东北大学学报(自然科学版) ›› 2026, Vol. 47 ›› Issue (1): 107-114.DOI: 10.12068/j.issn.1005-3026.2026.20240127

• 材料与冶金 • 上一篇    下一篇

基于混合特征选择的BiGRU-Att烧结矿转鼓指数预测模型

栗潇通, 宋小龙, 范金鑫, 吴朝霞()   

  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:2024-05-29 出版日期:2026-01-15 发布日期:2026-03-17
  • 通讯作者: 吴朝霞
  • 作者简介:栗潇通(2001—),男,河南开封人,东北大学硕士研究生.
  • 基金资助:
    河北省教育厅科学技术研究项目(BJ2021099)

Prediction Model of BiGRU-Att Sinter Drum Index Based on Hybrid Feature Selection

Xiao-tong LI, Xiao-long SONG, Jin-xin FAN, Zhao-xia WU()   

  1. School of Control Engineering,Northeastern University at Qinhuangdao,Qinhuangdao 066004,China.
  • Received:2024-05-29 Online:2026-01-15 Published:2026-03-17
  • Contact: Zhao-xia WU

摘要:

由于烧结过程具有复杂且高维的过程变量及诸多不确定性因素,单一特征选择方法难以有效地选出最佳特征集,从而影响模型的预测准确性.为此,提出一种基于混合特征选择的BiGRU-Att烧结矿转鼓指数预测模型.首先,利用最大信息系数(MIC)从原始特征集中筛选出候选特征.然后,运用基于同时扰动随机逼近的特征选择方法(SPSA-FS)对候选特征集进一步优选.最终,将最佳特征集作为基于注意力机制的双向门控循环单元模型(BiGRU-Att)的输入进行烧结矿转鼓指数预测.与多种模型和单一特征选择方法的比较分析结果表明,本文提出的混合特征选择方法能够选出最佳的特征集,所建模型具有较高的预测精度,为烧结过程提供了可靠的决策支持.

关键词: 烧结矿转鼓指数, 混合特征选择方法, BiGRU, 预测模型, 注意力机制

Abstract:

Because the sintering process has complex and high-dimensional process variables and many uncertain factors, it is difficult for a single feature selection method to effectively select the best feature set, which affects the prediction accuracy of the model. Therefore, a prediction model of attention mechanism-based bidirectional gated recurrent unit model (BiGRU-Att) sinter drum index based on hybrid feature selection was proposed. Firstly, the maximum information coefficient (MIC) was used to select candidate features from the original feature set. Then, the feature selection method based on simultaneous perturbation stochastic approximation (SPSA-FS) was used to further optimize the candidate feature set. Finally, the best feature set was used as the input of BiGRU-Att to predict the sinter drum index. The results of comparative analysis with multiple models and single feature selection methods show that the hybrid feature selection method proposed in this paper can select the best feature set, and the established model has higher prediction accuracy, providing reliable decision-making support for the sintering process.

Key words: sinter drum index, hybrid feature selection method, BiGRU, prediction model, attention mechanism

中图分类号: