IMPLEMENTASI ANALISIS PREDIKTIF UNTUK DETEKSI DINI KERUSAKAN BEARING PADA AIR COMPRESSOR
DOI:
https://doi.org/10.53026/prosidingsntem.v5i1.821Keywords:
Analisis Prediktif, Regresi Logistik, Air Compressor, Random Forest, Predictive MaintenanceAbstract
Penelitian ini mengembangkan model analisis prediktif untuk deteksi dini kerusakan bearing pada kompresor udara menggunakan dua metode: Regresi Logistik dan Random Forest. Data sensor yang digunakan mencakup berbagai parameter operasional seperti suhu, torsi, daya motor, kecepatan rotasi, getaran, dan kebisingan. Hasil evaluasi model menunjukkan akurasi 76.5% untuk kedua metode, dengan Random Forest menunjukkan kinerja yang lebih baik dalam mendeteksi kondisi Noisy (kerusakan bearing), dengan Precision (1) sebesar 78.3% dan Recall (1) sebesar 96.1%. Sementara itu, kemampuan kedua model dalam mendeteksi kondisi Ok (bearing sehat) cenderung lebih rendah. Analisis distribusi dan korelasi fitur mengidentifikasi getaran dan suhu outlet sebagai parameter yang paling relevan dalam membedakan kondisi bearing Ok dan Noisy. Penelitian ini menyarankan penggunaan Random Forest untuk sistem predictive maintenance, yang dapat membantu meningkatkan efisiensi perawatan dan mengurangi downtime kompresor udara.
References
A. Ciobotaru, C. Corches, D.-I. Gota, and L. Miclea, “An Explainable Deep Learning-Based Predictive Maintenance Solution for Air Compressor Condition Monitoring,” Sensors, 2025, doi: 10.3390/s25185797.
B. G. Joung, C. Nath, Z. Li, and J. W. Sutherland, “Bearing Anomaly Detection in an Air Compressor Using an LSTM and RNN-based Machine Learning Model,” Int. J. Adv. Manuf. Technol., 2024, doi: 10.1007/s00170-024-14322-z.
S. Ayankoso, A. Dutta, Y. He, F. Gu, A. D. Ball, and S. K. Pal, “Performance of Vibration and Current Signals in the Fault Diagnosis of Induction Motors Using Deep Learning and Machine Learning Techniques,” Struct. Heal. Monit., 2024, doi: 10.1177/14759217241289874.
O. Mey et al., “Condition Monitoring of Drive Trains by Data Fusion of Acoustic Emission and Vibration Sensors,” Processes, 2021, doi: 10.3390/pr9071108.
J. Liu, Y. Hu, Y. Wang, B. Wu, J. Fan, and Z. Hu, “An Integrated Multi-Sensor Fusion-Based Deep Feature Learning Approach for Rotating Machinery Diagnosis,” Meas. Sci. Technol., 2018, doi: 10.1088/1361-6501/aaaca6.
P. Dwivedi et al., “Predictive Maintenance and Monitoring of Industrial Compressors Using Machine Learning: A Proactive Approach,” Metall. Mater. Eng., 2025, doi: 10.63278/1387.
J. Mohammed and J. Abdulhady, “Rolling Bearing Fault Detection Based on Vibration Signal Analysis and Cumulative Sum Control Chart,” Fme Trans., 2021, doi: 10.5937/fme2103684m.
C. Ates, T. Höfchen, M. Witt, R. Koch, and H. J. Bauer, “Vibration-Based Wear Condition Estimation of Journal Bearings Using Convolutional Autoencoders,” Sensors, vol. 23, no. 22, 2023, doi: 10.3390/s23229212.
S. R. Saufi, Z. A. Bin Ahmad, M. S. Leong, and M. H. Lim, “Low-Speed Bearing Fault Diagnosis Based on ArSSAE Model Using Acoustic Emission and Vibration Signals,” IEEE Access, vol. 7, 2019, doi: 10.1109/ACCESS.2019.2909756.
A. J. Scott, D. W. Hosmer, and S. Lemeshow, “Applied Logistic Regression.,” Biometrics, vol. 47, no. 4, 1991, doi: 10.2307/2532419.
N. Hadroug, A. Hafaifa, A. Iratni, and M. Guemana, “Reliability Modeling Using an Adaptive Neuro-Fuzzy Inference System: Gas Turbine Application,” Fuzzy Inf. Eng., 2021, doi: 10.1080/16168658.2021.1915451.
G. Biau and E. Scornet, “A random forest guided tour,” Test, vol. 25, no. 2, 2016, doi: 10.1007/s11749-016-0481-7.
V. Svetnik, A. Liaw, C. Tong, J. Christopher Culberson, R. P. Sheridan, and B. P. Feuston, “Random Forest: A Classification and Regression Tool for Compound Classification and QSAR Modeling,” J. Chem. Inf. Comput. Sci., vol. 43, no. 6, 2003, doi: 10.1021/ci034160g.
Downloads
Published
Conference Proceedings Volume
Section
License
Copyright (c) 2025 Prosiding Seminar Nasional Teknologi Energi dan Mineral
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
