论文部分内容阅读
A neural network with a feed forward topology and Bayesian regularization training algorithm is used to predict the austenite formation temperatures(A c1and A c3)by considering the percentage of alloying elements in chemical composition of steel.The data base used here involves a large variety of different steel types such as structural steels,stainless steels,rail steels,spring steels,high temperature creep resisting steels and tool steels.Scatter diagrams and mean relative error(MRE)statistical criteria are used to compare the performance of developed neural network with the results of Andrew′s empirical equations and a feed forward neural network with“gradient descent with momentum”training algorithm.The results showed that Bayesian regularization neural network has the best performance.Also,due to the satisfactory results of the developed neural network,it was used to investigate the effect of the chemical composition on A c1and A c3temperatures.Results are in accordance with materials science theories.
A neural network with a feed forward topology and Bayesian regularization training algorithm is used to predict the austenite formation temperatures (A c1 and A c3) by considering the percentage of alloying elements in chemical composition of steel.The data base used here involves a large variety of different steel types such as structural steels, stainless steels, rail steels, spring steels, high temperature creep resisting steels and tool steels.Scatter diagrams and mean relative error (MRE) statistical criteria are used to compare the performance of developed neural network with the results of Andrew’s empirical equations and a feed forward neural network with “gradient descent with momentum ” training algorithm. The results showed that Bayesian regularization neural network has the best performance. Als, due to the satisfactory results of the developed neural network, it was used to investigate the effect of the chemical composition on A c1 and A c3temperatures. Results are in accordance with m aterials science theories.