OPTIMASI PREDIKSI LAJU ALIRAN PIPA KILANG MENGGUNAKAN KECERDASAN BUATAN BERBASIS ALGORITMA GENETIKA
DOI:
https://doi.org/10.53026/prosidingsntem.v5i1.758Keywords:
Algoritma Genetika, Prediksi Laju Aliran, Darcy-Weisbach, Hybrid Data-Fisika, Optimasi Pipa KilangAbstract
Prediksi laju aliran fluida yang akurat sangat penting dalam operasi pipa kilang untuk meningkatkan efisiensi dan mencegah risiko operasional. Penelitian ini bertujuan mengembangkan model prediksi laju aliran menggunakan Algoritma Genetika (GA) berbasis pendekatan hybrid datafisika dengan persamaan Darcy-Weisbach. Metode GA digunakan untuk mengoptimasi parameter model dengan meminimalkan fungsi objektif hybrid yang menggabungkan mean squared error data (MSE_data) dan error fisika (MSE_fisika). Tiga skenario percobaan dilakukan dengan variasi ukuran populasi (40–120), jumlah generasi (80–300), tingkat crossover (0,70–0,85), tingkat mutasi (0,02–0,12), dan bobot data (λ = 0,5–0,9). Dataset sintetis sebanyak 500 data poin dibangkitkan berdasarkan persamaan Darcy-Weisbach dengan parameter tekanan (100-500 kPa), diameter pipa (0,1-0,5 m), viskositas (0,001-0,01 Pa·s), dan kekasaran relatif (0,00001-0,001). Hasil menunjukkan bahwa konfigurasi optimal dicapai pada percobaan ketiga dengan populasi 120, generasi 300, crossover 0,85, mutasi 0,02, dan λ = 0,9, menghasilkan MSE (data) = 2,324, MSE (fisika) = 9,08 × 10⁸, dan R² = 0,8624. Peningkatan R² dari 0,087 (percobaan 1) menjadi 0,8624 (percobaan 3) menunjukkan efektivitas pendekatan hybrid dalam menyeimbangkan pembelajaran empiris dengan constraint fisika.
References
J. Zhou, G. Liang, T. Deng, and J. Gong, “Route Optimization of Pipeline in Gas-Liquid Two-Phase Flow Based on Genetic Algorithm,” Int. J. Chem. Eng., vol. 2017, pp. 1–9, 2017, doi: 10.1155/2017/1640303.
A. K. Arya, R. Jain, S. Yadav, S. Bisht, and S. Gautam, “Recent trends in gas pipeline optimization,” Mater. Today Proc., vol. 57, pp. 1455–1461, 2022, doi: 10.1016/j.matpr.2021.11.232.
H. Lü and Y. F. Cheng, “Artificial Intelligence in Energy Pipelines: Opportunities and Risks,” Engineering, 2025, doi: 10.1016/j.eng.2025.08.032.
Y. M. Liu, Q. Guo, W. Xie, and S. Wang, "Enhanced Leak Detection and Localization in Liquid Pipelines Using an Improved Extended Kalman Filter," Processes, vol. 13, no. 5, p. 1447, 2025, doi: 10.3390/pr13051447.
R. Shakarami and M. T. Sadeghi, “An intelligent flow measurement system based on pressure drop in straight pipeline: a deep learning approach,” Sci. Rep., vol. 15, no. 1, 2025, doi: 10.1038/s41598-025-19401-z.
T. Zheng, H. Song, and M. Li, “Research on Interpretation Method of Oil–Water Two-Phase Production Profile Using Artificial Intelligence Algorithm,” Processes, vol. 13, no. 3, 2025, doi: 10.3390/pr13030886.
L. Wei, L. Wang, Q. Zhou, and Y. Gao, “Prediction of oil pipeline process operating parameters based on mechanism and data mining,” J. Energy Resour. Technol., vol. 146, no. 11, 2024, doi: 10.1115/1.4065951.
X. Wu, C. Li, Y. He, and W. Jia, “Operation Optimization of Natural Gas Transmission Pipelines Based on Stochastic Optimization Algorithms: A Review,” Math. Probl. Eng., vol. 2018, 2018, doi: 10.1155/2018/1267045.
M. E. Takerhi and K. Dąbrowski, “Optimization of a gas network fuel consumption with genetic algorithm,” Energy Explor. Exploit., vol. 41, no. 2, pp. 344–369, 2023, doi: 10.1177/01445987221117182.
D. Karabaić, M. Kršulja, S. Maričić, and L. Liverić, “The Optimization of a Subsea Pipeline Installation Configuration Using a Genetic Algorithm,” J. Mar. Sci. Eng., vol. 12, no. 1, 2024, doi: 10.3390/jmse12010156.
. Meng, S. Seo, D. Cao, S. Griesemer, and Y. Liu, “When Physics Meets Machine Learning: A Survey of Physics-Informed Machine Learning,” arXiv (Cornell Univ.), 2022, doi: 10.48550/arxiv.2203.16797.
S. H. O. Al-Mansory, O. Al-Fatlawi, and A. Kadkhodaie, “Gas Lift Optimization for Zubair Oil Field Using Genetic Algorithm-Based Numerical Simulation: Feasibility Study,” Iraqi J. Chem. Pet. Eng., vol. 25, no. 2, pp. 161–174, 2024, doi: 10.31699/ijcpe.2024.2.15.
J. X. Wang and H. Xiao, “Data-driven CFD modeling of turbulent flows through complex structures,” Int. J. Heat Fluid Flow, vol. 62, pp. 138–149, 2016, doi: 10.1016/j.ijheatfluidflow.2016.11.007.
F. Gong, X. Zhao, C. Du, K. Zheng, Z. Shi, and H. Wang, “Pressure and Temperature Prediction of Oil Pipeline Networks Based on a Mechanism-Data Hybrid Driven Method,” Inf., vol. 15, no. 11, 2024, doi: 10.3390/info15110709.
C. Borraz-Sánchez and R. Z. Ríos-Mercado, “A hybrid meta-heuristic approach for natural gas pipeline network optimization,” Lect. Notes Comput. Sci., vol. 3636, pp. 54–65, 2005, doi: 10.1007/11546245_6.
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.
