Scholarlink

<p>Mitigating vortex-induced vibrations (VIV) in flexible risers represents a critical concern in offshore oil and gas production, considering its potential impact on operational safety and efficiency. The accurate prediction of displacement and position of VIV in flexible risers remains challenging under actual marine conditions. This study presents a data-driven model for riser displacement prediction that corresponds to field conditions. Experimental data analysis reveals that the XGBoost algorithm predicts the maximum displacement and position with superior accuracy compared with Support vector regression (SVR), considering both computational efficiency and precision. Platform displacement in the <i>Y</i>-direction demonstrates a significant positive correlation with both axial depth and maximum displacement magnitude. The fourth point displacement exhibits the highest contribution to model prediction outcomes, showing a positive influence on maximum displacement while negatively affecting the axial depth of maximum displacement. Platform displacement in the <i>X</i>- and <i>Y</i>-directions exhibits competitive effects on both the riser’s maximum displacement and its axial depth. Through the implementation of XGBoost algorithm and SHapley Additive exPlanation (SHAP) analysis, the model effectively estimates the riser’s maximum displacement and its precise location. This data-driven approach achieves predictions using minimal, readily available data points, enhancing its practical field applications and demonstrating clear relevance to academic and professional communities.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Data-Driven Prediction of Maximum Displacement of Flexible Riser Based on Movement of Platform

  • 期刊论文

  • 发表日期：

    2025年10月10日

查看全文
  • Jin-ze Song,
  • Yu-ze Wu,
  • Yu-fa He,
  • Shui-gen Zhou,
  • Hong-jun Zhu,
  • Kai-rui Deng

摘要

Mitigating vortex-induced vibrations (VIV) in flexible risers represents a critical concern in offshore oil and gas production, considering its potential impact on operational safety and efficiency. The accurate prediction of displacement and position of VIV in flexible risers remains challenging under actual marine conditions. This study presents a data-driven model for riser displacement prediction that corresponds to field conditions. Experimental data analysis reveals that the XGBoost algorithm predicts the maximum displacement and position with superior accuracy compared with Support vector regression (SVR), considering both computational efficiency and precision. Platform displacement in the Y-direction demonstrates a significant positive correlation with both axial depth and maximum displacement magnitude. The fourth point displacement exhibits the highest contribution to model prediction outcomes, showing a positive influence on maximum displacement while negatively affecting the axial depth of maximum displacement. Platform displacement in the X- and Y-directions exhibits competitive effects on both the riser’s maximum displacement and its axial depth. Through the implementation of XGBoost algorithm and SHapley Additive exPlanation (SHAP) analysis, the model effectively estimates the riser’s maximum displacement and its precise location. This data-driven approach achieves predictions using minimal, readily available data points, enhancing its practical field applications and demonstrating clear relevance to academic and professional communities.