, and Outer Race Fault. Nine time-domain features were analyzed. Performance was estimated through repeated stratified 5-fold cross-validation with 10 repetitions, accuracy, macro precision, macro recall, macro F1-score, and Wilcoxon signed-rank tests.

Findings – Deep MLP achieved mean accuracy and macro F1-score of 99.53%. SVM-RBF and Random Forest each achieved 100.00%. The difference was statistically significant at p = 0.0256; therefore, vibration-feature discriminability was supported, while Deep MLP superiority was not supported.

Implications – Highly discriminative engineered vibration features can allow conventional classifiers to match or exceed deeper neural models with lower computational complexity.

Originality – The study provides a controlled comparison of Deep MLP, SVM-RBF, and Random Forest using identical features and repeated validation partitions, showing that deep-learning superiority depends on input representation and task structure.

References

Ahsan, M., Hassan, M. W., Rodríguez, J., & Abdelrahem, M. (2025). Enhanced fault diagnosis in rotating machinery using a hybrid CWT-LeNet-5-LSTM model: Performance across various load conditions. IEEE Access, 13, 1026–1045. https://doi.org/10.1109/ACCESS.2024.3522948

Ali, M. I., Lai, N. S., & Abdulla, R. (2024). Predictive maintenance of rotational machinery using deep learning. International Journal of Electrical and Computer Engineering, 14(1), 1112–1121. https://doi.org/10.11591/ijece.v14i1.pp1112-1121

Almutairi, K. M., Sinha, J. K., & Wen, H. (2024). Fault detection of rotating machines using poly-coherent composite spectrum of measured vibration responses with machine learning. Machines, 12(8), 573. https://doi.org/10.3390/machines12080573

Anshori, M. I., & Dhini, A. (2025). Fault detection of rotating machinery in the petrochemical industry using a deep learning based approach: TabNet-WGAN. Eastern-European Journal of Enterprise Technologies, 3(1[135]), 90–99. https://doi.org/10.15587/1729-4061.2025.332597

Atmaji, F. T. D., Jamasri, Yuniarto, H. A., & Miasa, I. M. (2025). Experimental investigation of shaft misalignment effects on bearing reliability through vibration signal analysis using machine learning and deep learning. Results in Engineering, 27, 106754. https://doi.org/10.1016/j.rineng.2025.106754

Bagri, I., Tahiry, K., Hraiba, A., Touil, A., & Mousrij, A. (2024). Vibration signal analysis for intelligent rotating machinery diagnosis and prognosis: A comprehensive systematic literature review. Vibration, 7(4), 1013–1062. https://doi.org/10.3390/vibration7040054

Das, O., Das, D. B., & Birant, D. (2023). Machine learning for fault analysis in rotating machinery: A comprehensive review. Heliyon, 9(6), e17584. https://doi.org/10.1016/j.heliyon.2023.e17584

Dong, Z., Zhao, D., & Cui, L. (2024). An intelligent bearing fault diagnosis framework: One-dimensional improved self-attention-enhanced CNN and empirical wavelet transform. Nonlinear Dynamics, 112, 6439–6459. https://doi.org/10.1007/s11071-024-09389-y

Gao, W., Fu, D., Yu, J., & Akoudad, Y. (2025). HDNAT: A Transformer-based fault diagnosis model for rotating machinery across varying damage degrees. IEEE Transactions on Instrumentation and Measurement, 74, 1–16. https://doi.org/10.1109/TIM.2025.3623791

Hu, J. (2025). Intelligent fault diagnosis method for rolling bearings based on SSA-CNN-Transformer. Highlights in Science, Engineering and Technology, 143, 107–118. https://doi.org/10.54097/qfj5xs82

Jiang, W., Zhou, R., & Jia, H. (2024). Research on mechanical equipment fault diagnosis and prediction technology based on vibration signal analysis. In 2024 International Conference on Power, Electrical Engineering, Electronics and Control (PEEEC) (pp. 494–498). IEEE. https://doi.org/10.1109/PEEEC63877.2024.00096

Jiang, Z., Liu, D., & Cui, L. (2024). Deep adaptively dynamic edge graph convolution network with attention weight and high-dimension affinity feature graph for rotating machinery fault diagnosis. Measurement Science and Technology. https://doi.org/10.1088/1361-6501/ad9e1d

Jorge, A. R. F., Gouveia, E. B., da Cunha, M. J. R., Cavallini, A. A., Jr., & Freitas, L. C. G. (2024). Rotodynamics multi-fault diagnosis through time domain parameter analysis with MLP: A comprehensive study. In 2024 International Workshop on Artificial Intelligence and Machine Learning for Energy Transformation (AIE). IEEE. https://doi.org/10.1109/AIE61866.2024.10561397

Jweri, A.-R. K., Ogaili, A. A. F., Amin, S. A., Khalaf, M. I., Al-Haddad, L. A., Jaber, A. A., & Karkhi, M. I. (2025). Enhancing predictive maintenance in energy systems using a hybrid Kolmogorov-Arnold Network with Short-Time Fourier Transform framework for rotating machinery. ASEAN Journal of Science and Engineering, 5(2), 465–494. https://doi.org/10.17509/ajse.v5i2.89023

Kang, J., Luo, Y., Wang, P., Wei, Y., & Zhou, Y. (2023). Fault diagnosis of rotating machinery under complex conditions based on multi-scale convolutional neural networks. Journal of Physics: Conference Series, 2658(1), 012038. https://doi.org/10.1088/1742-6596/2658/1/012038

Kibrete, F., Woldemichael, D. E., & Gebremedhen, H. S. (2025). Fault diagnosis of rotating machines based on combination of one-dimensional convolutional neural network and long short-term memory in variable working conditions. Journal of Engineering, 2025, 1670810. https://doi.org/10.1155/je/1670810

Li, J., & Bai, M. (2024). Review of research on signal decomposition and fault diagnosis of rolling bearing based on vibration signal. Measurement Science and Technology. https://doi.org/10.1088/1361-6501/ad4eff

Li, X., Tang, J., Zhang, J., Pang, P., & Hou, Y. (2025). An improved CS-Transformer for fault diagnosis of rotating machinery bearings under strong noise conditions. Latin American Journal of Solids and Structures, 22(9), e8697. https://doi.org/10.1590/1679-7825/e8697

Liu, D., Cui, L., & Cheng, W. (2024). Interpretable domain adaptation transformer: A transfer learning method for fault diagnosis of rotating machinery. Structural Health Monitoring. https://doi.org/10.1177/14759217241249656

Ma, J., Huang, J., Liu, S., Luo, J., & Jing, L. (2024). A self-attention Legendre graph convolution network for rotating machinery fault diagnosis. Sensors, 24(17), 5475. https://doi.org/10.3390/s24175475

Matania, O., Dattner, I., Bortman, J., Kenett, R. S., & Parmet, Y. (2024). A systematic literature review of deep learning for vibration-based fault diagnosis of critical rotating machinery: Limitations and challenges. Journal of Sound and Vibration, 590, 118562. https://doi.org/10.1016/j.jsv.2024.118562

Mayo, S. A., Rehman, S., & Cai, Z. (2024). High-accuracy gearbox fault detection using deep learning on vibrational data. Journal of Physics: Conference Series, 2853(1), 012066. https://doi.org/10.1088/1742-6596/2853/1/012066

Mrabti, A., Younes, R., Ouelaa, N., Kebabsa, T., & Ouelaa, Z. (2025). Robust fault detection and severity classification in rotating machinery using VMD-LSTM for limited data scenarios. Advances in Mechanical Engineering, 17. https://doi.org/10.1177/16878132251342909

Nguyen, T. H. T., Pham, N. V., & Hoang, Q. V. (2025). Bearing fault diagnosis by machine learning and deep learning-based models: A comparative study applying for HUST bearing dataset. Journal of Research on Army Science and Technology, 103, 31–39. https://doi.org/10.54939/1859-1043.j.mst.103.2025.31-39

Prawin, J. (2025). Deep learning neural networks with input processing for vibration-based bearing fault diagnosis under imbalanced data conditions. Structural Health Monitoring, 24(2), 883–908. https://doi.org/10.1177/14759217241246508

Rezazadeh, N., De Oliveira, M., Lamanna, G., Perfetto, D., & De Luca, A. (2025). WaveCORAL-DCCA: A scalable solution for rotor fault diagnosis across operational variabilities. Electronics, 14(15), 3146. https://doi.org/10.3390/electronics14153146

Siavash-Abkenari, N., Rahmani-Sane, G., Torkaman, H., & Alipoor, G. (2024). Exploring a cutting-edge framework for bearing fault detection: A synergistic approach integrating statistical analysis and deep learning methods. IEEE Journal of Emerging and Selected Topics in Industrial Electronics. https://doi.org/10.1109/JESTIE.2024.3373313

Song, B., Liu, Y., Fang, J., Liu, W., Zhong, M., & Liu, X. (2024). An optimized CNN-BiLSTM network for bearing fault diagnosis under multiple working conditions with limited training samples. Neurocomputing, 574, 127284. https://doi.org/10.1016/j.neucom.2024.127284

Su, H., Xiang, L., & Hu, A. (2024). Application of deep learning to fault diagnosis of rotating machineries. Measurement Science and Technology, 35(4), 042003. https://doi.org/10.1088/1361-6501/ad1e20

Su, N., Chen, Y., Liu, Y., Zhang, Q., Zhou, L., He, Y., & Chang, X. (2024). Fault diagnosis of rotating machinery under variable operating conditions based on multi-feature and transfer learning. In 2024 6th International Conference on Internet of Things, Automation and Artificial Intelligence (IoTAAI) (pp. 190–194). IEEE. https://doi.org/10.1109/IOTAAI62601.2024.10692373

Tran, K., Vu, H., Pham, L., Boudaoud, N., & Nguyen, H.-S.-H. (2024). Robust-MBDL: A robust multi-branch deep-learning-based model for remaining useful life prediction of rotating machines. Mathematics, 12(10), 1569. https://doi.org/10.3390/math12101569

Wang, S., Su, X. L., Li, J., Li, F., Li, M., Ren, Y., Wang, G., Shi, N., & Huang, Q. (2025). A synergistic fault diagnosis method for rolling bearings: Variational mode decomposition coupled with deep learning. Electronics, 14(18), 3714. https://doi.org/10.3390/electronics14183714

Wang, X., Zhou, W., & Li, X. (2023). Bearing fault diagnosis based on graph formulation and graph convolutional network. Journal of Dynamics, Monitoring and Diagnostics, 2(4), 252–261. https://doi.org/10.37965/jdmd.2023.468

Wei, L., Peng, X., & Cao, Y. (2024). Multi-scale graph Transformer for rolling bearing fault diagnosis. Eksploatacja i Niezawodność – Maintenance and Reliability. https://doi.org/10.17531/ein/194779

Xie, F., Wang, G., Shang, J., Sun, E., & Xie, S. (2023). Gearbox fault diagnosis based on multi-sensor deep spatiotemporal feature representation. Mathematics, 11(12), 2679. https://doi.org/10.3390/math11122679

Yang, Z.-Z., Li, W., Yuan, F., Zhi, H., Guo, M., Xin, B., & Gao, Z. (2025). Hybrid CNN-BiLSTM-MHSA model for accurate fault diagnosis of rotor motor bearings. Mathematics, 13(3), 334. https://doi.org/10.3390/math13030334

Zhang, J., Zhang, Q., Feng, W., Qin, X., & Sun, Y. (2023). Gearbox fault diagnosis based on frequency-domain Gramian angular difference field and deep convolutional neural network. Proceedings of the Institution of Mechanical Engineers, Part C: Journal of Mechanical Engineering Science, 237(21), 5187–5202. https://doi.org/10.1177/09544062231157189

Zhang, Q., & Deng, L. (2023). An intelligent fault diagnosis method of rolling bearings based on short-time Fourier transform and convolutional neural network. Journal of Failure Analysis and Prevention, 23, 795–811. https://doi.org/10.1007/s11668-023-01616-9

Zhang, Q., Wei, X., Wang, Y., & Hou, C. (2024). Convolutional neural network with attention mechanism and visual vibration signal analysis for bearing fault diagnosis. Sensors, 24(6), 1831. https://doi.org/10.3390/s24061831

Zhang, S., Zhou, J., Ma, X., Pirttikangas, S., & Yang, C. (2024). TSViT: A time series vision transformer for fault diagnosis of rotating machinery. Applied Sciences, 14(23), 10781. https://doi.org/10.3390/app142310781