Abstrato

Estimation of temperature distribution along an annular fixed bed reactor in the oxidative coupling of methane (OCM) process by using artificial neural network

M.A.Torangi, A.Vatani, M.Yousefi, E.Joudaki

In this research an expertmodel based on artificial neural network was used to estimate temperature distribution along an annular fixed bed reactorwhich has been used in the Oxidative Coupling of Methane (OCM) Process. Experiments was done by using the Li/MgO Catalyst with different percentage of Li content in range of 1.6-6.6 %. In order to find the best efficiency estimator of sieve tray, different training schemes for the back-propagation learning algorithm, such as; Scaled Conjugate Gradient (SCG), Levenberg- Marquardt (LM),GradientDescentwithMomentum(GDM), variable learning rate BP(GDA) and Resilient BP(RP) methods were examined. Finally among those trained networks, the LM algorithm with ten neurons in the hidden layer shows the best suitable algorithm with the minimum average absolute relative error 0.005226.