基于模糊神经网络的固体粉末自动配料控制系统  

Automatic Batching Control System of Dyestuff Based on Fuzzy Neural Network

作　　者：龚利[1] 王云宽[1] 宋英华[1] 曹志强 

机构地区：[1]中国科学院自动化研究所高技术创新中心,北京100080 [2]渤海船舶重工业有限责任公司机动处,辽宁葫芦岛125004

出　　处：《计量学报》2008年第3期284-288,共5页Acta Metrologica Sinica

基　　金：国家863计划项目(2003AA421110)

摘　　要：在简单介绍固体染料自动配料设备组成的基础上,针对染料自身特性和外部环境变化等不确定因素,设计了基于模糊神经网络便于在线计算的学习算法。将模糊逻辑和神经网络的长处融合在一起,使模糊推理通过神经网络来实现。系统采用VC++编写友好的用户界面程序,用Matlab完成模糊神经网络控制算法的计算任务。实际运行结果表明,该控制算法具有很好的控制效果。After brief introduction of the equipments of automatic batching of dyestuff, an on-line learning algorithm is designsed, which is based on fuzzy neural network in order to deal with the uncertainty of dyestuff characteristic and external disturbance. By combining the merits of fuzzy logic and neural networks, a new method is proposed, in which a fuzzy inference of the model is realized by neural network. As for system application, friendly user interface based on VC ＋ ＋ is adopted and fuzzy neural control algorithm is realized by Matlab programming. The running result shows that the control algorithm has good efficiency.

关 键 词：计量学 固体自动配料 模糊神经网络 参考模型 

分 类 号：TB99[一般工业技术—计量学]