Discrete Wavelet Transfer Based BPNN for Calculating Carbon Efficiency of Sintering Process

Author(s):  
Xiaoxia Chen ◽  
◽  
Jinhua She ◽  
Xin Chen ◽  
Min Wu ◽  
...  

Iron ore sintering process is the secondary most energy consuming procedure in steel making industry. In this study, a discrete wavelet transfer based back-propagation neural network (BPNN) model is built to predict the carbon efficiency of an iron ore sintering process. The raw-material variables and manipulated variables are chosen to be the inputs of the predictive model. First, the input variables are decomposed into 5 components. Then, BPNN models of each component are built. Finally, the prediction results are obtained by adding the output from each wave series. Actual run data are collected to verify the validity of the predictive model. The results show the validity of the proposed method with a MSE of 0.7708, a MAPE of 0.0125, and a <span class="bold">R</span>2 of 0.7016.

2021 ◽  
Vol 106 ◽  
pp. 44-53
Author(s):  
Kailong Zhou ◽  
Xin Chen ◽  
Min Wu ◽  
Yosuke Nakanishi ◽  
Weihua Cao ◽  
...  

2021 ◽  
Vol 1045 ◽  
pp. 127-140
Author(s):  
Lina Kieush ◽  
Andrii Koveria ◽  
Maksym Boyko ◽  
Andrii Hrubyak ◽  
Artem Sova ◽  
...  

Iron ore sintering is a predominant process for fine iron ore and its concentrate to be applied in the blast furnace process. However, sintering produces a negative impact on the environment. One of the effective ways to reduce greenhouse gas emissions from iron ore sintering is to use CO2-neutral biomaterials for the fuel needs of this technology. Walnut shells (WNS) are a promising raw material for such fuel substitute. Herein, the effect of the raw and the pyrolyzed WNS with a constant fineness of 3-0 mm on the sintering process and the sinter properties were studied. The proportion of WNS in the fuel composition was set to 25 wt.%. It has been established that the use of WNS pyrolyzed up to 873 K is optimal. Additionally, the difference in the reactivity of WNS and coke breeze has provoked the studies on the influence of the pyrolyzed WNS size on the sintering process. WNS size was set to 1-0, 3-0, 5-0, and 7-0 mm. It has been found that the most optimal both for the iron ore sintering process and the sinter quality is the use of WNS with a particle size of 3-0 mm, subjected to preliminary pyrolysis up to 873 K.


Sign in / Sign up

Export Citation Format

Share Document