DIAGNOSIS KERUSAKAN PADA SISTEM COMPRESSOR PRODUKSI GAS MENGGUNAKAN PREDIKSI CERTAINTY FACTOR DAN NAIVE BAYES
DOI:
https://doi.org/10.53026/prosidingsntem.v5i1.764Keywords:
diagnosis kerusakan kompresor, sistem pakar, forward chaining, certainty factor, naïve bayesAbstract
Diagnosis dini pada sistem kompresor produksi gas memiliki peran strategis dalam mencegah down-time, mempertahankan efisiensi operasi, dan menekan biaya perawatan reaktif yang sering terjadi akibat keterlambatan deteksi kerusakan. Sebagian besar penelitian sebelumnya masih menggunakan pendekatan tunggal, baik berbasis aturan (rule-based inference) maupun klasifikasi probabilistik, yang cenderung kurang optimal ketika gejala bersifat ambigu, tumpang tindih, atau data sensor tidak lengkap. Untuk mengatasi keterbatasan tersebut, penelitian ini mengusulkan sistem pakar hibrid yang mengombinasikan forward chaining sebagai mesin inferensi utama, Certainty Factor (CF) untuk merepresentasikan tingkat keyakinan pakar terhadap hubungan gejala dan penyebab, serta Naïve Bayes untuk memperkuat keputusan diagnosis melalui pembelajaran probabilistik. Integrasi dilakukan dengan menerapkan fungsi pembobotan adaptif yang menyeimbangkan kontribusi nilai kepercayaan pakar (CF) dan probabilitas empiris hasil perhitungan posterior. Sistem diimplementasikan menggunakan bahasa pemrograman Python dan diuji menggunakan kumpulan data terstruktur yang berasal dari log historis gangguan kompresor serta skenario sintetik berbasis pengetahuan domain industri gas. Hasil pengujian menunjukkan bahwa pendekatan hibrid ini mampu meningkatkan stabilitas dan akurasi diagnosis secara signifikan, dengan peningkatan terukur hingga 37.7% dibandingkan metode Naïve Bayes murni pada skenario kasus kritis (seperti Level Transmitter Rusak). Temuan ini menegaskan potensi pendekatan hibrid dalam pengembangan sistem diagnosis cerdas di lingkungan industri proses.
References
K. Zhang, “Compressor fault diagnosis system based on PCA-PSO and LSSVM,” J. Mech. Eng., 2021.
B. Srivatsan et al., “Fault diagnosis of air compressors using transfer learning: A comparative study of pre-trained networks and hyperparameter optimization,” J. Low Freq. Noise Vib. Act. Control, vol. 43, no. 4, pp. 1877–1894, 2024, doi: 10.1177/14613484241273652.
A. Nambiar, “Prediction of air compressor faults with feature fusion techniques,” IEEE Access, vol. 12, pp. 56789–56798, 2024.
X. Duan, “Compressor fault diagnosis and result visualization,” 2024.
Z. Fang, “Reciprocating compressors intelligent fault diagnosis based on deep learning,” Sensors, vol. 24, no. 5, p. 2331, 2024.
X. Wang, “Hybrid routing protocol based on Naïve Bayes,” Electron., 2022.
M. S. Farooq, “Harnessing AI forward and backward chaining with IoT telemetry,”Appl. Sci., 2025.
J. Lee, “Certainty Factor-based expert system applications: A comprehensive survey,” Expert Syst. Appl., vol. 220, p. 119742, 2023.
L. Chen, “Bayes-based probabilistic diagnosis systems for industrial machines,” J. Intell. Manuf., vol. 32, no. 8, pp. 2035–2046, 2021.
R. Ali, “Hybrid rule and probabilistic frameworks for intelligent diagnosis,” Eng. Appl. Artif. Intell., vol. 94, p. 103734, 2020.
A.; Patel; S.Kumar, “Review: Hybrid expert systems for compressor diagnosis,” J. Mech. Eng. Res. Dev., 2024.
D. Singh, V. Sharma, “Evaluation of hybrid expert systems for process machines,” Int. J. Adv. Comput. Sci. Appl..
B. E. Team, “Forward Chaining vs. Backward Chaining in AI,” 2024. [Online]. Available: https://builtin.com/artificial-intelligence/forward-chaining-vs-backward- chaining
E. H. Shortliffe and B. G. Buchanan, “A Model of Inexact Reasoning in Medicine,” Math. Biosci., vol. 23, no. 3–4, pp. 351–379, 1975, doi: 10.1016/0025-5564(75)90009-9.
W. Zhang, C. Li, and Y. Huang, “Development of Contactless Conductivity Measurement Using Capacitively Coupled Detection for Non-Conductive Drilling Fluids,” Sensors Actuators B: Chem., vol. 386, p. 133925, 2023, doi: 10.1016/j.snb.2023.133925.
A. Santoso, D. Kurniawan, and R. Fadillah, “Application of the Certainty Factor Method for Mobile-Based Expert Systems in Diagnosing Motor Vehicle Damage,” Appl. Sci. Inf. Technol. J. (ASCI Journal), 2023, [Online]. Available: https://ascijournal.eu/index.php/asci/article/download/ 2254/1521
R. Dashti, “Application of Expert Systems in the Sciences,” The Ohio State University Knowledge Bank, 2020. [Online]. Available: https://kb.osu.edu/server/api/core/bitstreams/98710464-d567-5dac-a77f- 53e03a1a6ec9/content
P. Rahayu, L. Judijanto, H. Syaddad, and A. Apriyanto, “Pengantar Sistem Pakar: Teori dan Implementasi,” 2025, Accessed: Aug. 21, 2025. [Online]. Available: https://books.google.com/
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.
