Neural network analysis for corrosion of steel in concrete

A systematic study to develop a suitable method that can accept, analyze and evaluate experimental data that are at random and/or influenced by external, unpredictable variables has been carried out, using the back propagation method. This method is fast and is able to produce an output that has minimum error for this experimental setup. This has resulted in the development of back propagation neural network, that can train and test the system, to calculate the specified parameter for different conditions and recognize the behavioural pattern. Using this methodology, the corrosion of the steel embedded in concrete is analyzed and it is observed that the error encountered is only about 5% for the predictions made from the analysis.