A Novel Neural Network-Based Control Scheme for Controlling the Multivariable Anaesthesia

El-Rabaie, Nabila M-; Awad, Hamdi A.; Mahmoud, Tarek A.

doi:10.21608/mjeer.2007.64152

A Novel Neural Network-Based Control Scheme for Controlling the Multivariable Anaesthesia

Document Type : Original Article

Authors

Dept. of Industrial Electronics and Control Eng., Faculty of Electronic Engineering, Menoufya University, EGYPT

10.21608/mjeer.2007.64152

Abstract

Developing control schemes such as generalized predictive control and selforganized fuzzy logic control schemes to single-input single-output muscle relaxation process, has been validated in a series of clinical trials. The applications of these schemes to the multivariable anaesthetic model require many design parameters to be selected. This is due to the complex features that characterize such models. Among these features, the large patient-to-patient variability in model’s parameters is perhaps the most challenging one. This paper proposes a new internal model control (IMC) scheme to overcome this challenge with ease. Unlike the conventional IMC scheme, the proposed IMC scheme needs not a neural network used as a controller. Instead, its controller’s parameters are estimated based on its developed parametric neural network’s model; AutoRegressive eXogenous Local Model (ARX-LM). In short, the proposed IMC scheme has a delay-deprived ARX-LM network, and a controller that estimates its parameters based on the information of the developed delay-deprived model. Simulation results demonstrated the superiority of the proposed IMC scheme over self-organized schemes developed for the multivariable anaesthesia.

Keywords

References

[1] Mahfouf, M., and Linkens, A. D., Generalized predictive control and bioengineering, T. J. International Ltd, Padstow, UK, 1998. [2] Geneilini, A. L., Feedback control of hypnosis and analgesia in humans, Ph.D thesis, Swiss Federal Institute of Technology (ETH), Zurich, Switzerland, March, 2001. [3] Shieh, S. J., Linkens, A. D., and Peacock, E. J., “ Hierarchical rule –based and selforganizing fuzzy logic control for depth of anaesthesia”, IEEE Transaction on Systems, Man, and Cybernetics-Part C, vol. 29, no. 1, February, 1999. [4] Morari M. and Zafiriou E., Robust process control, Englewood Cliffs, NJ, PrenticeHall, 1989. [5] Hamdi A. Awad and Tarek A. Mahmoud “A novel ARX-local model network for modeling and controlling dynamic systems”, Proceedings of Alexandria Engineering Journal AEJ'06, vol. 45, Alexandria University, Egypt, 2005. [6] Ward, S., Neill, E. A. M., Weatherley, B. C., and Corall, I. M., “Pharmacokinetics of atracurium besylate in healthy patients”, British Journal of Anaesthesia, vol. 55, 1983. [7] Weatherley, B. C., Wiliams, S. G., and Neill, E. A. M., “Pharmacokinetics, Pharmacodynamics and dose response relationship of atracurium administrated i.v.”, British Journal of Anaesthesia, vol. 55, 1983. [8] Whiting, B., and Kelman, A. W., “The modeling of drug response”, Clinical Science, vol. 59, 1980. [9] Isabelle R., Leon P., “Nonlinear internal model control using neural network: application to processes with delay design issues”, IEEE Trans. Neural Network, Vol. 11, pp. 80 -90, 2000. [10]Takagi, T., and Sugeno, M., “Fuzzy identification of systems and its applications to modeling and control”, IEEE Transactions on Systems, Man, and Cybernetics, vol. SMC-15, pp. 116-132, 1985. [11]Daniel W., Ho. C., Ping-An Zhang, and Xu. Jinhua , “Fuzzy wavelet networks for function learning”, IEEE. Trans. Fuzzy System, Vol. 9, no. 1, 2001. [12]Larsen P. M., “Industrial applications of fuzzy logic control”, Int. J. Man Mach. Studies, vol. 22, 1980. [13]Carpenter, G.A., Grossberg, S., and Rosen, D.B., “Fuzzy ART: Fast stable learning and categorization of analogue patterns by an adaptive resonance system”, Neural Networks, vol. 4, 1991.

[14]Tanaka K. , “Stability and stabilization of fuzzy-neural-linear control systems,” IEEE. Trans. Fuzzy System, vol. 3, no. 4, 1995. [15]Kosko B., “Global stability of generalized adaptive fuzzy systems,” IEEE Trans. Sys. Man. Cybern. , Part C, vol. 28, no. 3, 1998. [16]Daio Y. K., and Passino M., “adaptive neural-fuzzy control for interpolated nonlinear systems” IEEE. Trans. Fuzzy System, vol. 10, no. 5, 2002