SISTEM PAKAR BERBASIS AGREGASI PROBABILITAS BAYESIAN UNTUK DETEKSI RISIKO BAHAYA DI KILANG MINYAK
DOI:
https://doi.org/10.53026/prosidingsntem.v5i1.754Keywords:
Agregasi Probabilitas Bayesian, Sistem Pakar, Deteksi Risiko, Kilang Minyak, Inferensi ProbabilistikAbstract
Industri kilang minyak menghadapi risiko bahaya tinggi dengan ketidakpastian operasional yang kompleks. Sistem pakar konvensional berbasis aturan sering gagal menangani agregasi multiple gejala secara probabilistik. Penelitian ini mengembangkan sistem pakar berbasis agregasi probabilitas Bayesian untuk deteksi risiko bahaya di kilang minyak. Dataset 60 gejala bahaya dari 5 pakar K3 dikodifikasikan menggunakan Modified Delphi method. Sistem diimplementasikan dalam Python dengan antarmuka grafis Tkinter dan algoritma inferensi menggunakan rumus 1 - Π(1 - p). Validasi fungsional menunjukkan sistem mampu mengintegrasikan multiple gejala dengan akurasi probabilistik tinggi (contoh: probabilitas 0.88 dari kombinasi 3 gejala dengan nilai individual 0.4-0.6). Fitur supporting evidence meningkatkan transparansi diagnosis, sementara ekspor CSV mendukung pembelajaran berkelanjutan. Sistem ini menawarkan solusi praktis untuk manajemen keselamatan proaktif di kilang minyak
References
O. Chencheva, S. Sukach, D. Rieznik, I. Petrenko, Ye. Lashko, and O. Hladiuk, “MODERN CONCEPT OF OCCUPATIONAL SAFETY AND HEALTH MANAGEMENT WITH A RISK-BASED APPROACH,” Municipal economy of cities, vol. 4, no. 185, pp. 221–227, Sep. 2024, doi: 10.33042/2522-1809-2024-4-185-221-227.
T. Musungwa and P. Kowe, “Effects of occupational health and safety management systems implementation in accident prevention at a Harare beverage company,” Cogent Eng, vol. 9, no. 1, Dec. 2022, doi: 10.1080/23311916.2022.2124638.
C. Mitrakas, A. Xanthopoulos, and D. Koulouriotis, “Techniques and Models for Addressing Occupational Risk Using Fuzzy Logic, Neural Networks, Machine Learning, and Genetic Algorithms: A Review and Meta-Analysis,” Applied Sciences, vol. 15, no. 4, p. 1909, Feb. 2025, doi: 10.3390/app15041909.
S. Hassan, J. Wang, C. Kontovas, and M. Bashir, “Modified FMEA hazard identification for crosscountry petroleum pipeline using Fuzzy Rule Base and approximate reasoning,” J Loss Prev Process Ind, vol. 74, p. 104616, Jan. 2022, doi: 10.1016/j.jlp.2021.104616.
T. Eskandari and I. Mohammadfam, “Application of Fuzzy Bayesian Network in Dynamic Risk Analysis of Explosion in Process Industries,” Health in Emergencies & Disasters Quarterly, vol. 10, no. 03, pp. 193–206, Apr. 2025, doi: 10.32598/hdq.10.3.466.3.
L. Yang, P. Wang, W. Zhao, C. Wang, X. Wu, and M. G. R. Faes, “On investigation of the Bayesian anomaly in multiple imprecise dependent information aggregation for system reliability evaluation,” International Journal of Intelligent Systems, vol. 36, no. 6, pp. 2895–2921, Jun. 2021, doi: 10.1002/int.22405.
B. Hong, B. Shao, J. Guo, J. Fu, C. Li, and B. Zhu, “Dynamic Bayesian network risk probability evolution for third-party damage of natural gas pipelines,” Appl Energy, vol. 333, p. 120620, Mar. 2023, doi: 10.1016/j.apenergy.2022.120620.
S. Qi, J. Shuai, L. Shi, Y. Li, and L. Zhou, “Quantitative risk assessment of leakage accident of crude oil storage tank based on fuzzy Bayesian network and improved AHP,” J Loss Prev Process Ind, vol. 90, p. 105341, Aug. 2024, doi: 10.1016/j.jlp.2024.105341.
Q.-Y. Zhou, B. Li, Y. Lu, J. Chen, C.-M. Shu, and M. Bi, “Dynamic risk analysis of oil depot storage tank failure using a fuzzy Bayesian network model,” Process Safety and Environmental Protection, vol. 173, pp. 800–811, May 2023, doi: 10.1016/j.psep.2023.03.072.
Y. Liu et al., “Failure Risk Assessment of Coal Gasifier Based on the Integration of Bayesian Network and Trapezoidal Intuitionistic Fuzzy Number-Based Similarity Aggregation Method (TpIFN-SAM),” Processes, vol. 10, no. 9, p. 1863, Sep. 2022, doi: 10.3390/pr10091863.
L. Wei, “Application of Bayesian Algorithm in Risk Quantification for Network Security,” Comput Intell Neurosci, vol. 2022, pp. 1–10, Jul. 2022, doi: 10.1155/2022/7512289.
N. Dong, N. Nair, and D. Du, “Scalable Bayesian Nonparametric Method for Clinical Risk Prediction Using Large-Scale Data From Heterogeneous Populations,” IEEE J Biomed Health Inform, vol. 29, no. 10, pp. 7514–7524, Oct. 2025, doi: 10.1109/JBHI.2025.3567944.
M. Ollenschläger et al., “MaD GUI: An Open-Source Python Package for Annotation and Analysis of Time-Series Data,” Sensors, vol. 22, no. 15, p. 5849, Aug. 2022, doi: 10.3390/s22155849.
A. Nakamura, “lys: interactive multi-dimensional data analysis and visualization platform,” J Open Source Softw, vol. 8, no. 92, p. 5869, Dec. 2023, doi: 10.21105/joss.05869.
X. He, Z. Wang, and S. Zhan, “Design and implementation of interactive image measurement software based on Tkinter and PIL library,” in Proceedings of the 4th International Conference on Computer, Artificial Intelligence and Control Engineering, New York, NY, USA: ACM, Jan. 2025, pp. 564–568. doi: 10.1145/3727648.3727740.
C. Ji, X. Su, Z. Qin, and A. Nawaz, “Probability Analysis of Construction Risk based on Noisy-or Gate Bayesian Networks,” Reliab Eng Syst Saf, vol. 217, p. 107974, Jan. 2022, doi: 10.1016/j.ress.2021.107974.
C. Bao, M. Cai, J. Li, Q. Zheng, D. Wu, and Q. Meng, “Risk aggregation considering probabilistic and consequential interactions: A general formulation with computational cost handling,” Risk Analysis, vol. 44, no. 6, pp. 1440–1459, Jun. 2024, doi: 10.1111/risa.14253.
L. Famiglini, A. Campagner, M. Barandas, G. A. La Maida, E. Gallazzi, and F. Cabitza, “Evidencebased XAI: An empirical approach to design more effective and explainable decision support systems,” Comput Biol Med, vol. 170, p. 108042, Mar. 2024, doi: 10.1016/j.compbiomed.2024.108042.
R. K. Khamaisi, M. Peruzzini, R. Raffaeli, G. Mangia, and M. Pellicciari, “Designing adaptive human- cyber-physical systems to improve industrial tasks: a methodological approach,” The International Journal of Advanced Manufacturing Technology, vol. 136, no. 9, pp. 4067–4082, Feb. 2025, doi: 10.1007/s00170-024-14698-y.
C. Bajan and G. Lambard, “MADGUI: Multi-Application Design Graphical User Interface for active learning assisted by Bayesian optimization,” Chemometrics and Intelligent Laboratory Systems, vol. 258, p. 105323, Mar. 2025, doi: 10.1016/j.chemolab.2025.105323.
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.
