A comparative analysis of machine and deep learning models for predictive maintenance and fault estimation of tools in industrial machinery within small-scale settings

Year 2025, Volume: 67 Issue: 2, 193 - 215, 24.12.2025

Yusuf Öztürk

https://doi.org/10.33769/aupse.1729175

Abstract

This study presents a comparative evaluation of machine learning (ML) and deep learning (DL) models for predictive maintenance (PdM) in small-scale industrial systems. A low-cost Arduino-based testbed equipped with vibration, temperature, and rotational speed sensors was developed to emulate real-world conditions. The primary focus of the study is the detailed implementation and analysis of a Recurrent Neural Network with Long Short-Term Memory (RNN-LSTM). For benchmarking, two baseline models—Linear Regression and K-Nearest Neighbors (KNN)—were also implemented. According to the evaluation results, RNN-LSTM achieved the highest performance, with 95.31% accuracy, 0.047 MSE, 0.217 RMSE, 0.047 MAE, and 23.4% SMAPE. In comparison, Linear Regression and KNN yielded lower accuracies (92.30% and 93.27%) and higher error values (e.g., SMAPE of 58.7% and 41.2%). These findings confirm the superiority of RNN-LSTM in modeling temporal dependencies, while baseline models demonstrated limited generalization. Overall, the study shows that advanced DL models can be deployed on resource-constrained embedded systems, supporting the wider adoption of Industry 4.0 practices in small and medium-sized enterprises.

Keywords

Predictive maintenance , RNN-LSTM , industrial IoT , sensor-based fault detection , low-cost embedded monitoring

References

• Malhi, A., Yan R., Gao, R. X., Prognosis of Defect Propagation Based on Recurrent Neural Networks, IEEE Trans. Instrum. Meas., 60(3), (2011), 703–711. https://doi.org/10.1109/TIM.2010.2078296.
• Jalayer, M., Kaboli, A., Orsenigo, C., & Vercellis, C., Fault Detection and Diagnosis with Imbalanced and Noisy Data: A Hybrid Framework for Rotating Machinery, Machines, 10(4), (2022), 237. https://doi.org/10.3390/machines10040237.
• Kondaveeti, H. K., Kumaravelu, N. K., Vanambathina, S. D., Mathe, S. E., & Vappangi, S., A systematic literature review on prototyping with Arduino: Applications, challenges, advantages, and limitations, Computer Science Review, 40, (2021), 100364. https://doi.org/10.1016/j.cosrev.2021.100364.
• Lee, J., Ni, J., Singh, J., Jiang, B., Azamfar, M., & Feng, J., Intelligent maintenance systems and predictive manufacturing, Journal of Manufacturing Science and Engineering, 142(11), (2020), 110805. https://doi.org/10.1115/1.4047856.
• Shukla, K., Nefti-Meziani, S., & Davis, S., A heuristic approach on predictive maintenance techniques: Limitations and scope, Advances in Mechanical Engineering, 14(6), (2022), 16878132221101009. https://doi.org/10.1177/16878132221101009.
• Wunsch, A., Liesch, T., Broda, S., Groundwater level forecasting with artificial neural networks: a comparison of long short-term memory (LSTM), convolutional neural networks (CNNs), and non-linear autoregressive networks with exogenous input (NARX), Hydrology and Earth System Sciences, 25(3), (2021), 1671-1687. https://doi.org/10.5194/hess-25-1671-2021.
• Azari, M. S., Flammini, F., Santini, S., Caporuscio M., A systematic literature review on transfer learning for predictive maintenance in Industry 4.0, IEEE Access, 11 (2023), 12887-12910. https://doi.org/10.1109/ACCESS.2023.3239784.
• Nunes, P., Santos, J., Rocha, E., Challenges in predictive maintenance – A review, CIRP J. Manuf. Sci. Technol., 40 (2023), 53–67. https://doi.org/10.1016/j.cirpj.2022.11.004.
• Roberts, D. A., Yaida, S., Hanin, B., The principles of deep learning theory, Vol. 46, Cambridge University Press, Cambridge, MA, USA, 2022.
• Saitoh, K., Deep learning from the basics: Python and deep learning: Theory and implementation, Packt Publishing Ltd., 2021.
• Zhao, R., Yan, R., Chen, Z., Mao, K., Wang, P., Gao, R. X., Deep learning and its applications to machine health monitoring, Mech. Syst. Signal Process., 115 (2019), 213–237. https://doi.org/10.1016/j.ymssp.2018.05.050.
• Li, W., Li, T., Comparison of deep learning models for predictive maintenance in industrial manufacturing systems using sensor data, Sci. Rep., 15, 23545 (2025). https://doi.org/10.1038/s41598-025-08515-z.
• Öztürk, Y., LSTM otokodlayıcılarla yatay frezeleme makinesinde güç aşımı kestirimi, in: Proceedings of the 6th International Bosphorus Scientific Research Congress, 18-19 January 2025, Istanbul, Türkiye.
• Mihigo, I.N.; Zennaro, M.; Uwitonze, A.; Rwigema, J.; Rovai, M., On-device IoT-based predictive maintenance analytics model: Comparing TinyLSTM and TinyModel from Edge Impulse, Sensors, 22(14), (2022), 5174. https://doi.org/10.3390/s22145174.
• Lekidis, A., Georgakis, A., Dalamagkas, C., Papageorgiou, E. I., Predictive maintenance framework for fault detection in remote terminal units, Forecasting, 6(2), (2024), 239-265. https://doi.org/10.3390/forecast6020014.
• Ece, H. S., Öztürk, Y., Özgün, K., Comparative study of machine learning techniques for remaining useful life estimation in simulated mini factory environment, Futuristic Computational Systems and Advanced Engineering for the Society, ICAIAME 2024, Engineering Cyber-Physical Systems and Critical Infrastructures, vol. 15, Springer, Cham, 2025. https://doi.org/10.1007/978-3-031-92552-8_15.