Hierarchical Process Neural Network Model within Variable-Sampling Time

Abstract:

The biochemical processes are usually described as seriously time varying and nonlinear dynamic systems. It is very costly and difficult to build their first-principle models due to the absence of inherent mechanism and efficient on-line sensors. In this paper, a hierarchical process neural network (HPNN) model within variable-sampling time has been proposed. Simulation is based on penicillin fed-batch fermentation process, shows that the model established is more accurately and efficient, and suffice for the requirements of control and optimization for biochemical processes.

• Periodical: Applied Mechanics and Materials (Volumes 20-23)
• Pages: 920-925
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.20-23.920
• Online since: January 2010
• Authors: Lei Chen, Fei Liu
• Keywords: Biochemical Processes, Hierarchical Process Neural Network, Modeling, Variable-Sampling Time

References

[1] Campello, R. J. G. B. and Amaral, W. C. : Takagi-Sugeno fuzzy models within orthonormal basis function framework and their application to process control. The 11th IEEE International Conference on Fuzzy Systems, Honolulu/USA (2002) 1399-1404.

DOI: 10.1109/fuzz.2002.1006709

[2] Campello, R. J. G. B. and F. J. VonZuben, etc. Hierarchical fuzzy models within the framework of orthonormal basis functions and their application to bioprocess control. Chemical Engineering Science 58 (2003) 4259-4270.

DOI: 10.1016/s0009-2509(03)00309-9

[3] L.A. Rusinov and I.V. Rudakova etc. Fault diagnosis in chemical processes with application of hierarchical neural networks. Chemometrics and Intelligent Laboratory Systems 97 (2009) 98-103.

DOI: 10.1016/j.chemolab.2008.09.004

[4] LeiZhi Chena, Sing Kiong Nguanga, etc. Modeling and optimization of fed-batch fermentation processes using dynamic neural networks and genetic algorithms. Biochemical Engineering Journal 22 (2004) 51-61.

DOI: 10.1016/j.bej.2004.07.012

[5] Jie Zhang. Modeling and Optimal Control of Batch Processes Using Recurrent Neuro-Fuzzy Networks. IEEE Transactions on Fuzzy Systems, VOL. 13, NO. 4, (2005). 417-427.

DOI: 10.1109/tfuzz.2004.841737

[6] He Xingui, Liang Jiuzhen. Some Theoretical Issues on Procedure Neural Networks. Engineering Science. Vol. 2, No. 12, (2000): 40-44.

[7] He Xingui, XU Shaohua. Process Neural Network with Time-Varied Input and Output Functions and Its Applications. Journal of Software. Vol. 14, No. 4, (2003): 764-769.

[8] XU Shaohua, He Xingui. Learning Algorithms of Process Neural Networks Based on Orthogonal Function Basis Expansion. Chinese Journal of Computers. Vol. 27, No. 5, (2004): 645-650.

[9] XU Shaohua, He Xingui, etc. Some Theoretical Issues on Continuous Process Neural Networks. Acta Electronica Sinica, Vol. 34, No. 10, (2006): 1838-1841.

[10] He Xingui, XU Shaohua. Process Neural Networks. Beijing: Publishing House of Science Press. (2007).

[11] Raju, G. U., Zhou, J. and Kisner, R. A. Hierarchical fuzzy control. International Journal of Control, Vol. 54, No. 5, (1991): 1201-1216.

DOI: 10.1080/00207179108934205

[12] Information on http: /216. 47. 139. 198/pensim/links. html.

[13] G. Birol, C. Undey, and A. Cinar, A modular simulation package for feed-batch fermentation: penicillin production. Journal of Computers and Chemical Engineering. vol. 26. (2002): 1553-1565.

DOI: 10.1016/s0098-1354(02)00127-8

[14] R. S. Parker. Nonlinear model predictive control of a continuous bioreactor using approximate data-driven models. American Control Conference, Anchorage, AK, USA, (2002).

DOI: 10.1109/acc.2002.1025227

[15] Bajpai R, Reuss M. A mechanistic model for penicillin production. Journal of Chemical Technology and Biotechnology (S0268-2575), (1980), 30: 332－344.

[16] Liu Zhongkan. Orthogonal functions and applications. Beijing: Publishing House of National Defence, (1982): 40-52.