首页|基于PSO-BP神经网络双机架炉卷轧机轧制力的预测

基于PSO-BP神经网络双机架炉卷轧机轧制力的预测

扫码查看
为了有效预测双机架炉卷轧机的轧制力,使热轧板带材生产具有很好的可操作性,采用粒子群算法(PSO)优化BP神经网络,建立了往复式双机架炉卷轧机轧制力预测的智能模型.以某钢厂热轧产品Q195实测数据作为试验样本,并将粒子群算法优化的BP神经网络模型和标准BP网络模型分别用于轧制力预测,结果表明PSO-BP神经网络模型在预报精度上明显优于标准BP网络模型,并且PSO-BP神经网络模型预测轧制力的误差率控制在10 %以内.
Prediction of rolling force for two-stand steckel millbased on PSO-BP neural network
To predict the rolling force of the two-stand steckel mill efficiently and make the hot rolled plate and strip easy to produce,the intelligent model of rolling force prediction for the two-stand steckel mill was established with the BP neural network optimized by the particle swarm optimization (PSO) algorithm.The data of the hot rolled product Q195 steel produced at a steel plant were taken as the experimental samples, and the BP neural network model of particle swarm optimization and the standard BP neural network model were used for rolling force prediction.The results showed that the prediction accuracy of the PSO-BP neural network model was better than that of the standard BP network model obviously,and the error rate of the rolling force predicted by the PSO-BP neural network model was controlled within 10 %.

two-stand steckel millparticle swarmBP neural networksrolling force

王智、张果、王剑平、杨俊东、杨奇、尹丽琼

展开 >

昆明理工大学 信息工程与自动化学院,云南 昆明 650500

云南大学 信息学院, 云南 昆明 650091

昆明钢铁控股有限公司 板带厂,云南 昆钢650302

双机架炉卷轧机 粒子群 BP神经网络 轧制力

国家自然科学基金云南省应用基础研究重点项目云南省教育厅重点基金

613640082014FA0292013Z127

2017

钢铁研究
武汉钢铁(集团)公司

钢铁研究

CSTPCD
影响因子:0.314
ISSN:1001-1447
年,卷(期):2017.45(3)
  • 6
  • 7