Multi-criteria optimization of sucker rod pump operation using AHP–TOPSIS based decision analysis for predictive paraffin control
Article Sidebar
Main Article Content
Abstract
This study presents an integrated methodological framework for optimizing the operation of sucker rod pumps affected by paraffin deposition through the application of multi-criteria decision-making techniques. Predictive maintenance (PdM) data collected from five production wells were analyzed to evaluate performance indicators before and after implementation of paraffin control procedures. The Analytic Hierarchy Process (AHP) was used to determine the relative importance of key performance criteria (post-PdM downtime, reduction percentage, and post-maintenance operational stability) and the Technique for Order Preference by Similarity to the Ideal Solution (TOPSIS) ranked the wells according to their overall efficiency and reliability. Results indicated that well K-3 had the highest overall performance, with minimal downtime and low operational variability; wells K-1 and K-5 followed in the ranking. The combined AHP-TOPSIS approach provided a systematic decision support tool for prioritizing investments in automation, monitoring and maintenance strategies within oil production systems. The findings indicate that integrating MCDM methods with predictive maintenance data improves the accuracy of decision making and supports operational optimization in petroleum production environments.
Article Details
References
[1] A. Abbas, “AI for Predictive Maintenance in Industrial Systems”, International Journal of Advanced Engineering Technologies and Innovations, Vol. 1(1), pp. 31–51, (2024)
[2] J. Dalzochio, R. Kunst, E. Pignaton, A. Binotto, S. Sanyal, J. Favilla, and J. Barbosa, “Machine learning and reasoning for predictive maintenance in Industry 4.0: Current status and challenges”, Computers in Industry, Vol. 123, p. 103298, https://doi.org/10.1016/j.compind.2020.103298, (2020)
[3] W. Li and T. Li, “Comparison of deep learning models for predictive maintenance in industrial manufacturing systems using sensor data”, Scientific Reports, Vol. 15(1), p. 23545, https://doi.org/10.1038/s41598-025-08515-z, (2025)
[4] M. A. Rahman, M. F. Shahrior, K. Iqbal, and A. A. Abushaiba, “Enabling intelligent industrial automation: A Review of machine learning applications with digital twin and edge AI Integration”, Autom. 2025, Vol. 6(3), p. 37, https://doi.org/10.3390/automation6030037, (2025)
[5] J. Li, B. Liang, C. Li, M. Yan, and J. Yu, “Calculation methods for the gas pipeline failure rate”, Journal of Petroleum Science and Engineering, Vol. 174, pp. 229–234, https://doi.org/10.1016/j.petrol.2018.11.020, (2019)
[6] B. Z. Novaković, L. Djordjević, M. Đurđev, Lj. Radovanović, N. Zuber, E. Desnica, and M. Bakator, “Effect of changes in hydraulic parameters and tank capacity of the hydraulic press system on the heating of the hydraulic oil”, Eksploatacja i Niezawodność – Maintenance and Reliability, Vol. 26(4), https://doi.org/10.17531/ein/190826, (2024)
[7] A. Ucar, M. Karakose, and N. Kırımça, “Artificial intelligence for predictive maintenance applications: Key components, trustworthiness, and future trends”, Appl. Sci. 2024, Vol. 14(2), p. 898, https://doi.org/10.3390/app14020898, (2024)
[8] I. Ul Hassan, K. Panduru, and J. Walsh, “Predictive maintenance in Industry 4.0: A review of data processing methods”, Procedia Computer Science, Vol. 257, pp. 896–903, https://doi.org/10.1016/j.procs.2025.03.115, (2025)
[9] M. Belim, T. Meireles, G. Gonçalves, and R. Pinto, “Forecasting models analysis for predictive maintenance”, Frontiers in Manufacturing Technology, Vol. 4, p. 1475078, https://doi.org/10.3389/fmtec.2024.1475078, (2024)
[10] A. Shamayleh, M. Awad, and J. Farhat, “IoT based predictive maintenance management of medical equipment”, Journal of Medical Systems, Vol. 44(4), 72, https://doi.org/10.1007/s10916-020-1534-8, (2020)
[11] J. H. Ccatamayo-Barrios, Y. L. Huamán-Romaní, M. V. Seminario-Morales, M. M. Flores-Castillo, E. Gutiérrez-Gómez, L. K. Carrillo-De la cruz, K. A. de la Cruz-Girón, “Comparative analysis of AHP and TOPSIS multi-criteria decision-making methods for mining method selection”, Mathematical Modelling of Engineering Problems, Vol. 10(5), pp. 1665–1674, https://doi.org/10.18280/mmep.100516, (2023)
[12] S. Hussain, J. H. Chen, and T. Hussain, “Decision-making framework for improving bank performance in emerging markets: The analysis of AHP-TOPSIS and AHP-GRA models”, Journal of Central Banking Theory and Practice, Vol. 13(3), pp. 191–218, https://doi.org/10.2478/jcbtp-2024-0027, (2024)
[13] M. Alemi, H. Jalalifar, G. Kamali, M. Kalbasi, “A prediction to the best artificial lift method selection on the basis of TOPSIS model”, Journal of Petroleum and Gas Engineering, Vol. 1(1), pp. 009-015, (2010)