摘要
铜冶转炉吹炼是一个复杂的过程,具有多变量、非线性、强耦合、大惯性和不确定性,机理复杂、物料变化范围大、影响因素多,给吹炼终点预报带来了极大困难。目前国内外铜锍吹炼过程终点判断仍以人工经验判断为主,此方式不仅增加工作强度,且吹炼终点判断严重依赖经验和工作态度,易导致欠吹或过吹等现象,影响正常生产,造成铜损失,严重时甚至发生喷炉事故。为此,利用转炉吹炼的终点与炉内烟气SO_(2)、O_(2)含量存在精确对应关系,结合人工经验和转炉工艺原理,在线对造铜期终点实现准确判断。利用SO_(2)浓度与烟气温度、送风量、送风压力、富氧量、内在因素(原料含硫比、原料重量、原料质量等)的关系实现动态补偿,采用Elman递归神经网络模型实现过程自调整、自学习,使判断准确率达到98%以上,对指导实际生产具有重大意义。
The copper smelting converter blowing is a complex process with multi-variable, nonlinear, strong coupling, great inertia and uncertainty, complex mechanism, a wide range of material changes and many influencing factors, which brings great difficulty to the prediction of blowing endpoint. At present, the end-point judgment of copper-matte converting process at home and abroad is still dominated by manual experience judgment, which not only increases the working intensity, but also makes the end-point judgment of copper-matte converting heavily dependent on experience and working attitude, which may easily lead to under-blowing or over-blowing, affect the normal production, and cause copper loss and even furnace injection accidents in a serious accident. Based on the accurate correspondence between the end point of converter blowing and the content of SO_(2) and O_(2) in flue gas, combined with artificial experience and converter process principle, the end of copper smelting could realize the accurate judgment online. The relationship between the SO_(2) concentration and flue gas temperature, air supply volume, air supply pressure, oxygen-enriched volume, internal factors(sulfur ratio of raw material, the weight of raw material, quality of raw material, etc.) was used to realize dynamic compensation, Elman recursive neural network model was used to realize self-adjustment and self-learning, so that the accuracy of judgment was more than 98%, which was of great significance to guide actual production.
作者
胡金宝
余向阳
HU Jin-bao;YU Xiang-yang(Research and Development Department,LIWODE Technology Co.,Ltd.,Nanchang 330000,Jiangxi,China;School of Physics,State Key Laboratory of Optoelectronic Materials and Technologies,Sun Yat-sen University,Guangzhou 510275,Guangdong,China)
出处
《中国冶金》
CAS
北大核心
2021年第4期110-117,共8页
China Metallurgy
关键词
铜冶炼
转炉工艺
吹炼终点判断
动态补偿
Elman递归神经网络
copper smelting
converter process
blowing end-point judgment
dynamic compensation
Elman recursive neural network