Data-Driven Prediction of Sintering Burn-Through Point Based on Novel Genetic Programming
Data-Driven Prediction of Sintering Burn-Through Point Based on Novel Genetic Programming
复制标题
基于新型遗传编程的数据驱动的烧结烧穿点预测
DOI：
10.1016/s1006-706x(10)60188-4
复制
发表时间：
2010-12-01
影响因子：
2.5
通讯作者：
Ying Yu-qian
中科院分区：
文献类型：
--
作者：
Shang Xiu-qin;Lu Jian-gang;Ying Yu-qian
建立了烧结过程烧穿点的经验动力学模型。根据冷床透气性，采用K-均值聚类进行给料分配。这是由在冷段的表观气速估计。针对每个聚类，提出了一种新的遗传编程（NGP）来构建烧结阶段废气温度和床层压降的经验模型。NGP采用最小二乘法（LSM）和M-估计器，以提高计算能力和抗干扰能力。仿真结果表明了该方法的优越性。
An empirical dynamic model of burn-through point (BTP) in sintering process was developed. The K-means clustering was used to feed distribution according to the cold bed permeability,. Which was estimated by the superficial gas velocity in the cold stage. For each clustering, a novel genetic programming (NGP) was proposed to construct the empirical model of the waste gas temperature and the bed pressure drop in the sintering stage. The least square method (LSM) and M-estimator were adopted in NGP to improve the ability to compute and resist disturbance. Simulation results show the superiority of the proposed method.