节点文献
人工神经网络和数学模型在热连轧机组轧制力预报中的综合应用
APPLICATION OF NEURAL NETWORKS IN COMBINATIONWITH MATHEMATICAL MODELS TO PREDICTION OF ROLLING LOAD OF HOT STRIP ROLLING MILL
【摘要】 针对传统轧制力模型的固有缺陷,为了提高精轧机组轧制力预设定精度,提出一种将人工神经网络和数学模型相结合的新方法,用于热连轧精轧机组轧制力的预设定。离线仿真表明,采用本文所述的方法,预报精度优于传统方法。预报结果的相对误差限制在±5%以内。
【Abstract】 In view of intrinsic imperfection of traditional models of rolling load, in order to improve the prediction precision of rolling load, a new method combining artificial neural networks with mathematical models to predict rolling load is put forward. Offline simulation indicates that the predicted results are more accurate than that estimated with traditional models. The relative error is within 5 %
【关键词】 人工神经网络;
BP算法;
数学模型;
轧制力预报;
【Key words】 artificial neural networks; BP algorithm; mathematical models; prediction of rolling load;
【Key words】 artificial neural networks; BP algorithm; mathematical models; prediction of rolling load;
- 【文献出处】 钢铁 ,IRON AND STEEL , 编辑部邮箱 ,1999年03期
- 【分类号】TG331,TG331
- 【被引频次】75
- 【下载频次】419