Multi-ANN Predictive Control of Citrus Peel Supercritical Extraction Temperature

Abstract:

Considering nonlinearity, time-variation and inertia during temperature control of large supercritical extraction units, especially under the disturbance of system flow and pressure, a multi-artificial neural network (ANN) predictive control policy was proposed. It contains a radial basis function (RBF) ANN, aiming to approach nonlinear extraction temperature object and predicting output variable based on this model. There is also a back propagation (BP) ANN controller, seeking the optimal controlling signal by feedback correction and rolling optimization on purpose to overcome the time-variation and inertia. The experimental results indicate that this control strategy has excellent dynamic response performance, small steady state error and strong robustness.

• Periodical: Advanced Materials Research (Volumes 236-238)
• Pages: 1472-1479
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.236-238.1472
• Online since: May 2011
• Authors: Hong Yu Zhou, Qian Zhao, Zhen Hua Zhang, Ming Wei Tong, Zheng Hai Wang
• Keywords: Essential Oil, Multi-Neural Network, Supercritical Extraction

References

[1] Raeissi, S.,Diaz, S.,Espinosa, S.Peters, C.J. Brignole, E.A Ethane as an alternative solvent for supercritical extraction of orange peel oils. Journal of Supercritical Fluids, 45, 306–313. (2008).

DOI: 10.1016/j.supflu.2008.01.008

[2] Zia-ur-Rehman. Critrus peel extract—A natural source of antioxidant. Food Chemistry, 99, 450–454. (2006)

DOI: 10.1016/j.foodchem.2005.07.054

[3] S.A. Rezzoug, N.Louka. Thermomechanical process intensification for oil extraction from orange peels. Innovative Food Science and Emerging Technologies 10. 530-536. (2009)

DOI: 10.1016/j.ifset.2009.05.008

[4] Diaz,S., Espinosa,S.,&Brignole, E.A. Citrus oil deterpenation with supercriticalfuids.Optimal process and solvent cycle design. Journal of supercritical fluids, 35, 49–61. (2005)

DOI: 10.1016/j.supflu.2004.12.002

[5] Danielski, L.,Brunner, G.,Schwfinke, C.,Zetzl,C.,Hense, H.,&Donoso J.P.M.. Deterpenation of mandarin (Citrus reticulata) peel oils by means of counter current multistage extraction and adsorption/desorption with supercritical CO2.Journal of Supercritical Fluids, 44,315–3240. (2008)

DOI: 10.1016/j.supflu.2007.09.007

[6] Feng Xu, Xionglin Luo. Margin analysis and control design of FCCU regenerator based on dynamic optimization. Mathematical description of dynamic optimization. CIESC Journal, 2009, 60(3):678.(In Chinese)

[7] Zhigang Hua, Jianhong Lü, Tiejun Zhang. Research and application of state variable-predictive control in 600MW unit reheater temperature control system. Proceedings of the CSEE, 2005,5(12):104-105. (In Chinese)

[8] Yong Wang, Jizhen Liu, Xiangjie Liu, et al. Design of superheat steam temperature controller based on discount recursive least square adaptive DMC. Proceedings of the CSEE, 2007, 27(8):71. (In Chinese)

[9] Xing Du, Min Tan. Analysis of the structure of one-input fuzzy PID. Control Theory & Application, 2004, 21(2):221. (In Chinese)

[10] Jiangtao Ji, Rongxian Wang, Lijun Fu. Grey prediction fuzzy PID control of the feeding quantity in combine. Transactions of the Chinese Society for Agricultural Machinery, 2008, 39(3):64-65. (In Chinese)

[11] Yang,Xue Guangzheng Peng, Baoguo He, et al. Asymmetric fuzzy PID control for pneumatic position control system. Control Theory & Application, 2004, 20(1):131.(In Chinese)

[12] Changliang Xia, Jie Xiu. RBF ANN nonlinear prediction model based adaptive PID control of switch reluctance motor. Proceedings of the CSEE, 2007, 27(3):58. (In Chinese)

DOI: 10.1109/chicc.2006.4347328

[13] Yan Zhang, Zengqiang Chen, Zhuzhi Yuan. PID-type multi-step predictive control of nonlinear system based on Taylor approximation. Control and decision, 2004,19(4):450.(In Chinese)

DOI: 10.1109/wcica.2004.1340664

[14] Kittisupakorn P, Thitiyasook P, Hussain M A, et al. Neural network based model predictive control for a steel pickling process. Journal of Process Control, 19:581. (2009)

DOI: 10.1016/j.jprocont.2008.09.003

[15] G.Cybenko. Approximation by superpositions of a sigmoidal function. Math.Con.Signal Syst., 2:pp.303-314. (1989)

DOI: 10.1007/bf02551274

[16] K.S. Narendra and K.Parthasarathy. Identification and control of dynamical systems using neural networks. IEEE Tras. Neural networks, 1:pp.4-27,March. (1990)

DOI: 10.1109/72.80202

[17] Michael L,Thompson, Mark A Kramer. Modeling Chemical Processes Using Prior Knowledge and Neural Networks. AIChE Journal, 40(8):1328-1340. (1994)

DOI: 10.1002/aic.690400806

[18] Satish Kumar. Neural networks. Beijing:Tsinghua University Press,:304-310.(2006)

[19] Zhigang Zhao, Kai Miao, Huixian Lü. Hydrid structure optimization algorithm of radial basis function neural network. Chinese Journal of Scientific Instrument, 2007, 28(4):650. (In Chinese)

[20] M G Zhang, X G Wang, M Q Liu. Adaptive PID control based on RBF neural network identification. Proceedings of the 17th IEEE International Conference on Tools with Artificial Intelligence. (2005)

DOI: 10.1109/ictai.2005.26

[21] Hongyu Zhou, Jian Zhang, et al. Nonlinear predictive function control based on hydrid neural network. Control Theory & Application, 2005, 22(1):112. (In Chinese)

[22] Tao Xie, Yigang He, Jiangang Yao, et al. Design of micro strip radio frequency band pass filter based on improved BP algorithm. Chinese Journal of Scientific Instrument, 2009, 30(6):1318. (In Chinese)

[23] Yingke Mao, Zhicheng Guan, Liming Wang, et al. Prediction of leakage current of outdoor insulators based on BP artificial neural network. Proceedings of the CSEE, 27(27):10. (2007) (In Chinese)

DOI: 10.1109/ceidp.2007.4451478