Predicting coal ash fusion temperature based on its chemical composition using ACO-BP neural network

2007 ◽  
Vol 454 (1) ◽  
pp. 64-68 ◽  
Author(s):  
Y.P. Liu ◽  
M.G. Wu ◽  
J.X. Qian
Keyword(s):  
Neural Network ◽  
Chemical Composition ◽  
Bp Neural Network ◽  
Coal Ash ◽  
Fusion Temperature ◽  
Ash Fusion Temperature

scholarly journals Modeling and Prediction of Coal Ash Fusion Temperature based on BP Neural Network

2016 ◽  
Vol 40 ◽  
pp. 05010 ◽  
Author(s):  
Suzhen Miao ◽  
Qingyin Jiang ◽  
Hua Zhou ◽  
Jia Shi ◽  
Zhikai Cao
Keyword(s):  
Neural Network ◽  
Bp Neural Network ◽  
Coal Ash ◽  
Fusion Temperature ◽  
Modeling And Prediction ◽  
Ash Fusion Temperature

An Empirical Study of the Relation of Chemical Properties to Ash Fusion Temperatures

1975 ◽  
Vol 97 (3) ◽  
pp. 395-403 ◽  
Author(s):  
E. C. Winegartner ◽  
B. T. Rhodes
Keyword(s):  
Regression Analysis ◽  
Thermal Properties ◽  
Chemical Composition ◽  
Empirical Study ◽  
Chemical Properties ◽  
Coal Ash ◽  
Temperature Measurements ◽  
Standard Errors ◽  
Fusion Temperature ◽  
Ash Fusion Temperature

Regression analysis is used to develop equations for calculating fusion temperatures of coal ash from chemical composition, based on 1250 analyses of ash from both eastern and western coal. Standard errors for the equations are generally less than 50°F (27°C), which is the analytical tolerance of the ash fusion temperature measurements. Equations are given for eastern, western, and combined eastern and western coals. These equations: (1) provide a technique for calculating ash fusion temperatures from the chemical composition of the ash; (2) provide a method for calculating the ash fusion properties of coal blends; and (3) provide an improved understanding of the effect, significance, and interactions of ash elements with respect to the thermal properties of coal ash.

Using BP Neural Network to Predict the Sinter Comprehensive Performance: TFe and Fuel Consumption

2013 ◽  
Vol 771 ◽  
pp. 213-216
Author(s):  
Wei Chen ◽  
Bao Xiang Wang ◽  
Ying Chen ◽  
Hui Juan Zhang ◽  
Xing Li
Keyword(s):  
Neural Network ◽  
Chemical Composition ◽  
Fuel Consumption ◽  
Bp Neural Network ◽  
Raw Material ◽  
High Rate ◽  
Production Data ◽  
Practical Application ◽  
High Quality ◽  
Comprehensive Performance

The principal objective of blast furnace is to produce high quality molten iron at a high rate with a low consumption. It is very important to control sinter chemical composition and comprehensive performance. This is because the sinter is the main raw material for ironmaking. In this paper, a predictive system for sinter chemical composition TFe and the solid fuel consumption was established based on BP neural network, which was trained by actual production data. The MATLAB m file editor was used to write code directly in this paper. Practical application shows the applications of the system not only can reduce the work difficulty of technical personnel, but also can improve the hit ratio of production index and the productivity.

A Thermodynamically Based Model for Ash Fusion Temperature

1987 ◽  
Vol 109 (3) ◽  
pp. 124-128 ◽  
Author(s):  
R. R. Rhinehart ◽  
A. A. Attar
Keyword(s):  
Standard Error ◽  
Coal Ash ◽  
Model Parameters ◽  
Fusion Temperature ◽  
Ash Composition ◽  
Parameter Correlation ◽  
Ash Fusion Temperature ◽  
Wide Range

This paper describes a thermodynamically based correlation between coal ash fusion temperatures and ash composition. A wide range of data from the literature was used to obtain the values of model parameters. A seven-parameter correlation is proposed which permits predicting the ash fusion temperature with a standard error ± 65°C or better.

Effect of High-Efficiency Flux on the Melting Characteristics of Coal Ash

2013 ◽  
Vol 295-298 ◽  
pp. 3094-3097 ◽  
Author(s):  
Han Xu Li ◽  
Zi Li Zhang ◽  
Yong Xin Tang
Keyword(s):  
Melting Temperature ◽  
Coal Gasification ◽  
High Efficiency ◽  
Coal Ash ◽  
Fusion Temperature ◽  
Gasification Process ◽  
Ash Fusion Temperature ◽  
Melting Characteristics ◽  
Temperature Detector ◽  
Ash Melting

High-efficiency flux was developed to lower the ash fusion temperature of coal LQ and reduce the addition content in coal gasification process. The effect of high-efficiency flux on the coal ash melting temperature and mineral transformation were studied by ash fusion temperature detector and XRD (X-ray diffractometer) respectively in reducing atmosphere. Compared with limestone flux, the high-efficiency flux can decrease the coal ash melting temperature effectively with half addition content. The ash flow temperature (FT) of coal LQ can be lowered to less than 1350°C with the addition of 3% high-efficiency flux ,while limestone flux need to add more than 8% to reach to this temperature. With the high-efficiency flux added, cordierite, anorthite and Mg-Fe-Al oxide were formed at high temperature, which is the main reason to sharply decrease the ash fusion temperature.

Using BP Neural Network to Predict the Sinter Comprehensive Performance: FeO and Sinter Yield

2013 ◽  
Vol 771 ◽  
pp. 209-212
Author(s):  
Wei Chen ◽  
Bao Xiang Wang ◽  
Ying Chen ◽  
Hui Juan Zhang ◽  
Xing Li
Keyword(s):  
Neural Network ◽  
Chemical Composition ◽  
Bp Neural Network ◽  
High Accuracy ◽  
Raw Material ◽  
Production Data ◽  
Prediction System ◽  
Accuracy Rate ◽  
Actual Production ◽  
Comprehensive Performance

Sinter is the main raw material for ironmaking. It is very important to control sinter chemical composition and comprehensive performance. In this paper, a predictive system for sinter chemical composition FeO and the sinter yield was established based on BP neural network, which was trained by actual production data. The MATLAB m file editor was used to write code directly in this paper.The application results show that the prediction system has high accuracy rate, stability and reliability, the sintering productivity was improved effectively.

Sign in / Sign up

Export Citation Format

Share Document