基于GRNN算法的铜阳极炉精炼还原终点预报模型  

Prediction Model for Copper Anode Furnace Refining Reduction Endpoint Based on GRNN Algorithm

作　　者：舒波 王恩志 徐建新[2,3] 陈习堂 任军祥 俞建明 高荣 王华[2,3] SHU Bo;WANG Enzhi;XU Jianxin;CHEN Xitang;REN Junxiang;YU Jianming;GAO Rong;WANG Hua(Chuxiong Dianzhong Nonferrous Metals Co.,Ltd.,Chuxiong 675000,Yunnan,China;State Key Laboratory of Complex Nonferrous Metal Resources Clean Utilization,Kunming University of Science and Technology,Kunming 650093,China;Faculty of Metallurgical and Energy Engineering,Kunming University of Science and Technology,Kunming 650093,China)

机构地区：[1]楚雄滇中有色金属有限责任公司,云南楚雄675000 [2]昆明理工大学复杂有色金属资源清洁利用国家重点实验室,昆明650093 [3]昆明理工大学冶金与能源工程学院,昆明650093

出　　处：《有色金属（冶炼部分）》2024年第12期35-42,49,共9页Nonferrous Metals（Extractive Metallurgy)

基　　金：国家自然科学基金资助项目(52166004);国家重点研发计划项目(2022YFC3902000);云南省重大科技专项(202202AG050007,202202AG050002)。

摘　　要：针对阳极炉炼铜还原期终点判断依赖人工判断的局限,利用机器学习技术实现智能判断。通过图像去模糊处理优化图像特征,对图像进行灰度差分矩阵运算,将矩阵中提取出的特征值作为神经网络的输入,构建了一种新的铜阳极炉精炼还原期终点判断模型。试验结果显示,在真实生产环境下,采用GRNN算法对还原终点进行预测,有助于消除铜阳极炉精炼过程中不同指标之间的相关性,减少了数据冗余和系统误差,使预测精度提高至96.54%。相较于传统方法,这种新的判断模型有效提高了阳极炉炼铜还原期终点判断的准确性。Address to limitations of relying on manual judgment for determining the endpoint of reduction period in copper smelting in anode furnaces,machine learning techniques was utilized to achieve intelligent judgment.Image feature optimization was performed through image deblurring,followed by grayscale difference matrix operation on the images.The extracted feature values from the matrix were used as inputs to a neural network,a novel model for determining the endpoint of the reduction period in copper smelting in anode furnaces was established.Experimental results demonstrate that employing the GRNN algorithm for predicting the reduction endpoint effectively eliminates correlations among different indicators during copper smelting,thereby reducing data redundancy and system errors,leading to an improved prediction accuracy of 96.54% in real production environments.Compared to traditional methods,this new judgment model significantly enhances the accuracy of determining the endpoint of the reduction period in copper smelting in anode furnaces.

关 键 词：阳极炉炼铜 还原期 GRNN算法 图像处理 终点判断 

分 类 号：TF811[冶金工程—有色金属冶金]