论文部分内容阅读
本文试用人工神经网络总结合金钢研制数据中的规律,并应用偏相关指数表征各影响因子对合金钢性能影响的程度。计算结果表明,IF钢的延伸率、耐低温钢的无塑性变形温度预报值与实测值相当符合。根据偏相关指数绝对值的大小判别影响耐深冲钢合格率的主要因素效果亦佳。
In this paper, artificial neural network is used to summarize the rules in the development of alloy steel. The partial correlation index is used to characterize the influence of each factor on the performance of alloy steel. The calculation results show that the predictions of ductility and ductility of IF steel are in good agreement with the measured values. According to the partial correlation index of the absolute value of the size of the resistance of deep-drawn steel qualified rate of the main factors are also good results.