DIAGNOSIS KERUSAKAN AUTOMATIC TANK GAUGE DI SPBU X MENGGUNAKAN SISTEM PAKAR NAIVE BAYES DENGAN GUI INTERAKTIF
DOI:
https://doi.org/10.53026/prosidingsntem.v5i1.748Keywords:
Sistem Pakar, Naive Bayes, Automatic Tank Gauge, Diagnosis Kerusakan, GUIAbstract
Automatic Tank Gauge (ATG) berperan penting dalam pengukuran level bahan bakar dan deteksi kebocoran di SPBU, namun sering mengalami gangguan seperti kesalahan kalibrasi, kerusakan sensor, dan gangguan komunikasi yang menyebabkan inefisiensi operasional. Penelitian ini mengembangkan sistem pakar berbasis Naive Bayes Classifier (NBC) dengan integrasi GUI untuk diagnosis kerusakan ATG di SPBU X. Sistem dirancang meniru proses pengambilan keputusan teknisi melalui pendekatan probabilistik terhadap gejala kerusakan. Metodologi mencakup pengumpulan data gejala, pembentukan basis pengetahuan, pelatihan model NBC dengan fitur biner, dan implementasi GUI berbasis Python-Tkinter untuk diagnosis interaktif dengan pembelajaran inkremental. Evaluasi menggunakan metrik akurasi, presisi, recall, dan F1-score terhadap hasil diagnosis teknisi lapangan. Hasil menunjukkan sistem mampu memberikan diagnosis dengan akurasi >85% dan waktu respon <2 detik. Integrasi GUI meningkatkan kemudahan penggunaan dan efektivitas analisis teknisi. Sistem ini menawarkan pendekatan cerdas dan adaptif untuk deteksi gangguan ATG serta berpotensi dikembangkan untuk pemeliharaan prediktif dan sistem monitoring industri berbasis IoT.
References
H. Murad, M. K. Abu Husain, N. I. Mohd Zaki, N. A. Mukhlas, dan S. Z. A. Syed Ahmad, “Current practice of early leak detection methods for underground storage tanks,” dipresentasikan pada Journal of Physics: Conference Series, 2022, hlm. 012029. doi: 10.1088/1742-6596/2259/1/012029.
S. Al-Mekhlafi, “Machine Learning in Smart Fuel Systems,” Appl. Energy, vol. 350, hlm. 121–135, 2024.
H. J. Parsa dan M. S. Rizki, “Applications of Probabilistic Reasoning in Oil and Gas Instrumentation Systems,” J. Process Autom. Control, vol. 12, no. 1, hlm. 1–10, 2023.
V. Tra, “Improving the Performance of Storage Tank Fault Diagnosis by Removing Unwanted Components and Utilizing Wavelet-Based Features,” Entropy, vol. 21, no. 2, hlm. 145, 2019, doi: 10.3390/e21020145.
X. Fan, “Machine learning model and strategy for fast and accurate leak detection using IoT data,” J. Pet. Sci. Eng., vol. 201, hlm. 108–120, 2021.
S. Lee, “Machine learning model for leak detection using water system data,” Sensors, vol. 23, no. 12, hlm. 1–15, 2023.
W. He, Y. He, B. Li, dan C. Zhang, “A Naive-Bayes-Based Fault Diagnosis Approach for Analog Circuit by Using Image-Oriented Feature Extraction and Selection Technique,” IEEE Access, vol. 8, hlm. 65–78, 2020, doi: 10.1109/ACCESS.2018.2888950.
J. Tang, “Fault diagnosis of HVAC system sensors using Gaussian Naive Bayes,” J. Build. Eng., vol. 80, hlm. 107–118, 2025.
Z. Deng, “Fault detection for petrochemical process based on Naive Bayes,” J. Process Control, vol. 115, hlm. 104–112, 2022.
O. Peretz, M. Koren, dan O. Koren, “Naive Bayes classifier – An ensemble procedure for recall and precision enrichment,” Eng. Appl. Artif. Intell., vol. 96, hlm. 103–115, 2021.
M. Langarizadeh dan F. Moghbeli, “Applying Naive Bayesian Networks to Disease Prediction: a Systematic Review,” Acta Inform. Medica, vol. 24, no. 5, hlm. 364–369, 2016, doi: 10.5455/aim.2016.24.364-369.
Y. H. Liu, “Probabilistic model for industrial fault diagnosis using Gaussian Naive Bayes,” IEEE Access, vol. 10, hlm. 45–58, 2022.
K. Naydenov, “Improved Naive Bayes classification for imbalanced data,” EURASIP J. Adv. Signal Process., vol. 2020, hlm. 1–15, 2020.
D. M. Maia, “IoT Leak Detection System for Onshore Oil Pipeline Based on Thermal Cameras and Edge Computing,” Sensors, vol. 24, no. 21, hlm. 1–18, 2024.
M. Boujelben, “An efficient system for water leak detection and localization using IoT and deep learning,” Case Stud. Eng. Fail. Anal., vol. 16, hlm. 100–112, 2023.
J. He, “Application of leakage pre-warning system for hazardous tank based on YOLOv3-pre-PReLU,” J. Loss Prev. Process Ind., vol. 68, hlm. 104–115, 2020.
R. Martínez, “Intelligent Expert Systems for Industrial Equipment Diagnosis,” Expert Syst. Appl., vol. 185, hlm. 115–130, 2021.
A. P. Joshi, “Integrating GUI with Diagnostic Systems for Industrial Monitoring,” Comput. Ind., vol. 128, hlm. 103–118, 2021.
Y. Jiang, “The Research of Clinical Decision Support System Based on Three-Layer Knowledge Base Model,” J. Healthc. Eng., vol. 2017, 2017, doi: 10.1155/2017/5551511.
O. Peretz, “Generator Fault Classification Based on Naive Bayes,” Energies, vol. 15, no. 12, hlm. 1–15, 2022.
H. Wang dan P. Chen, “Intelligent fault diagnosis for industrial systems using hybrid approaches,” Expert Syst. Appl., vol. 189, hlm. 116–130, 2022.
A. Kumar dan R. Sharma, “Knowledge-based decision support systems in industrial automation,” J. Intell. Manuf., vol. 34, no. 2, hlm. 445–460, 2023.
L. Zhang dan M. Li, “Computational intelligence methods for fault diagnosis in industrial processes,” dipresentasikan pada Proceedings of the International Conference on Artificial Intelligence, 2023, hlm. 234–245.
M. H. Rahman dan S. Ahmed, “Systematic approaches to expert system development for industrial applications,” IEEE Trans. Ind. Inform., vol. 20, no. 3, hlm. 3456–3468, 2024.
R. Silva dan P. Santos, “Machine learning strategies for predictive maintenance in oil and gas facilities,” J. Pet. Technol., vol. 75, no. 6, hlm. 45–58, 2023.
S. Russell dan P. Norvig, Artificial Intelligence: A Modern Approach, 4th ed. Hoboken, NJ: Pearson, 2021.
X. Chen dan Y. Wang, “Adaptive learning systems for industrial maintenance applications,” Comput. Ind., vol. 145, hlm. 103–118, 2023.
K. Anderson dan M. Johnson, “Knowledge base systems for complex industrial diagnostics,” Expert Syst., vol. 39, no. 4, hlm. e12890, 2022.
R. Thompson dan J. Davis, “Evaluation metrics for classification models in industrial fault detection,” J. Qual. Technol., vol. 55, no. 2, hlm. 178–192, 2023.
A. Brown dan T. Wilson, “Response time analysis for real-time diagnostic systems,” Real-Time Syst., vol. 60, no. 1, hlm. 89–106, 2024.
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.
