Prediction Model of Coke Quality Based on DE-BP Neural Network

Authors

Wenhua Tao, School of Information and Control Engineering, Liaoning Shihua University, Fushun 113001, China;
Zhengbo Yuan, School of Information and Control Engineering, Liaoning Shihua University, Fushun 113001, China;

Abstract

Abstract: The quality of coke has a great effect on the furnace process. In order to solve the problem of large amount of calculation and inspection of coke quality prediction linear method, the coke quality prediction model based on DE-BP neural network is established on the basis of analyzing the factors affecting coke quality, which uses principal component analysis method to determine the parameters of the input vector with the coal and coke ash quality indicators A_d, sulfur S_td, crushing strength M₄₀, abrasion resistance M₁₀ as the output vector prediction. The result of simulation shows that the relative errors of real and estimated values of the indicators are below 4%, overcoming the low prediction precision of BP neural network and the shortcoming of easily trapped in local minimum. It can meet the requirements of production process and has a certain value for coke production.

Recommended Citation

Tao, Wenhua and Yuan, Zhengbo (2019) "Prediction Model of Coke Quality Based on DE-BP Neural Network," Journal of System Simulation: Vol. 30: Iss. 5, Article 4.
DOI: 10.16182/j.issn1004731x.joss.201805004
Available at: https://dc-china-simulation.researchcommons.org/journal/vol30/iss5/4

First Page

1650

Revised Date

2016-08-03

DOI Link

https://doi.org/10.16182/j.issn1004731x.joss.201805004

Last Page

1656

CLC

TP183

Recommended Citation

Tao Wenhua, Yuan Zhengbo. Prediction Model of Coke Quality Based on DE-BP Neural Network[J]. Journal of System Simulation, 2018, 30(5): 1650-1656.

DOI

10.16182/j.issn1004731x.joss.201805004