Temperature prediction and analysis based on BP and Elman neural network for cement rotary kiln

Baosheng Yang; Xiushui Ma

doi:10.1117/12.888304

26 May 2011 Temperature prediction and analysis based on BP and Elman neural network for cement rotary kiln

Baosheng Yang, Xiushui Ma

Proceedings Volume 7997, Fourth International Seminar on Modern Cutting and Measurement Engineering; 79972I (2011) https://doi.org/10.1117/12.888304
Event: Fourth International Seminar on Modern Cutting and Measuring Engineering, 2010, Beijing, China

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.

Citation Download Citation

Baosheng Yang and Xiushui Ma "Temperature prediction and analysis based on BP and Elman neural network for cement rotary kiln", Proc. SPIE 7997, Fourth International Seminar on Modern Cutting and Measurement Engineering, 79972I (26 May 2011); https://doi.org/10.1117/12.888304

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available