基于火焰及烟气特征深融合的转炉吹炼终点判断  

Endpoint Determination of Converter Blowing Based on Deep Fusion of Flame and Flue Gas Characteristics

作　　者：张红哲 张冰洁 郭廷谦 ZHANG Hongzhe;ZHANG Bingjie;GUO Tingqian(China Enfei Engineering Technology Co.,Ltd.,Beijing 100038,China)

机构地区：[1]中国恩菲工程技术有限公司,北京100038

出　　处：《铜业工程》2023年第6期175-180,共6页Copper Engineering

基　　金：北京市自然科学基金项目(8234060)资助。

摘　　要：转炉吹炼的终点判断是火法炼铜最重要的步骤之一,该步骤一般由操作人员凭经验或仪器对固定监测因素进行判断,但受制于个人操作经验、仪器测量精度、物料品位等诸多因素的差异,判断精度无法得到保证。为提高转炉吹炼终点判断的精准度,本文设计了一套智能化预测系统,首先基于显著性分析法对传统火焰、烟气浓度进行特征分析与显著性指标设计,然后利用残差网络构建终点预测模型,通过融合火焰、最后连续时间的PbS/PbO浓度比与SO_(2)浓度3个显著特征,实现了造渣期终点和造铜期终点的预测。实验结果证明了该融合特征的性能,造渣期终点时间预测误差均值为2.12%,造铜期终点时间预测误差均值为2.06%,双期预测准确率达到93.66%。这种高精度的判断主要归因于基于传统特征的显著性指标设计,所选用的火焰及烟气特征能在高维度对终点判断进行准确的预测,同时引入大量历史数据所训练的模型能够对预测过程进行显著量化。The determination of the endpoint of converter blowing is crucial in the entire pyrometallurgical process.This process is gen‐erally judged by operators based on experience or fixed factors monitored by instruments.However,due to personal operational differ‐ences and other factors,the accuracy of blowing cannot be fundamentally guaranteed.This paper designed an intelligent prediction sys‐tem based on feature significance analysis,and constructed an endpoint prediction model using Resnet network.It integrated three dif‐ferent dimensional features of flame,continuous time PbS/PbO concentration ratio,and SO_(2) concentration to achieve endpoint predic‐tion during slag and copper making periods.The experimental results showed that the average prediction error during the slag making period was 2.12%,the average prediction error during the copper making period was 2.06%,and the accuracy of endpoint prediction reached 93.66%.The high precision characteristics were mainly attributed to the significance index design based on traditional charac‐teristics,the selected flame and smoke characteristics could accurately predict the end point judgment in a high dimension,and the model trained by introducing a large number of historical data could significantly quantify the prediction process.

关 键 词：转炉吹炼 终点判断 火法炼铜 人工智能 特征融合 

分 类 号：TF813[冶金工程—有色金属冶金] TF804.2