用机器学习估算油井井底压力，精度超98%且成本低
Soft Sensor for Bottom-Hole Pressure Estimation in Petroleum Wells Using Long Short-Term Memory and Transfer Learning
- 用LSTM模型结合井口数据预测井底压力
- 真实海上数据测试下平均误差低于2%
- 支持跨工况迁移学习，适合多种油田应用
监测石油井的井底参数对生产优化、安全和减排至关重要。永久井下压力计（PDGs）虽能提供实时压力数据，但存在可靠性差和成本高的问题。本文提出一种基于机器学习的软传感器，利用井口和上部测量数据估算流动井底压力（BHP）。引入长短期记忆（LSTM）模型，并与多层感知机（MLP）和岭回归进行对比。首次将迁移学习应用于不同作业环境间的模型适应。在巴西盐下盆地真实海上数据集上测试，该方法的平均绝对百分比误差（MAPE）持续低于2%，优于基准模型。本研究提供了一种经济高效、高精度的物理传感器替代方案，适用于多种储层和流动条件。
原文摘要 · Abstract (English)
Monitoring bottom-hole variables in petroleum wells is essential for production optimization, safety, and emissions reduction. Permanent Downhole Gauges (PDGs) provide real-time pressure data but face reliability and cost issues. We propose a machine learning-based soft sensor to estimate flowing Bottom-Hole Pressure (BHP) using wellhead and topside measurements. A Long Short-Term Memory (LSTM) model is introduced and compared with Multi-Layer Perceptron (MLP) and Ridge Regression. We also pioneer Transfer Learning for adapting models across operational environments. Tested on real offshore datasets from Brazil's Pre-salt basin, the methodology achieved Mean Absolute Percentage Error (MAPE) consistently below 2\%, outperforming benchmarks. This work offers a cost-effective, accurate alternative to physical sensors, with broad applicability across diverse reservoir and flow conditions.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。