Study on multi-factor casing damage prediction method based on machine learning

Fuli Li, Wei Yan, Xianyong Kong, Juan Li, Wei Zhang, Zeze Kang, Tao Yang, Qing Tang, Kongyang Wang and Chaodong Tan

Energy, 2024, vol. 296, issue C

Abstract: Casing damage is one of the common problems encountered in reservoir development, which seriously affects the normal production of the oil field. In this study, through the analysis of oil field data, a casing damage model under the coupling effects of mudstone hydration-corrosion and sand production-corrosion was established. Thirty-four influencing factors of casing damage were determined in four categories: geology, engineering, development, and corrosion. Six machine learning methods were used to predict the probability of casing damage under the coupling effects of multiple factors. The generalization performance of the model was evaluated using the recall rate of casing damage wells and accuracy. The results show that the random forest and LightGBM models show the best generalization performance. The prediction accuracy rates of the two models on the test set were 84.2% and 85.9%, respectively, and the random forest model showed an excellent performance of 92.3% on the recall rate of casing damage wells. Finally, the optimized model was used to perform sensitivity analysis on each influencing factor, and the main controlling factors of casing damage were obtained. Engineering measures to prevent casing damage are proposed. This study has made outstanding contributions to improving the economic benefits of the oilfield.

Keywords: Casing damage prediction; Multi-factor coupling; Model selection; Machine learning; Sensitivity analysis; Preventive measures (search for similar items in EconPapers)
Date: 2024
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0360544224008168
Full text for ScienceDirect subscribers only

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:eee:energy:v:296:y:2024:i:c:s0360544224008168

DOI: 10.1016/j.energy.2024.131044

Access Statistics for this article

Energy is currently edited by Henrik Lund and Mark J. Kaiser

More articles in Energy from Elsevier
Bibliographic data for series maintained by Catherine Liu ().