摘要：To address the complexity of predicting the viscosity-temperature relationship in the pipeline transportation of highly viscous and gel-prone crude oil, this paper innovatively proposes a combinatorial Machine Learning Models that integrates the strengths of multiple algorithms. By leveraging the DBSCAN and the XGBoost, the robustness and generalization capability of viscosity-temperature characteristic prediction are significantly enhanced. The results demonstrate that this model achieves mean absolute percentage errors (MAPE) of 5.39% and 1.77% for the prediction of consistency coefficient K and flow behavior index n, respectively, while keeping the viscosity prediction error within 10%. The model also exhibits outstanding performance in sensitivity to data volume and cross-condition adaptability validation, providing a high-precision and transparent prediction tool for crude oil flow assurance. ? 2025 IEEE.

ISSN号：2833-2415

卷、期、页：页881-885

发表日期：2025-01-01

期刊分区（SCI为中科院分区）：无

收录情况：EI（工程索引）

发表期刊名称：2025 IEEE 7th International Conference on Communications, Information System and Computer Engineering, CISCE 2025

参与作者：李皓,王怡然,张春,吴尚书

第一作者：马杰,苏怀

论文类型：会议论文

论文概要：李皓,马杰,王怡然,张春,吴尚书,苏怀，A Combinatorial Machine Learning Models -Based Method for Predicting the Viscosity-Temperature Relationship of Crude Oil，2025 IEEE 7th International Conference on Communications, Information System and Computer Engineering, CISCE 2025，2025，页881-885

论文题目：A Combinatorial Machine Learning Models -Based Method for Predicting the Viscosity-Temperature Relationship of Crude Oil