The burning zone temperature in rotary kiln process is a vitally important controlled variable, on which the sinter quality mainly relies. Boundary conditions such as components of raw material slurry often change during kiln operation, but related offline analysis data delay to reach or even are unknown to the human operator. This causes unsatisfactory performance of the burning zone temperature controller and subsequent unstable production quality. To deal with this problem, a Q-learning-based supervisory control approach for burning zone temperature is proposed, in which the signals of human intervention are regarded as the reinforcement learning signals, so that the set point of burning zone temperature can be duly adjusted to adapt the fluctuations of the boundary conditions. This supervisory control system has been developed in DCS and successfully applied in an alumina rotary kiln. Satisfactory results have shown that the adaptability and performances of the control system have been improved effectively, and remarkable benefit has been obtained.
[1]
John N. Tsitsiklis,et al.
Feature-based methods for large scale dynamic programming
,
2004,
Machine Learning.
[2]
Zhiqiang Liu,et al.
Status and prospect of the application of municipal solid waste incineration in China
,
2006
.
[3]
Mika Järvensivu,et al.
Intelligent control system of an industrial lime kiln process
,
2001
.
[4]
Richard S. Sutton,et al.
Reinforcement Learning: An Introduction
,
1998,
IEEE Trans. Neural Networks.
[5]
L. P. Holmblad,et al.
The FLS application of fuzzy logic
,
1995
.
[6]
Richard S. Sutton,et al.
Generalization in ReinforcementLearning : Successful Examples UsingSparse Coarse
,
1996
.
[7]
Esko Juuso,et al.
Intelligent control of a rotary kiln fired with producer gas generated from biomass
,
2001
.
[8]
Hector Budman,et al.
Model predictive control with soft constraints with application to lime kiln control
,
1999
.