基于物理信息神经网络的油气管道内腐蚀预测方法

周涛涛, 刘迎正, 郑文培, 姜恒良, 刘海鹏, 夏刚

Pipeline Corrosion Prediction Method Based on Physics-informed Neural Networks

ZHOU Taotao, LIU Yingzheng, ZHENG Wenpei, JIANG Hengliang, LIU Haipeng, XIA Gang

图5 不同模型预测的管道在不同温度下的腐蚀速率随pCO2的变化

Fig.5 Corrosion rate vs. pCO2 curves obtained for pipelines by SVM (a), XGBoost (b), ANN (c) and PINN (d) at different temperatures