模糊神经网络在电磁铸造液柱成形控制中的应用

电磁铸造的液柱成形性控制是工艺成败及获得合理的形状铸锭的关键，稳定、合适的液柱高反映了各种工艺参数的良好配合，采用基于模糊理神经网络预测方法，通过对铸造系统电信电信号的踊跃，进行模糊模式识别，预测液高度，结果表明，基于模糊神经网络的控制系统使得过程中液柱高度更加稳定，有利于电磁铸工艺过程的顺利进行，使铸锭的表面质量得到的改善。

Application of fuzzy neural network in controlling the height of liquid column during electromagnetic casting

During electromagnetic casting, the control of suitable and stable height of liquid column is the crucial point to operate the process and to obtain ingots with desirable shape. Stable and suitable height of liquid column implies the excellent match of all process parameters. In this paper, a fuzzy neural network has been used to help control the liquid column by predicting the height of it on line. The results show that the stabilization of the height of liquid column and surface quality of the ingot were remarkably improved by the neural network based control system.