Prediction of Corrosion Rate of Carbon Steel in Simulated Cooling Water Based on BP Artificial Neural Network

A model for predicting the average corrosion rate of carbon steel in circulating cooling water was built on the basic of BP neural network theory in order to analyzse the problems of corrosion caused by simulated circulating cooling water. In this model, pH, Cl-, Ca2+, SO42-, HCO3- and temperature were set as input parameters while the average corrosion rate was the output parameter. The results show that the model has good forecasting accuracy and it could reflect the corrosion factors effectively.