A chaotic system with measurable state variables fewer than the degrees of freedom of the system is identified with the Artificial Neural Network (ANN) method combined with dynamic training. Instead of using the usual method of Sum of Square Errors (SSE), the identified models are validated with the return maps (embedded trajectories), the largest Lyapunov exponent, and the correlation dimension when there is no exogenous input, and bifurcation diagram when there is an exogenous input. This method is demonstrated for nonisothermal, irreversible, first-order, series reaction A -> B -> C in a CSTR.
Kim HJ, Lee JS, Han C, Chang KS, "Chaos and Fractals in Process Systems Engineering," Proceedings of the forty-first annual meeting of the ISSS, Seoul, 1997
Kim HJ, "Identification and Validation of Neural Network Models for Chaotic Chemical Reaction Systems," M.S. Thesis, Pohang University of Science and Technology, Korea, 1998
Takens F, "Detecting Strange Attractors in Turbulence," in Lecture Notes in Mathematics, vol. 898 eds. Rand, D.A. and Young, L.S., Dynamical Systems and Turbulence, Springer Verlag, Berlin, 366, 1981
Teymour F, Ray WH, Chem. Eng. Sci., 44(9), 1967, 1989
Teymour F, Ray WH, Chem. Eng. Sci., 47(15-16), 4121, 1992
Teymour F, Ray WH, Chem. Eng. Sci., 47(15-16), 4133, 1992
Wang Y, Hudson JL, AIChE J., 37(12), 1833, 1991
Wolf A, Swift JB, Swinney HL, Vastano JA, Physica 16D, 285, 1985