ARTIFICIAL NEURAL NETWORK MODELING FOR ATMOSPHERIC CORROSION OF CARBON STEEL AND LOW ALLOY STEEL
用人工神经网络构建碳钢、低合金钢大气腐蚀模型

An artificial neural network(ANN) modeling was developed for the prediction of atmospheric corrosion of carbon steel and low alloy steel,neural network architecture is composed of thirteen input nodes,nineteen hidden layer nodes and one output nodes.The ANN Prediction result is close to practical data.Sensitivity analysis method was used to study the effect of alloy element and environment factors on atmospheric corrosion rate.The result shows this kind of method is effective.