基于GA-BP神经网络的LF精炼过程合金加入量预测模型  

Prediction model of alloy addition amount in LF refining process based on GA-BP neural network

作　　者：胡倩倩 韩啸 刘吉辉[1,2] 何志军 杨鑫[1,2] 施树蓉 HU Qianqian;HAN Xiao;LIU Jihui;HE Zhijun;YANG Xin;SHI Shurong(School of Materials and Metallurgy,University of Science and Technology Liaoning,Anshan 114051,China;Key Laboratory of Green Low-Carbon and Intelligent Metallurgy Liaoning Province,Anshan 114051,China)

机构地区：[1]辽宁科技大学材料与冶金学院,辽宁鞍山114051 [2]辽宁省绿色低碳与智能冶金重点实验室,辽宁鞍山114051

出　　处：《冶金自动化》2025年第1期32-41,共10页Metallurgical Industry Automation

基　　金：国家自然科学基金青年科学基金项目(52104331)。

摘　　要：为了实现更加精准地计算合金加入量,采用了基于遗传算法(genetic algorithm,GA)优化BP神经网络的综合算法。在BP神经网络训练过程中,将精炼开始钢水成分作为BP神经网络模型的输入参数,再利用GA算法的适应度函数对BP神经网络的权重和阈值进行优化和调整,预测LF的精炼终点钢液成分,通过对比BP神经网络算法和GA-BP神经网络算法的预测结果,发现GA-BP算法的平均绝对误差(mean absolute error,MAE)和均方误差(mean square error,MSE)更小,预测结果更准确且与实际钢液成分基本相符,表明此模型可用于生产。基于该GA-BP神经网络模型,根据LF精炼开始钢水成分和控制成分要求,确定合金加入量。通过在某钢厂140 t钢包LF精炼系统部署预测模型并跟踪188炉数据,合金的实际加入量与模型预测加入量的差值在±30 kg之内的炉次中,高锰合金的预测准确率为91.3%,高铬合金的预测准确率为90.4%,硅铁合金的预测准确率为90.2%,增碳剂的预测准确率为91%,可以指导实际精炼过程合金加入量的确定。In order to achieve more accurate calculation of alloy addition amount,a comprehensive algorithm based on genetic algorithm(GA)optimization for BP neural network was adopted.During the training process of the BP neural network,the refining starting composition of the molten steel was used as input parameters for the BP neural network model.Then,the fitness function of the GA was used to optimize and adjust the weight and threshold of BP neural network,predicting the refining endpoint steel composition of the LF furnace.By comparing the prediction results of BP neural net-work algorithm and GA-BP neural network algorithm,it was found that the GA-BP algorithm has smaller mean absolute error(MAE)and mean square error(MSE),and the prediction results are more accurate and basically consistent with the actual steel composition,indicating that this model can be used in production.Based on the GA-BP neural network model,the alloy addition amount was determined according to the composition of the molten steel at the beginning of LF refining and control composition requirements.After deploying a predictive model in the 140 ton ladle LF refining system of a steel plant and tracking 188 furnace data,the difference between the actual amount of alloy added and the predicted amount was within±30 kg,then the prediction accuracy of high manganese alloy was 91.3%,high chromium alloy was 90.4%,ferrosilicon alloy was 90.2%,and the prediction accuracy of carburant was 91%in furnaces,from which can guide the determination of alloy addition amount in the actual refining process.

关 键 词：LF精炼 GA优化 BP神经网络 合金微调 预测模型 

分 类 号：TF769[冶金工程—钢铁冶金] TP18[自动化与计算机技术—控制理论与控制工程]