基于深度学习的烧结返矿量组合预报模型研究  

Research on combined forecasting model of return fine amount based on deep learning

作　　者：张振 刘小杰 刘颂 李福民 李欣 吕庆 ZHANG Zhen;LIU Xiaojie;LIU Song;LI Fumin;LI Xin;LU Qing(College of Metallurgy and Energy,North China University of Science and Technology,Tangshan 063210,Hebei,China;College of Artificial Intelligence,Tangshan University,Tangshan 063000,Hebei,China)

机构地区：[1]华北理工大学冶金与能源学院,河北唐山063210 [2]唐山学院人工智能学院,河北唐山063000

出　　处：《烧结球团》2023年第1期57-66,共10页Sintering and Pelletizing

基　　金：唐山市科技计划项目(21130233C);河北省教育厅科学技术研究项目(BJ2021099);河北省自然科学基金高端钢铁冶金联合基金资助项目(E2019209314)。

摘　　要：返矿量是影响烧结矿质量和炼铁成本的重要因素。针对该数据难以在短时间内获得且相关预测研究较少的问题,本文提出了一种应用深度学习算法构建的烧结返矿量组合预报模型。该模型首先将烧结实际生产流程大数据与数据预处理技术相结合,建立模型基础数据集;然后将烧结流程中存在的滞后性与时域神经网络相结合,实现模型的提前预报功能;同时将皮尔逊相关性分析和PCA技术制定的烧结配料规则与深度森林相结合,实现模型的实时监测功能。预测结果分析表明:该模型整体误差范围(返矿量在15 t/h内)命中率能够达到90%以上,并展示出良好的提前预报和实时监测效果,能够达到预测返矿趋势与数量的目标。As an important factor affecting the quality of sinter and ironmaking cost,a combined forecasting model of return fine amount constructed by deep learning algorithm is proposed to solve the problem that its data is difficult to obtain in a short time based on few related prediction studies.Firstly,the big data of the actual sintering production process is combined with the data preprocessing technology to establish the basic data set of the model.Then,the hysteretic nature in the sintering process is combined with the time-domain neural network to realize the early prediction function of the model.At the same time,the Pearson correlation analysis and the sintering accessory rules formulated by PCA technology are combined with deep forest to realize the real-time monitoring function of the model.The analysis of prediction results shows that the overall eror range of the model(return fine amount within 15/h)can reach more than 90%,and show good forecast in advance and real-time monitor effect,which can achieve the goal of predicting the trend and amount of return fine.

关 键 词：烧结返矿 滞后性 配料规则 深度学习 提前预报 实时监测 

分 类 号：TF046.4[冶金工程—冶金物理化学] TP183[自动化与计算机技术—控制理论与控制工程]