摘要：

本文针对地热采出井流体闪蒸相变问题，通过设计强制循环可视化实验平台，系统探究了闪蒸过程中流型演化规律及压差波动信号特征，并基于信号分解与机器学习方法实现了流型的高精度识别。该平台包含流体动力控制、温度调控、动态数据采集及可视化实验管段等部件，通过高速摄像记录了闪蒸引发的汽液两相流型(泡状流、弹状流、搅动流、环状流)，明确了各流型的触发条件(如压力梯度、温度分布)与形态特征(气泡尺寸、液膜稳定性)。实验采集了可视化管道2~3 m高度区间内的压差波动信号，发现不同流型的压差信号在振幅范围、振荡频率及信号形态上呈现显著差异：泡状流表现为高频小振幅随机波动，弹状流为低频中振幅周期性振荡，搅动流为宽频高振幅无序扰动，环状流则为周期特大振幅的液膜断裂主导波动，验证了压差信号与流型的强相关性。进一步结合经验模态分解(EMD)与互补集合经验模态分解(CEEMD)对压差信号进行分解，结果表明CEEMD能有效提取各流型的本征模态函数(IMF)分量及能量谱信息，为流型特征量化提供了关键依据。最终，基于PSO优化的最小二乘支持向量机(PSO-LSSVM)模型，利用入口温度、流速及压差波动信号的IMF能量频谱等多参数组合，实现了对闪蒸流型的高精度识别(流型识别准确率可达到97%以上)。本研究为地热采出井闪蒸起始位置定位、剧烈程度评估提供了理论方法与技术支撑，对优化井筒设计及提高地热能开采效率具有重要工程意义。

关键词: 采出井, 闪蒸相变, 最小二乘支持向量机, 流型识别

Abstract:

This study addresses the fluid flash evaporation phase change in geothermal production wells. A forced circulation visual experimental platform was designed to investigate flow pattern evolution and differential pressure fluctuation characteristics during flash evaporation, and high-precision flow pattern recognition was achieved via signal decomposition and machine learning. Key steps include: constructing an experimental system with fluid dynamic control, temperature regulation, data acquisition, and a visual pipe section; recording flow patterns (bubble, slug, churn, annular flow) via high-speed photography and analyzing their triggering conditions/morphological features; collecting differential pressure signals (2~3 meters height) and identifying distinct amplitude-frequency-morphology characteristics among flow patterns; applying CEEMD to decompose signals and extract IMF energy spectra; and developing a PSO-LSSVM model using multi-parameters (inlet temperature, velocity, IMF spectra) for high-accuracy recognition. Results provide theoretical support for flash evaporation localization and severity assessment, aiding wellbore optimization and geothermal extraction efficiency improvement.

Key words: geothermal production well, flash evaporation, least Squares SVM, flow pattern identification

中图分类号: 

• TE312

• P314