摘要
烧结工序是钢铁冶金生产中的一个重要工序,在实际生产条件下,研究烧结各主要原料投入与烧结能耗的关系问题具有非常重要的意义。在大量实际生产数据的基础上,选取一部分典型数据,利用带动量项、具有自适应学习速率的BP神经网络建立了烧结固体能耗及其性能指标的预测模型,结果验证了该方法的有效性。
Sintering process is one of the most important processes in iron-and-steel making.It is great significance to research the relationship of the main raw materials＇ consumption and energy consumption in sintering process under some particular conditions for production.A sintering predictive model of the solid fuel consumption and sinter performance was developed by the BP neural network algorithm with appending momentum and adaptive variable learning rate.It was derived on the basis of typical data of actual runs.
出处
《机械工程师》
2012年第2期45-47,共3页
Mechanical Engineer
基金
安徽省钢铁产业技术创新规划研究资助项目(09020203014)
上海市重点学科建设资助项目(B004)
关键词
烧结
固体能耗
性能指标
神经网络
sinter
consumption of solid fuel
sinter performance
neural network
