Share Email Print

Proceedings Paper

Temperature prediction and analysis based on BP and Elman neural network for cement rotary kiln
Author(s): Baosheng Yang; Xiushui Ma
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

In order to reduce energy consumption and improve the stability of cement burning system production, it is necessary to conduct in-depth analysis of the cement burning system, control the operation state and law of the system. In view of the rotary kiln consumes most of the fuel, we establish the simulation model of the cement kiln used to find effective control methods. It is difficult to construct mathematical model for the rotary cement kiln as the complex parameters, so we expressed directly using neural network method to establish the simulation model for the kiln. Choosing reasonable state and control variables and collecting actual operation data to train neural network weights. We first in-depth analyze mechanism and working parameters correlation to determine factors of the yield and quality as the model input variables; then constructed cement kiln model based on BP and Elman network, both achieved good fitting results. Elman network model has a faster convergence speed, high precision and good generalization ability. So the Elman network based model can be used as simulation model of the cement rotary kiln for exploring new control method.

Paper Details

Date Published: 26 May 2011
PDF: 6 pages
Proc. SPIE 7997, Fourth International Seminar on Modern Cutting and Measurement Engineering, 79972I (26 May 2011); doi: 10.1117/12.888304
Show Author Affiliations
Baosheng Yang, Suzhou Univ. (China)
Xiushui Ma, Zhejiang Univ. (China)

Published in SPIE Proceedings Vol. 7997:
Fourth International Seminar on Modern Cutting and Measurement Engineering
Jiezhi Xin; Lianqing Zhu; Zhongyu Wang, Editor(s)

© SPIE. Terms of Use
Back to Top