用反向传播人工神经网络预测低碳低合金钢的马氏体转变开始温度

根据收集和整理的实验数据，建立了低碳低合金钢的成分与马氏体转变开始温度(M.点)的反向传播(BP)人工神经网络，用这种方法预测了一些钢的M.点，并与用其它经验公式得到的结果进行了比较．结果表明：用人工神经网络能更精确地预测钢的M.点，预测精度明显高于其它线性经验公式．另外用正交实验法设计了几种基准成分的钢，用人工神经网络分析了几种合金元素对M.点的定量影响，计算结果表明，与传统的经验公式表达的信息不同，合金元素的含量与钢的M.点间表现为非线性关系．可以认为，这种非线性关系是由合金元素间复杂的交互作用引起的．

PREDICTING THE MARTENSITIC TRANSFORMATION START TEMPERATURE USING BACK-PROPAGATION ARTIFICIAL NEURAL NETWORKS

The back-propagation artificial neural network was established using data collected from domestic and foreign literatures and the Ms temperatures of some steels were predicted by using the network and compared with those acquired from other methods. Results indicate that the Ms temperatures can be predicted more accurately using artificial neural networks. Moreover, the influence of alloying elements on Ms temperatures was analysed quantitatively using artificial neural networks. The results show that there exists nonlinear relationship between contents of alloying elements in steels and their MS temperature which is related to the interaction among the alloying elements.