Classification of silicon content variation trend based on fusion of multilevel features in blast furnace ironmaking

被引：24

作者：

Jiang, Ke ^{[1
]}

Jiang, Zhaohui ^{[1
]}

Xie, Yongfang ^{[1
]}

Chen, Zhipeng ^{[1
]}

Pan, Dong ^{[1
]}

Gui, Weihua ^{[1
]}

机构：

[1] Cent South Univ, Sch Automat, Changsha 410083, Peoples R China

来源：

INFORMATION SCIENCES | 2020年 / 521卷

基金：

中国国家自然科学基金; 美国国家科学基金会;

关键词：

Denoising autoencoder (DAE); Recurrent neural network (RNN); Multilevel features fusion; Variation trend for silicon content; Classification; STOCHASTIC CONFIGURATION NETWORKS; PREDICTION; MODEL;

D O I：

10.1016/j.ins.2020.02.039

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

The silicon content variation trend, which can reflect the quality of molten iron, provides significant information that can assist in ensuring the smooth operation of a blast furnace. This paper proposes a novel dynamic data-driven model for the online classification of the variation trend for the silicon content. Typically, a dynamic model for the silicon content variation trend primarily relies on process data feature extraction. First, a multilevel features fusion algorithm based on mutual information is developed to extract a rich and robust feature representation. Subsequently, the fused multilevel feature vectors and their corresponding trend labels are fed into a recurrent neural network model to capture the process dynamics and classify the variation trend. An experimental simulation and industrial application verified the effectiveness and feasibility of the proposed method. The classification results can provide guidance to ensure that the quality of molten iron is maintained within the desired range in the ironmaking process. (C) 2020 Elsevier Inc. All rights reserved.

引用

页码：32 / 45

页数：14