一种高炉炉温模糊分类判定方法的研究

A Method of Blast Furnace Temperature Identification

提出一种基于粒子群优化(PSO)的K-means模糊聚类方法(FKM),并将该方法应用于攀钢高炉炉温分类判定。与神经网络方法和遗传算法等模型相比,PSO-FKM方法具有快速、识别率高和不易陷入局部最优等优点。结果表明,该方法基本上能够正确划分高炉炉温状况。

Particle swarm optimization (PSO) algorithm was put forward to optimize the center of fuzz K-means (FKM),which was used to classify the temperature of blast furnace.This PSO-FKM method took advantags for the solution of complex problems and profits from the character of fast and efficiency of K-means.Experiments show that it has higher cognition,compared with other methods such as ANN and SW-GA.This method can obtain a good result in practice for 6# blast furnace of Panzhihua Iron and Steel Industry Co.Ltd.