Linear Priors Mined and Integrated for Transparency of Blast Furnace Black-Box SVM Model

Although its theoretical foundation is well understood by researchers, a blast furnace is like a black box in practice because its behavior is not always as expected. It is a complex reactor where multiple reactions and multiple phases are involved, and the operation heavily relies on the operators' experience. In order to help the operators gain insights into the operation, the authors do not use traditional metallurgy models but instead use machine learning methods to analyze the data associated with the operation performance of a blast furnace. They analyze the variables that are connected to the economic and technical performance indices by combining domain knowledge and results obtained from two fundamental feature selection methods, and they propose a classification algorithm to train classifiers for the prediction of the operation performance. The findings could assist the operators in reviewing as well as improving the guideline for the operation.

Download Full-text

Optimal Design of Heating System for Annular Furnace

Advanced Materials Research ◽

10.4028/www.scientific.net/amr.402.403 ◽

2011 ◽

Vol 402 ◽

pp. 403-406 ◽

Cited By ~ 2

Author(s):

Yin Mei Yuan ◽

Chao Xiang Li

Keyword(s):

Temperature Distribution ◽

Optimal Design ◽

Heat Load ◽

Heating System ◽

Black Box ◽

Heating Process ◽

Temperature Uniformity ◽

Furnace Black ◽

Annular Furnace

According to the present problems of annular furnace, using the furnace black box, the temperature distribution of billet in the heating process is measured. Based on the results, the existing heating system is found deficient. Therefore, make improvements to the heating system, and mainly increase the heat load. Heating process tracking test is carried out again. Achieve the desired outcome, such as temperature uniformity, better quality, shorten time,etc.

Download Full-text

Efficient Utilization of Active Carbon in a Blast Furnace through a Black-Box Model-Based Optimizing Control Scheme

IFAC-PapersOnLine ◽

10.1016/j.ifacol.2021.08.230 ◽

2021 ◽

Vol 54 (3) ◽

pp. 128-133

Author(s):

Pourya Azadi ◽

Rainer Klock ◽

Sebastian Engell

Keyword(s):

Blast Furnace ◽

Active Carbon ◽

Black Box ◽

Box Model ◽

Efficient Utilization ◽

Model Based ◽

Control Scheme ◽

Optimizing Control

Download Full-text

Experimental Study and Prediction Model of the Flexural Strength of concrete Containing Fly Ash and Ground Granulated Blast-Furnace Slag

Advances in Civil Engineering ◽

10.1155/2021/8773664 ◽

2021 ◽

Vol 2021 ◽

pp. 1-16

Author(s):

Hua Zhang ◽

Qing-Fu Li ◽

Hua-De Zhou ◽

Zong-Ming Song

Keyword(s):

Blast Furnace ◽

Fly Ash ◽

Flexural Strength ◽

Prediction Model ◽

Blast Furnace Slag ◽

Early Stage ◽

Support Vector ◽

Granulated Blast Furnace Slag ◽

Svm Model ◽

Furnace Slag

Orthogonal experiments were performed to study the flexural strength of an eco-friendly concrete containing fly ash (FA) and ground granulated blast-furnace slag (GGBFS). The effects of different test parameters, such as water-binder ratio (W/B), FA content, GGBFS content, sand ratio, gravel gradation, and curing time, on the flexural strength of the concrete were analyzed. The significance level of each influencing factor and the optimal mixing proportion of the concrete were determined by range analysis and hierarchy analysis. It was found that the W/B ratio had the greatest influence on the flexural strength of the concrete. The flexural strength of the concrete decreased gradually with the increase of W/B. The GGBFS content and the sand ratio had a greater influence in the early stage of concrete curing. The middle and later stages of concrete curing were mainly affected by gravel gradation and the FA content. A flexural strength prediction model of the concrete was developed based on a backpropagation neural network (BPNN) and a support vector machine (SVM) model. It was noticed that the BPNN and SVM models both had higher accuracy than the empirical equation, and the BPNN model was more accurate than the SVM model.

Download Full-text