Simulation of Coke Quality Indicators Using Artificial Neural Network


The article shows the application of a neural network for modeling coke quality indicators Coke Reactivity Index (CRI) and Coke Strength after Reaction (CSR). Two optimization methods were used to train the neural network. The influence of the number of neurons on the simulation results was studied. The difference between experimental and calculated data on average does not exceed 2 %. The conclusion is made about the prospects of using a neural network to predict the values of CRI and CSR of coke.

Keywords: artificial neural network, coke, coke reactivity index, coke strength after reaction

[1] Ulanovskii, M. L. Parameters for optimization of coke quality (CRI and CSR)//Coke and Chemistry. 2009. T. 52. No. 1. pp. 11-15.

[2] Doroganov V. S., Pimonov A. G. Methods of statistical analysis and neural network technologies for predicting quality indicators of metallurgical coke / / Bulletin of Kemerovo state University. Technical science. 2015. pp. 123-129.

[3] Neural networks in applied Economics: studies. manual / E. A. Trofimova, Vol.D. Mazurov, D. V. Gilev under the General editorship of E. A. Trofimova // Ural Federal University, Ekaterinburg. 2017.

[4] Vasilyeva, E. V., Doroganov, V. S., Piletskaya, A. B. Results of estimation of neural network mathematical model of output of chemical products of coking. Coke and chemistry. - 2019. - No. 2. pp. 31-40.

[5] Wasserman F. Neurocomputer technique: Theory and practice. Moscow: Mir, 1992.

[6] Abbasov, M. E. Methods of optimization: a tutorial. SPb.: VVM publishing house, 2014.