LSTM-BASED MACHINE LEARNING FOR REMAINING USEFUL LIFE PREDICTION OF BEARING MOTORS USING MULTI-SENSOR MONITORING

Yani Koerniawan; Raynaldi Yudha Prasetya

doi:10.23960/jitet.v14i1.8890

Authors

Yani Koerniawan Akademi Komunitas Toyota Indonesia
Raynaldi Y.P. Akademi Komunitas Toyota Indonesia

DOI:

https://doi.org/10.23960/jitet.v14i1.8890

Abstract Views: 63 File Views: 27

Keywords:

Bearing Motor, IoT, Multi-Sensor Monitoring, LSTM, Predictive Maintenance, Remaining Useful Life

Abstract

This study presents an advanced Long Short-Term Memory (LSTM) machine learning framework for predicting the Remaining Useful Life (RUL) of bearing motors through multi-sensor monitoring. Critical parameters, including vibration (RMS), acoustic emission, temperature, stator current, and rotational speed (RPM), were simulated over a 1000-day operational period for three motors with varying conditions. Failure thresholds were defined to represent severe operational conditions. The LSTM model achieved RMSE values of 28.15, 30.29, and 29.21 days and R² values of 0.989, 0.9876, and 0.9877 for training, validation, and test datasets, respectively. These results demonstrate high predictive accuracy and reliability. Integrating multi-sensor data improves the model’s robustness and supports proactive maintenance planning. The study provides a foundation for future integration of LSTM-based predictive models with IoT-enabled real-time monitoring systems in industrial applications.

Downloads

Download data is not yet available.

References

S. Apeiranthitis, P. Zacharia, A. Chatzopoulos, and M. Papoutsidakis, “Predictive Maintenance of Machinery with Rotating Parts Using Convolutional Neural Networks,” mdpi.comS Apeiranthitis, P Zacharia, A Chatzopoulos, M PapoutsidakisElectronics, 2024•mdpi.com, vol. 13, no. 2, Jan. 2024, doi: 10.3390/ELECTRONICS13020460.

J. Garcia, L. Rios-Colque, A. Peña, and L. Rojas, “Condition monitoring and predictive maintenance in industrial equipment: An NLP-assisted review of signal processing, hybrid models, and implementation,” mdpi.comJ Garcia, L Rios-Colque, A Peña, L RojasApplied Sciences, 2025•mdpi.com, vol. 15, no. 10, May 2025, doi: 10.3390/APP15105465.

Y. Lei, F. Jia, J. Lin, … S. X.-I. T. on, and undefined 2016, “An intelligent fault diagnosis method using unsupervised feature learning towards mechanical big data,” ieeexplore.ieee.orgY Lei, F Jia, J Lin, S Xing, SX DingIEEE Transactions on Industrial Electronics, 2016•ieeexplore.ieee.org, doi: 10.1109/TIE.2016.2618679.

L. Wang, M. W.-S. Reports, and undefined 2025, “Research on bearing fault diagnosis based on machine learning and SHAP interpretability analysis,” nature.comL Wang, M WuScientific Reports, 2025•nature.com, doi: 10.1038/s41598-025-25083-4.

H. Taoufyq, K. El Guemmat, … K. M.-J. of I., and undefined 2025, “Predictive maintenance approaches: A systematic literature review,” jiem.orgH Taoufyq, K El Guemmat, K Mansouri, F AkefJournal of Industrial Engineering and Management, 2025•jiem.org, vol. 18, no. 3, pp. 427–458, 2025, doi: 10.3926/jiem.8537.

W. Li, T. L.-S. Reports, and undefined 2025, “Comparison of deep learning models for predictive maintenance in industrial manufacturing systems using sensor data,” nature.comW Li, T LiScientific Reports, 2025•nature.com, doi: 10.1038/S41598-025-23545-X.

N. Farouk, A. Jaafar, and A. Ayoub, “LSTM-ANN-GA A HYBRID DEEP LEARNING MODEL FOR PREDICTIVE MAINTENANCE OF INDUSTRIAL EQUIPEMENT,” pesjournal.netN Farouk, A Jaafar, A AyoubProceedings on Engineering, 2025•pesjournal.net, vol. 7, no. 2, pp. 861–868, 2025, doi: 10.24874/PES07.02.014.

A. Mawardi, … R. P.-J. I. dan, and undefined 2025, “Komparasi Algoritma Boosting Untuk Prediksi Gangguan Tidur,” journal.eng.unila.ac.idAB Mawardi, RS Pradini, MS HarisJurnal Informatika dan Teknik Elektro Terapan, 2025•journal.eng.unila.ac.id, Accessed: Jan. 06, 2026. [Online]. Available: http://journal.eng.unila.ac.id/index.php/jitet/article/view/7281

F. Wu, Q. Wu, Y. Tan, and X. Xu, “Remaining useful life prediction based on deep learning: a survey,” mdpi.comF Wu, Q Wu, Y Tan, X XuSensors, 2024•mdpi.com, vol. 24, no. 11, Jun. 2024, doi: 10.3390/S24113454.

S. H. Jeon, S. Yoo, Y. S. Yoo, and I. W. Lee, “ML-and LSTM-based radiator predictive maintenance for energy saving in compressed air systems,” mdpi.comSH Jeon, S Yoo, YS Yoo, IW LeeEnergies, 2024•mdpi.com, vol. 17, no. 6, Mar. 2024, doi: 10.3390/EN17061428.

M. Krichen and A. Mihoub, “Long short-term memory networks: a comprehensive survey,” mdpi.comM Krichen, A MihoubAI, 2025•mdpi.com, vol. 6, no. 9, Sep. 2025, doi: 10.3390/AI6090215.

X. Li, L. Zhang, T. Tan, X. Wang, X. Zhao, and Y. Xu, “Multi-Sensor Data Fusion and Vibro-Acoustic Feature Engineering for Health Monitoring and Remaining Useful Life Prediction of Hydraulic Valves,” mdpi.comX Li, L Zhang, T Tan, X Wang, X Zhao, Y XuSensors, 2025•mdpi.com, vol. 25, no. 20, Oct. 2025, doi: 10.3390/S25206294.

M. Imani, A. Beikmohammadi, and H. R. Arabnia, “Comprehensive analysis of random forest and XGBoost performance with SMOTE, ADASYN, and GNUS under varying imbalance levels,” mdpi.comM Imani, A Beikmohammadi, HR ArabniaTechnologies, 2025•mdpi.com, vol. 13, no. 3, Mar. 2025, doi: 10.3390/TECHNOLOGIES13030088.

K. Hamani, M. Kuchar, M. Kubatko, and S. Kirschner, “Advancements in Induction Motor Fault Diagnosis and Condition Monitoring: A Comprehensive Review,” pmc.ncbi.nlm.nih.govK Hamani, M Kuchar, M Kubatko, S KirschnerSensors (Basel, Switzerland), 2025•pmc.ncbi.nlm.nih.gov, vol. 25, no. 19, Oct. 2025, doi: 10.3390/S25195942.

D. Neupane, M. R. Bouadjenek, R. Dazeley, and S. Aryal, “Data-driven machinery fault diagnosis: A comprehensive review,” ElsevierD Neupane, MR Bouadjenek, R Dazeley, S AryalNeurocomputing, 2025•Elsevier, vol. 627, Apr. 2025, doi: 10.1016/J.NEUCOM.2025.129588.

F. M. Butt, L. Hussain, A. Mahmood, and K. J. Lone, “Artificial Intelligence based accurately load forecasting system to forecast short and medium-term load demands,” aimspress.comFM Butt, L Hussain, A Mahmood, KJ LoneMathematical Biosciences and Engineering, 2021•aimspress.com, vol. 18, no. 1, pp. 400–425, 2021, doi: 10.3934/MBE.2021022.

L. Magadán, J. C. Granda, and F. J. Suárez, “Robust prediction of remaining useful lifetime of bearings using deep learning,” ElsevierL Magadán, JC Granda, FJ SuárezEngineering Applications of Artificial Intelligence, 2024•Elsevier, vol. 130, Apr. 2024, doi: 10.1016/J.ENGAPPAI.2023.107690.

Z. Gao, C. Cecati, S. D.-I. transactions on industrial, and undefined 2015, “A survey of fault diagnosis and fault-tolerant techniques—Part II: Fault diagnosis with knowledge-based and hybrid/active approaches,” ieeexplore.ieee.orgZ Gao, C Cecati, SX DingIEEE transactions on industrial electronics, 2015•ieeexplore.ieee.org, doi: 10.1109/TIE.2015.2417503.