基于模糊加权的转炉炼钢磷分配比计算模型

来源期刊：冶金自动化2010年第3期

论文作者：韩敏 张俊杰 赵耀 肖正宇 彭飞

文章页码：14 - 18

关键词：活度系数； 磷分配比； 模糊C均值； 多元回归

Key words：activity coefficient； phosphorous partition ratio； fuzzy C-means； multiple regression

摘    要：炼钢脱磷过程比较复杂,采用单模型建模一直得不到很好的效果。针对该问题给出渣与钢水间磷分配比的基本关系式,并提出对多个模型采用模糊加权的方法来计算渣与钢水间的磷分配比。该方法采用模糊C均值算法进行分类,将炉况相近的数据进行聚类,分别对各分类结果建立多元回归磷分配比模型,并计算出数据点对应各模型的隶属度,作为模糊权值,进而将各磷分配比模型的计算结果进行模糊加权,以此对渣与钢水间的磷分配比进行估计。采用某钢厂的实际生产数据进行仿真,结果证明本文提出模型的有效性。

Abstract: Focusing on single-model has not got ideal results for complicated dephosphorization process of BOF.For this reason,the basic relationship of slag-metal phosphorous partition ratio is given,and fuzzy weighted method of multiple models is proposed to calculate slag-metal phosphorous partition ratio.First,fuzzy C-means algorithm is used for clustering of data which is in the similar condition of furnace,and a multiple regression phosphorous partition ratio model is established for each classified result.Then,the degree of membership of data point to each model is calculated and used as fuzzy weight.Last,the fuzzy weighted method is used for calculating results of each phosphorous partition ratio model to estimate slag-metal phosphorous partition ratio.The simulation result of the model using practical data from a certain steel plant proves effectiveness of this modeling method.