Pengembangan Model Predictive Maintenance Pada Main Motor Mesin Raw Mill
DOI:
https://doi.org/10.55826/jtmit.v5i1.1482Keywords:
Predictive Maintenance, ; Remaining Usefull Life, , Downtime, Random Forest, LSTMAbstract
Downtime akibat kegagalan mesin yang terjadi secara tiba-tiba dapat menyebabkan kerugian yang signifikan bagi perusahaan. Oleh karena itu, diperlukan strategi perawatan yang tepat untuk meminimalkan risiko kegagalan tersebut. Seiring dengan perkembangan smart manufacturing, mesin-mesin industry menghasilkan data sensor yang digunakan untuk memantau kondisi kesehatan mesin. Pengelolaan data berskala besar ini menuntut penerapan Teknik analitik yang andal, khususnya dalam konteks predictive maintenance di Industri 4.0. Predictive maintenance dinilai lebih efektif dibandingkan dengan preventive dan corrective maintenance karena mampu memantau kondisi mesin secara real-time dan memprediksi kegagalan dan Remaining Useful Life (RUL) peralatan. Penelitian ini bertujuan untuk membangun model prognosis berbasis klasifikasi RUL pada komponen main motor raw mill menggunakan algoritma Long Short-Term untuk membentuk representasi deret waktu, kemudian dilakukan pelabelan RUL berdasarkan interval waktu terhadap kejadian kegagalan untuk mengidentifikasi kondisi early fault. Pemisahan data dilakukan secara time-based untuk menghindari data leakage. Selain itu, dilakukan hyperparameter tuning untuk memperoleh konfigurasi model yang optimal. Hasil pengujian menunjukkan bahwa pada model diagnosis akurasi terbaik didapatkan sebesar 97,4% dengan parameter optimal. Sedagkan pada model prognosis menggunakan LSTM mampu memberikan kinerja klasifikasi RUL yang baik dengan nilai ROC AUC sebesar 0,806 yang menunjukkan kemampuan model dalam membedakan kondisi normal dan early fault. Dengan demikian, model yang diusulkan dapat digunakan sebagai sistem pendukung pengambilan Keputusan dalam implementasi predictive maintenance pada mesin industri.
References
[1] R. S. Velmurugan and T. Dhingra, “Asset Maintenance: A Primary Support Function,” 2021, pp. 1–21. doi: 10.1007/978-3-030-74154-9_1.
[2] T. Zhu, Y. Ran, X. Zhou, and Y. Wen, “A Survey of Predictive Maintenance: Systems, Purposes and Approaches,” Dec. 2019, [Online]. Available: http://arxiv.org/abs/1912.07383
[3] S. Elkateb, A. Métwalli, A. Shendy, and A. E. B. Abu-Elanien, “Machine learning and IoT – Based predictive maintenance approach for industrial applications,” Alexandria Engineering Journal, vol. 88, pp. 298–309, Feb. 2024, doi: 10.1016/j.aej.2023.12.065.
[4] G. Elvis, “Developing a Predictive Maintenance Model Using IoT and Machine Learning,” 2025.
[5] Y. Gholipour, M. Zare, M. Vaziri Sereshk, and Y. Gholipour, “A Comprehensive Review of Maintenance Strategies: From Reactive to Proactive Approaches.”
[6] Z. Wenbin et al., “Markov reward approach and reliability associated cost model for machine tools maintenance-planning optimization,” International Journal of Mathematical, Engineering and Management Sciences, vol. 4, no. 4, pp. 824–840, 2019, doi: 10.33889/IJMEMS.2019.4.4-065.
[7] T. O. Alamri and J. P. T. Mo, “Optimisation of Preventive Maintenance Regime Based on Failure Mode System Modelling Considering Reliability,” Arab J Sci Eng, vol. 48, no. 3, pp. 3455–3477, Mar. 2023, doi: 10.1007/s13369-022-07174-w.
[8] T. O. Alamri and J. P. T. Mo, “Optimisation of Preventive Maintenance Regime Based on Failure Mode System Modelling Considering Reliability,” Arab J Sci Eng, vol. 48, no. 3, pp. 3455–3477, Mar. 2023, doi: 10.1007/s13369-022-07174-w.
[9] M. Molęda, B. Małysiak-Mrozek, W. Ding, V. Sunderam, and D. Mrozek, “From Corrective to Predictive Maintenance—A Review of Maintenance Approaches for the Power Industry,” Jul. 01, 2023, Multidisciplinary Digital Publishing Institute (MDPI). doi: 10.3390/s23135970.
[10] A. Ahmed Murtaza, A. Saher, M. Hamza Zafar, S. Kumayl Raza Moosavi, M. Faisal Aftab, and F. Sanfilippo, “Paradigm shift for predictive maintenance and condition monitoring from Industry 4.0 to Industry 5.0: A systematic review, challenges and case study,” Dec. 01, 2024, Elsevier B.V. doi: 10.1016/j.rineng.2024.102935.
[11] A. Benhanifia, Z. Ben Cheikh, P. M. Oliveira, A. Valente, and J. Lima, “Systematic review of predictive maintenance practices in the manufacturing sector,” Intelligent Systems with Applications, vol. 26, p. 200501, Jun. 2025, doi: 10.1016/j.iswa.2025.200501.
[12] E. Traini, G. Bruno, G. D’Antonio, and F. Lombardi, “Machine learning framework for predictive maintenance in milling,” in IFAC-PapersOnLine, Elsevier B.V., Sep. 2019, pp. 177–182. doi: 10.1016/j.ifacol.2019.11.172.
[13] O. Surucu, S. A. Gadsden, and J. Yawney, “Condition Monitoring using Machine Learning: A Review of Theory, Applications, and Recent Advances,” Jul. 01, 2023, Elsevier Ltd. doi: 10.1016/j.eswa.2023.119738.
[14] M. Nagy, M. Figura, K. Valaskova, and G. Lăzăroiu, “Predictive Maintenance Algorithms, Artificial Intelligence Digital Twin Technologies, and Internet of Robotic Things in Big Data-Driven Industry 4.0 Manufacturing Systems,” Mathematics, vol. 13, no. 6, Mar. 2025, doi: 10.3390/math13060981.
[15] A. Haleem, P. Gupta, S. Bahl, M. Javaid, and L. Kumar, “3D scanning of a carburetor body using COMET 3D scanner supported by COLIN 3D software: Issues and solutions,” in Materials Today: Proceedings, Elsevier Ltd, 2020, pp. 331–337. doi: 10.1016/j.matpr.2020.07.427.
[16] E. Rauch, C. Linder, and P. Dallasega, “Anthropocentric perspective of production before and within Industry 4.0,” Comput Ind Eng, vol. 139, Jan. 2020, doi: 10.1016/j.cie.2019.01.018.
[17] T. Zonta, C. A. da Costa, R. da Rosa Righi, M. J. de Lima, E. S. da Trindade, and G. P. Li, “Predictive maintenance in the Industry 4.0: A systematic literature review,” Comput Ind Eng, vol. 150, Dec. 2020, doi: 10.1016/j.cie.2020.106889.
[18] Oluwatope R. Ojo, Oluwagbemisola Elizabeth Elesho, Aruna Adeniyi, and Ojo John Oluwadamilola, “Applying Machine Learning Models for Real-Time Process Monitoring and Anomaly Detection in Pharma Manufacturing,” GSC Biological and Pharmaceutical Sciences, vol. 27, no. 1, pp. 315–341, Apr. 2024, doi: 10.30574/gscbps.2024.27.1.0153.
[19] K. T. P. Nguyen and K. Medjaher, “A new dynamic predictive maintenance framework using deep learning for failure prognostics,” Reliab Eng Syst Saf, vol. 188, pp. 251–262, Aug. 2019, doi: 10.1016/j.ress.2019.03.018.
[20] A. G. Mohapatra et al., “An Industry 4.0 implementation of a condition monitoring system and IoT-enabled predictive maintenance scheme for diesel generators,” Alexandria Engineering Journal, vol. 76, pp. 525–541, Aug. 2023, doi: 10.1016/j.aej.2023.06.026.
[21] M. Z. Djidrov, “Challenges in Damage Detection for Real-time Monitoring and Predictive Maintenance Methodology,” SAR Journal - Science and Research, pp. 310–316, Dec. 2024, doi: 10.18421/sar74-04.
[22] Y. Wen, M. Fashiar Rahman, H. Xu, and T. L. B. Tseng, “Recent advances and trends of predictive maintenance from data-driven machine prognostics perspective,” Measurement (Lond), vol. 187, Jan. 2022, doi: 10.1016/j.measurement.2021.110276.
[23] M. Ogrizović, D. Drašković, and D. Bojić, “Quality assurance strategies for machine learning applications in big data analytics: an overview,” J Big Data, vol. 11, no. 1, Dec. 2024, doi: 10.1186/s40537-024-01028-y.
[24] I. Muhamad and M. Matin, “Hyperparameter Tuning menggunakan GridsearchCV pada Random Forest untuk Deteksi Malware,” May 2023.
[25] S. Wang, C. Ma, Y. Xu, J. Wang, and W. Wu, “A Hyperparameter Optimization Algorithm for the LSTM Temperature Prediction Model in Data Center,” Sci Program, vol. 2022, 2022, doi: 10.1155/2022/6519909.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Fauziyyah Firdausi Zakiyyah, Mokh Suef
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
