Model Identification of Boiler Combustion System Based on the Modified ELMAN Network

Abstract:

Boiler combustion system is a multiple input multiple output complex controlled process, which with large time delay and model uncertainty features. In order to improve the control quality of industrial boiler system and find the appropriate control algorithm to realize the optimal control of boiler combustion system, the article has carried on the model identification for boiler combustion system by the method of neural network. It could make the adjustment of controller parameter more effective, make industrial process simulation more convenient; and play a big role for online control and forecast to the industrial object. The results show that the modified ELMAN neural network can identify the mathematical model of combustion system quickly and accurately.

• Periodical: Applied Mechanics and Materials (Volumes 556-562)
• Pages: 4491-4495
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.556-562.4491
• Online since: May 2014
• Authors: Ruo Gu Zhang*, Yu Ning Peng, Yi Fei XIE, Zhang Ming Huang
• Keywords: Boiler Combustion System, Elman Neural Network (ENN), Large Time Delay, System Identification

References

[1] Liukkonen M, Heikkinen M, Hiltunen T, et al. Artificial neural networks for analysis of process states in fluidized bed combustion[J]. Energy, 2011, 36(1): 339-347.

DOI: 10.1016/j.energy.2010.10.033

[2] Chen Y, Xiaolong G. Dynamic modeling and simulation of a 410t/h Pyroflow CFB boiler[J]. Computers & chemical engineering, 2006, 31(1): 21-31.

DOI: 10.1016/j.compchemeng.2006.04.006

[3] Ding S, Zhang Y, Chen J, et al. Research on using genetic algorithms to optimize Elman neural networks[J]. Neural Computing and Applications, 2013, 23(2): 293-297.

DOI: 10.1007/s00521-012-0896-3

[4] Wang X, Zhang C, Zhang S. Modified Elman neural network and its application to network traffic prediction[C]/Cloud Computing and Intelligent Systems (CCIS), 2012 IEEE 2nd International Conference on. IEEE, 2012, 2: 629-633.

DOI: 10.1109/ccis.2012.6664250

[5] Li M, Wei Z L, Hua X Z, et al. The Short-term Predicting Method of Algal Blooms Based on Libsvm and Elman Neural Network Modeling[J]. (2013).

[6] Lu H, Zhang Y, Wu C, et al. Dynamic Model Identification of the Main Steam Temperature for Supercritical Once-through Boiler[J]. Energy Procedia, 2012, 17: 1704-1709.

DOI: 10.1016/j.egypro.2012.02.301

[7] Geng-biao C, Hui-yong C, Shang-hong H E. Application of Improved Elman Network in System Identification [J][J]. Mechanical Engineering & Automation, 2005, 6.