作　　者： ; ;

机构地区： 湖南大学电气与信息工程学院

出　　处： 《湖南大学学报（自然科学版）》 2004年第3期47-51,共5页

摘　　要： 提出了一种在线测量混炼胶粘度的新方法.该方法以模糊建模技术为基础,综合考虑混炼过程各因素对胶料粘度的影响,建立起胶料粘度的在线测量模型.在模糊建模中,采用T S模型描述胶料粘度变化的非线性过程,提出了一种基于相似性判别的模糊聚类算法以自动确定合适的聚类组数目,并用实数编码的遗传算法优化全局参数,从而获得了规则简化的、具有较高精度的模糊模型.根据此方法,设计了测量装置,并进行了现场试验.试验结果表明模糊模型输出与实验室测量值基本一致,平均误差较低且最大误差未超过1门尼.该方法较大地提高了橡胶混炼的生产效率,为粘度最优控制奠定了基础. This paper presents a new approach for on-line measurement of viscosity of rubber mixture. In the approach, fuzzy modeling was adopted to construct the viscosity measurement model. During the fuzzy modeling, T-S model was employed to approximate the non-linearity of viscosity of rubber mixture, an improved clustering algorithm based on similarity assessing was proposed to determine the optimum number of clusters, and a real-coded genetic algorithm was adopted to optimize model parameters. All these techniques made the fuzzy model simple and accurate. Based on it, an instrument was developed and the test on an actual mixer was conducted. The results showed that the proposed approach provided a result similar to laboratory measurement. The error was lower and acceptable. It greatly improved the efficiency of rubber mixing and laid a foundation for the optimal control of viscosity.

关 键 词： 混炼胶粘度 在线测量 模糊建模 遗传算法 橡胶混炼 轮胎加工

领　　域： [化学工程]