L360钢在H_2S/CO_2环境中腐蚀的预测

Prediction of Corrosion Rate of L360 Steel in H_2S/CO_2 Environment

运用BP人工神经网络技术建立了预测L360钢在H_2S/CO_2环境中腐蚀的模型,神经网络拓扑结构为5-4-1,网络模型训练成功以后,应用它预测L360钢在H_2S/CO_2中的腐蚀速度.结果表明,人工神经网络模型预测的结果与实验数据相当符合,误差在14%以内.由此可见,BP神经网络模型可以作为预测H_2S/CO_2环境致集输管线腐蚀速率的工具.

An BP（back-propagation） aritifical neueal network（ANN） model for the predicting of the corrosion rate of L360 steel in H_2S/CO2 environment was established,neural network architecture is 5-4-1.After the successive training,the model could be applied to predict the corrosion rate of L360 steel in H_2S/CO2 environment.The forecast results from the network model are in good agreement with the experimental data,the comparative error is less than 14%.Application of BP aritifical neural network to predict the corrosion rate of gathering and transport pipeline in H_2S/CO_2 environment is feasible.