基于RBF网络的混炼胶质量软测量技术实现  

Realization of RBF Neural Network Based Soft-Measuring Technology of Mix Rubber Quality

作　　者：杨帆[1] 张玉杰[1] 张彩丽[2] 

机构地区：[1]陕西科技大学电信学院,陕西西安710021 [2]陕西科技大学机电学院,陕西西安710021

出　　处：《微计算机信息》2008年第24期224-226,共3页Control & Automation

基　　金：陕西省工业攻关项目(2006K05-G18);陕西科技大学自然科学基金项目(ZX05-37)

摘　　要：针对混炼胶生产过程中影响产品质量各个因素之间存在的复杂未知映射关系,精确数学模型难以建立的问题,提出了基于RBF神经网络的混炼胶质量在线预测模型,并和多元线性回归法测量结果进行了比较。实验结果表明,基于RBF神经网络的混炼胶质量的软测量模型具有很高的测量精度,可以在实际生产中发挥有效作用。Since complex mapping relation existed in multi-factors which produce an effect on quality of mix rubber product, and it is difficult to build accurate mathematics models by traditional methods, A RBF neural network based soft-sensing model for mix rubber quality online detecting is presented in this paper, the measurement result of RBF model and Multiple Linear Regression model is compared. The experimental results show clearly that RBF neural network based soft-sensing model has high measurement precision, and can play efficiency effect in practice producing.

关 键 词：混炼胶 软测量 神经网络RBF 

分 类 号：TP274[自动化与计算机技术—检测技术与自动化装置]