THERMAL RUNAWAY OF ETHYLENE OXIDATION REACTORS - PREVISION THROUGH NEURONAL NETWORKS

The dynamic behavior of an ethylene oxidation fixed-bed reactor has be en originally simulated by a phenomenological model, encompassing mass and energy balances of the catalytic bed. This model makes use of the one-dimensional pseudo-homogeneous approach, with apparent kinetic pa rameters obtained from the literature. The resulting set of partial-di ferential equations is solved by discretization of the space variable in finite-differences and integration of the attained ordinary-differe ntial equations with respect to time with a marching algorithm that ac counts for the problem of stiffness near the runaway point. This paper focuses on the use of a neuronal network in forecasting possible ther mal runaway situations of this highly exothermic process. The final ob jective is to build a reliable inference alarm algorithm for fast dete ction and prevention of this situation. The neuronal network also pred icts eventual hot spot position and temperature, based on informations such as inlet flows, temperatures and pressures, provided by the plan t instrumentation. Feedforward neuronal networks were used, with one h idden layer. A training algorithm based on a combination of backpropag ation and gaussian random guesses was applied. The neuronal network re presents well the evolution of the transient temperature profile.