(1. 清华大学 机械工程系, 北京 100084;
2. 东北大学 材料与冶金学院, 沈阳 110006)
摘 要: 通过分析强脉冲电磁场作用下铝合金凝固组织晶粒尺寸实验数据，并结合人工神经网络，建立了强脉冲电磁场作用下铝合金凝固组织晶粒尺寸的人工神经网络BP算法模型。研究结果表明，用该神经网络模型进行模拟得到的计算结果和实验数据吻合得较好，因此这一方法可用来对强脉冲电磁场作用下的凝固组织晶粒尺寸进行预测和控制，为优化实验设计提供了简便、实用的方法和手段。
关键字: 凝固组织； 晶粒尺寸； 人工神经网络； BP算法模型
predicting grain size of solidification structure
（1. Department of Mechanical Engineering,
Tsinghua University, Beijing 100084, P.R.China;
2. School of Materials & Metallurgy,
Northeastern University, Shenyang 110006,P.R.China）
Abstract:After analyzing the experimental data of the solidified grain size in Al-alloy under strong pulsed electromagnetic field, a BP algorithmic model of artificial neural network was established. The results show that the simulating results are better in agreement with the experimental results. Therefore, this BP algorithmic model of artificial neural network can be used to control the parameters and predict solidified grain size under applied strong pulsed electromagnetic field. It provides an easy and practical method and means for optimizing experimental design.
Key words: solidification structure; grain size; artificial neural network; BP arithmetic model
