SISTEM PAKAR HYBRID CF-NAIVE BAYES UNTUK DIAGNOSIS GANGGUAN P&ID DISTILASI BENZENA
DOI:
https://doi.org/10.53026/prosidingsntem.v5i1.688Keywords:
Sistem Pakar, Certainty Factor, Naïve Bayesian, Distilasi, P&IDAbstract
Diagnosis gangguan pada P&ID sistem distilasi benzena merupakan tantangan kompleks yang membutuhkan keahlian teknis mendalam. Penelitian ini bertujuan mengembangkan prototipe sistem pakar hybrid yang mengintegrasikan metode Certainty Factor (CF) dan Naive Bayes. Kombinasi ini dipilih untuk menggabungkan kekuatan aturan pakar (CF) yang tegas dalam mereplikasi alur pikir ahli dengan kemampuan Naive Bayes dalam mengelola ketidakpastian data gejala yang tidak lengkap. Metode penelitian mencakup perancangan knowledge base dengan 114 gejala dan 60 aturan, yang diperkuat dengan integrasi prinsip-prinsip Kister's Distillation Operation untuk fenomena kritis seperti flooding dan pinching. Hasil validasi sistem menggunakan 30 test case menunjukkan akurasi hybrid keseluruhan mencapai 86,7%, secara signifikan mengungguli metode baseline tunggal yaitu Certainty Factor (83,3%) maupun Naive Bayes (80,0%). Secara khusus, akurasi diagnosis pada 15 kasus yang diperkuat analisis Kister (Studi Kasus Literatur) terbukti sangat tinggi, mencapai 93,3%. Kesimpulannya, prototipe sistem pakar hybrid ini terbukti efektif dan konsisten dalam mentransfer pengetahuan ahli yang kompleks ke dalam platform digital untuk diagnosis gangguan P&ID.
Downloads
References
N. M. Tahir, J. Zhang, and M. Armstrong, “Control of Heat-Integrated Distillation Columns: Review, Trends, and Challenges for Future Research,” Processes, vol. 13, no. 1, p. 17, Dec. 2024, doi: 10.3390/pr13010017.
L. S. Balhorn et al., “Rule-based autocorrection of Piping and Instrumentation Diagrams (P& IDs) on graphs,” 2025, doi: 10.48550/ARXIV.2502.18493.
X. Wen, W. Bai, T. Ren, J. Wang, A. Kummer, and J. Lv, “An open-source dataset of heat-integrated side-stream extractive distillation process to support development of fault diagnosis algorithms,” Process Safety and Environmental Protection, vol. 203, p. 107884, Sep. 2025, doi: 10.1016/j.psep.2025.107884.
W. Li, H. Li, S. Gu, and T. Chen, “Process fault diagnosis with model- and knowledge-based approaches: Advances and opportunities,” Control Engineering Practice, vol. 105, p. 104637, Sep. 2020, doi: 10.1016/j.conengprac.2020.104637.
G. Asbjörnsson, L. M. Tavares, A. Mainza, and M. Yahyaei, “Different perspectives of dynamics in comminution processes,” Minerals Engineering, vol. 176, p. 107326, Dec. 2021, doi: 10.1016/j.mineng.2021.107326.
W. Wang, F. D. Maio, and E. Zio, “Considering the human operator cognitive process for the interpretation of diagnostic outcomes related to component failures and cyber security attacks,” Reliability Engineering & System Safety, vol. 202, p. 107007, May 2020, doi: 10.1016/j.ress.2020.107007.
M. S. Farooq et al., “Harnessing AI forward and backward chaining with telemetry data for en-hanced diagnostics and prognostics of smart devices,” Scientific Reports, vol. 15, no. 1, Mar. 2025, doi: 10.1038/s41598-025-89266-9.
P. Kumari, D. Lee, Q. Wang, M. N. Karim, and J. S. Kwon, “Root Cause Analysis of Key Process Variable Deviation for Rare Events in the Chemical Process Industry,” Industrial & Engineering Chemistry Research, vol. 59, no. 23, p. 10987, May 2020, doi: 10.1021/acs.iecr.0c00624.
H. Nikpour and A. Aamodt, “Fault diagnosis under uncertain situations within a Bayesian knowledge-intensive CBR system,” Progress in Artificial Intelligence, vol. 10, no. 3, p. 245, Mar. 2021, doi: 10.1007/s13748-020-00227-x.
Y. Wang, W. Jiang, Weikai Ma, P. Han, and Z. Han, “Intelligent Diagnosis Methods and Strategies for Systemic Faults in Petrochemical Processes: A Review.” Jan. 01, 2025. doi: 10.2139/ssrn.5136340.
A. Wijanarko, M. Hidayat, and S. Sutijan, “Evaluation of Jet Flooding in Distillation Column Olefins Plant on Naphtha to LPG Feed Substitution,” May 2023, doi: 10.20944/preprints202305.0392.v1.
Downloads
Published
Issue
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.
