东北大学学报(自然科学版) ›› 2025, Vol. 46 ›› Issue (6): 56-65.DOI: 10.12068/j.issn.1005-3026.2025.20240011

• 材料与冶金 • 上一篇    下一篇

基于特征优选的GA-BiLSTM烧结矿中FeO含量预测模型

李中正, 吴朝霞, 王金杨, 康增鑫   

  1. 东北大学秦皇岛分校 控制工程学院,河北 秦皇岛 066004
  • 收稿日期:2024-01-11 出版日期:2025-06-15 发布日期:2025-09-01
  • 作者简介:李中正(1999—),男,山西吕梁人,东北大学硕士研究生
    吴朝霞(1969—),女,河北秦皇岛人,东北大学教授,硕士生导师.
  • 基金资助:
    河北省教育厅科学技术研究项目(BJ2021099)

FeO Content Prediction Model in Sinter Based on GA-BiLSTM with Feature Optimization

Zhong-zheng LI, Zhao-xia WU, Jin-yang WANG, Zeng-xin KANG   

  1. School of Control Engineering,Northeastern University at Qinhuangdao,Qinhuangdao 066004,China. Corresponding author: WU Zhao-xia,E-mail: ysuwzx@126. com
  • Received:2024-01-11 Online:2025-06-15 Published:2025-09-01

摘要:

针对传统烧结矿质量预测模型特征选择方法单一、脱离工艺机理等问题,导致模型预测精度不高且缺乏解释性,提出了一种基于特征优选的遗传算法优化双向长短期记忆网络(GA-BiLSTM)预测模型.首先通过多种特征选择方法并且结合烧结工艺机理筛选出最佳特征集,然后利用GA优化BiLSTM,最后将最佳特征集作为GA-BiLSTM模型的输入来预测烧结矿中FeO含量.将特征优选的GA-BiLSTM模型与其他模型进行对比分析.结果表明,所建立的模型预测误差较低,并且烧结矿中FeO质量分数在允许误差±0.5%的范围内准确度为94%,表现了较高的预测精度,为提高烧结矿质量提供了新的指导方向.

关键词: 烧结矿, 特征优选, FeO含量, 预测模型, 大数据

Abstract:

In order to solve the problems of traditional sinter quality prediction model, such as using single feature selection method and having no background of process mechanism, which results in low model prediction accuracy and lack of interpretability, a GA-BiLSTM prediction model with feature optimization is proposed. First, the optimal feature set is selected through various feature selection methods and combined with the sintering process mechanism, then GA is used to optimize BiLSTM, and finally the optimal feature set is used as the input of the GA-BiLSTM model to predict the FeO content in sinter. The GA-BiLSTM model with feature optimization was compared with other models. The results show that the prediction error of the established model is low, and the prediction accuracy for FeO mass fraction in sinter is as high as 94% within the allowable error range of ±0.5%, which may provide a new guiding direction for improving the quality of sinter.

Key words: sinter, feature optimization, FeO content, prediction model, big data

中图分类号: