摘要
提出了一种在线测量球团密度的新方法.该方法以模糊技术为基础,综合考虑制团过程各因素对球团密度的影响,建立起球团密度的软测量模型.在软测量模型中,采用T-S模糊模型描述球团密度变化的非线性过程,并提出了一种改进的模型辨识算法,利用减法聚类法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,从而获得了结构简单、具有较高精度的模糊软测量模型.根据此方法,设计了测量装置,并进行了现场试验,试验结果表明软测量模型输出与实验室测量值基本一致,平均误差较低.该方法较大地提高了制团的生产效率,为球团密度的最优控制奠定了基础.
A new on-line measurement approach for pellet density is presented which adopted fuzzy modeling to construct a simple accurate soft measuring fuzzy model for pellet density. During the modeling, T-S fuzzy model is employed to approximate the non-linearity of pellet density, an improved model identifying method is put forward, subtractive-clustering algorithm is used to determine the optimum number of clusters, and a real coded genetic algorithm is adopted to optimize model parameters. A measuring device is designed and the actual experimental results showed that the proposed approach provided a result similar to that of the laboratory measurement and had low average error. It greatly improved the productive efficiency of pelletizing and laid a foundation for the optimal control of pellet density.
出处
《测试技术学报》
2006年第1期27-31,共5页
Journal of Test and Measurement Technology
关键词
球团密度
软测量
模糊建模
遗传算法
误差分析
pellet density
soft sensing system
fuzzy modeling
genetic algorithm
error analysis
