SISTEM PEMELIHARAAN PREDIKTIF POMPA SENTRIFUGAL BERBASIS RULE-BASED INFERENCE DAN CERTAINTY FACTOR MENGGUNAKAN DATA MULTISENSOR
DOI:
https://doi.org/10.53026/sntem2025.v5i1.565Keywords:
Certainty factor, Forward chaining, Getaran, Pemeliharaan prediktif, Pompa sentrifugal, Rule-based inference, Tekanan, TemperaturAbstract
Penelitian ini bertujuan mengembangkan sistem pemeliharaan prediktif berbasis Rule-Based Inference dan Certainty Factor untuk mendeteksi dini kegagalan pompa sentrifugal di fasilitas produksi migas. Sistem ini mengintegrasikan data multisensor yang terdiri atas getaran, suhu, dan tekanan, sehingga mampu merepresentasikan kondisi operasional pompa secara menyeluruh. Data dikumpulkan setiap detik selama 24 jam, meng-hasilkan 86.400 titik data per sensor. Sistem inferensi dibangun menggunakan 18 aturan (rule) hasil kombinasi antara wawasan pakar lapangan dan hasil pengujian eksperimental. Data diolah melalui pengambilan fitur (RMS, kurtosis, ΔP, dan tren suhu) dan dianalisis menggunakan prinsip IF–THEN berdasarkan wawasan pakar. Hasil inferensi mengidentifikasi tiga pola kegagalan dominan kerusakan bantalan, overheating, dan kebocoran cairan dengan rata-rata Certainty Factor (CF) sebesar 0,82 menunjukkan tingkat kepercayaan diagnosis yang tinggi. Validitas dan konsistensi hasil diagnosa ini selanjutnya diperkuat melalui analisis statistik komprehensif (Shapiro–Wilk, Levene, Pearson, Spearman, dan Durbin–Watson). Sistem yang dibuat mampu memberikan deteksi awal terhadap kegagalan secara langsung, tingkat kepercayaan yang terukur, serta rekomendasi tindakan pemeliharaan yang mudah dimengerti oleh operator. Metode ini terbukti efektif dan efisien sehingga mendukung penerapan predictive maintenance secara real-time di fasilitas industri minyak dan gas.
References
J. F. Olesen dan H. R. Shaker, “Predictive maintenance for pump systems and thermal power plants: State-of-the-art review, trends and challenges,” Sensors (Switzerland), vol. 20, no. 8, 2020, doi: 10.3390/s20082425.
Y. Zhang et al., “Vibration analysis of a high-pressure multistage centrifugal pump,” Sci. Rep., vol. 12, no. 1, hal. 1–14, 2022, doi: 10.1038/s41598-022-22605-2.
I. U. Hassan, K. Panduru, dan J. Walsh, “An In-Depth Study of Vibration Sensors for Condition Monitoring,” Sensors, vol. 24, no. 3, 2024, doi: 10.3390/s24030740.
N. Es-sakali, M. Cherkaoui, M. O. Mghazli, and Z. Naimi, “Review of predictive maintenance algorithms applied to HVAC systems,” Energy Reports, vol. 8, no. August, hal. 1003–1012, 2022, doi: 10.1016/j.egyr.2022.07.130.
C. E. Sunal, V. Velisavljevic, V. Dyo, B. Newton, and J. Newton, “Centrifugal Pump Fault Detection with Convolutional Neural Network Transfer Learning,” Sensors, vol. 24, no. 8, hal. 1–12, 2024, doi: 10.3390/s24082442.
W. Zaman, Z. Ahmad, dan J. M. Kim, “Fault Diagnosis in Centrifugal Pumps: A Dual-Scalogram Approach with Convolution Autoencoder and Artificial Neural Network,” Sensors, vol. 24, no. 3, 2024, doi: 10.3390/s24030851.
P. Mallioris, E. Aivazidou, and D. Bechtsis, “Predictive maintenance in Industry 4.0: A systematic multi-sector mapping,” CIRP J. Manuf. Sci. Technol., vol. 50, no. February 2023, hal. 80–103, 2024, doi: 10.1016/j.cirpj.2024.02.003.
G. S. Dave, A. P. Pandhare, A. P. Kulkarni, dan D. V. Khankal, “Innovative data techniques for centrifugal pump optimization with machine learning and AI model,” PLoS One, vol. 20, no. 6, June, hal. 1–27, 2025, doi: 10.1371/journal.pone.0325952.
M. Menanno dan A. Salsano, “Centrifugal Pump Fault Diagnosis using a Predictive Maintenance Model,” no. July 2023, 2023, doi: 10.46254/eu6.20230422.
W. Zaman, Z. Ahmad, M. F. Siddique, N. Ullah, dan J. M. Kim, “Centrifugal Pump Fault Diagnosis Based on a Novel SobelEdge Scalogram and CNN,” Sensors, vol. 23, no. 11, 2023, doi: 10.3390/s23115255.
M. H. Garousi, M. Karimi, P. Casoli, M. Rundo, dan R. Fallahzadeh, “Vibration Analysis of a Centrifugal Pump with Healthy and Defective Impellers and Fault Detection Using Multi-Layer Perceptron,” Eng, vol. 5, no. 4, hal. 2511–2530, 2024, doi: 10.3390/eng5040131.
A. S. Sembiring et al., “Implementation of Certainty Factor Method for Expert System,” J. Phys. Conf. Ser., vol. 1255, no. 1, 2019, doi: 10.1088/1742-6596/1255/1/012065.
F. S. Nurrachma dan N. L. Azizah, “Application of Expert System for Diagnosing Cat Disease Based on Web Using Forward Chaining and Certainty Factor,” hal. 1–12, 2023.
B. Pulido, N. Moya, C. J. Alonso-González, and A. Bregon, “Efficient generation of minimal dynamic Bayesian Networks for hybrid systems fault diagnosis using hybrid possible conflicts,” PHM 2013 - Proc. Annu. Conf. Progn. Heal. Manag. Soc. 2013, hal. 288–299, 2013, doi: 10.36001/phmconf.2013.v5i1.2255.
M. S. Farooq et al., “Harnessing AI forward and backward chaining with telemetry data for enhanced diagnostics and prognostics of smart devices,” Sci. Rep., vol. 15, no. 1, hal. 1–17, 2025, doi: 10.1038/s41598-025-89266-9.
Downloads
Published
Conference Proceedings Volume
Section
License
Copyright (c) 2025 Seminar Nasional Teknologi Energi dan Mineral 2025
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
