Heuristic dynamical programming control for catalyst baking furnace temperature

doi:10.3969/j.issn.0438-1157.2013.12.051

Abstract

Abstract: To solve the temperature control problem of the catalyst baking furnace,a heuristic dynamical programming (HDP) control method is proposed.The optimal control policy in HDP scheme is approximated gradually by implementing policy evaluation and policy improvement repeatedly.The system dynamics and the critic model are established by artificial neural networks.The learning algorithm of the HDP controller is clarified based on the gradient-decent principle.The proposed controller is tested on a baking furnace in a certain catalyst company.The experimental results indicate that the HDP controller has stronger ability to accommodate different work conditions than PID controller.In comparison with PID controller,the control precision in HDP controller increases about 70%,and the average electric current in HDP controller decreases about 5%.

Key words: catalyst, temperature control, heuristic dynamical programming, artificial neural networks

摘要： 针对催化剂生产过程中焙烧窑炉温度控制问题，提出了一种启发式动态规划（heuristic dynamical programming，HDP）控制方法。该方法通过策略评价及策略提升的重复进行逐渐逼近最优的控制策略。采用人工神经网络建立了被控系统和评价指标模型，基于梯度下降原理阐明了控制器各模块的在线学习方法。对某催化剂公司的窑炉温度控制实验表明，与常规PID控制相比，HDP控制方案具有较强的工况适应能力，其控制精度较常规控制提高约70%，加热电流均值减小约5%。

关键词: 催化剂, 温度控制, 启发式动态规划, 人工神经网络

CLC Number:

TP18

BO Yingchun, XIA Bokai. Heuristic dynamical programming control for catalyst baking furnace temperature[J]. CIESC Journal, 2013, 64(12): 4615-4620.

薄迎春, 夏伯锴. 催化剂窑炉温度的启发式动态规划控制[J]. 化工学报, 2013, 64(12): 4615-4620.

References 20

[1]	Li J, Hai H, Yan C F.Effect of calcination temperature on properties of Cu/ZnO/Al2O3/Cr2O3+H-ZSM-5 bi-functional catalysts for steam reforming of dimethyl ether[J].Journal of Fuel Chemistry and Technology, 2012, 40 (10):1240-1245
[2]	Li X, Zheng J M, Yang X L.Preparation and application of highly efficient Au/SnO2 catalyst in the oxidative lactonization of 1, 4-butanediol to γ-butyrolactone[J].Chinese Journal of Catalysis, 2013, 34:1013-1019
[3]	Li Zhong (李忠), Zhang Xiaobing (张小兵), Guo Qihai (郭启海), Liu Yan (刘岩).Influence of spray drying temperature on performance of CuO/ZnO/Al2O3 catalyst for methanol synthesis in slurry reactor[J].CIESC Journal (化工学报), 2011, 62 (6):1554-1562
[4]	Zhang Kongyuan (张孔远), Liu Jingyi (刘静怡), Liu Yukang (刘毓康).Influence of calcination temperature on properties of Co-Mo-Ni-W/γ-Al2O3 hydrotreating catalyst[J].Acta Petrolei Sinica (石油学报), 2013, 29 (1):28-34
[5]	Yu Jun (俞俊), Mao Dongsen (毛东森), Guo Qiangsheng (郭强胜).Effect of calcination temperature of monodispersed SiO2 on the performance of Rh-based catalysts for CO hydrogenation[J].Acta Phys. -Chim.Sin. (物理化学学报), 2012, 28 (3), 667-673
[6]	Zhao Zhengtao (赵峥涛), Chen Qiyang (陈其扬).Research on the gas furnace temperature control system[J].Control and Instruments in Chemical Industry (化工自动化及仪表), 2000, 27 (1):21-23
[7]	Li Yingchong (李颖冲), Chen Xiaoqiang (陈小强), Wang Siming (王思明).Simulation based on fuzzy adaptive PID for ceramics KILN temperature control system[J].China Ceramics (中国陶瓷), 2009, 45 (7):51-54
[8]	Cui G M, Xiao P, Li Y N.Based on the heating furnace temperature fuzzy-PID control method research//World Congress on Intelligent Control and Automation[C].Beijing, 2012:1553-1557
[9]	Zhou Yilin (周以琳), Jiang Haibo (江海波), Zhan Zhitao (战智涛).Furnace temperature control system based on IMC[J].Journal of Qingdao University of Science and Technology (青岛科技大学学报), 2008, 29 (2):164-166, 174
[10]	Zhang Y X, Liu T, Wang J H.A novel RBF neural network based on data dispersion level and its application in BOF endpoint prediction//Chinese Control and Decision Conference[C].Guiyang, 2013:1900-1903
[11]	Li J J, Feng H T, Li S T.Wavelet prediction fuzzy neural network of the annealing furnace temperature control//International Conference on Electric Information and Control Engineering[C].Wuhan, 2011:940-943
[12]	Wen D D.Decoupling control of electric heating furnace temperature based on DRNN neural network//International Conference on Electronic Computer Technology[C].Kuala Lumpur, 2010:261-264
[13]	Wang F Y, Zhang H G, Liu D R.Adaptive dynamic programming:an introduction[J].IEEE Computational Intelligence Magazine, 2009, 4 (2):39-47
[14]	Lewis F L, Vrabie D.Reinforcement learning and adaptive dynamic programming for feedback control[J].IEEE Circuits and Systems Magazine, 2009, 9 (3):32-50
[15]	Zhang H G, Cui L L, Zhang X.Data-driven robust approximate optimal tracking control for unknown general nonlinear systems using adaptive dynamic programming method[J].IEEE Transactions on Neural Networks, 2011, 22 (12):2226-2236
[16]	Yang L, Si J, Tsakalis K S, Rodriguez A A.Direct heuristic dynamic programming for nonlinear tracking control with filtered tracking error[J].IEEE Transactions on Systems, Man, and Cybernetics, Part B:Cybernetics, 2009, 39 (6):1617-1622
[17]	Ku C, Lee K Y.Diagonal recurrent neural networks for dynamic systems control[J].IEEE Transactions on Neural Networks, 1995, 6 (1):144-156
[18]	Wedge D, Ingram D, McLean D.On global-local artificial neural networks for function approximation[J].IEEE Transactions on Neural Networks, 2006, 17 (4):942-952
[19]	Hayakawa T, Haddad W M.Neural network adaptive control for a class of nonlinear uncertain dynamical systems with asymptotic stability guarantees[J].IEEE Transactions on Neural Networks, 2008, 19 (1):80-89
[20]	Qiao Junfei (乔俊飞), Bo Yingchun (薄迎春), Han Guang (韩广).Application of ESN-based multi indices dual heuristic dynamic programming on wastewater treatment process[J].Acta Automatica Sinica (自动化学报), 2013, 39 (7):1146-1151