In this thesis, the effect of operating conditions, such as temperature, gas hourly space velocity(GHSV), CH 4 /O 2 ratio and diluents gas (mol%) on ethylene production by oxidative coupling of methane (OCM) in a fixed bed reactor at atmospheric pressure was studied over Mn/Na 2 WO 4 /SiO 2 catalyst. 0.5gr of catalyst was loaded in a quartz reactor. Based on the properties of neural networks, an artificial neural network was used for model development from experimental data. In order to prevent network complexity and effective data input to network, principal component analysis method was used and the number of output parameters were reduced from 4 to 2. A feed-forward back-propagation network was used for simulating the relations between process operating conditions (the above-mentioned parameters) and aspects of catalytic performance, which include conversion of methane, C 2 + products selectivity, yield of C 2 + and C 2 H 4 /C 2 H 6 ratio. Levenberg– Marquardt method is presented to train the network. For first output, optimum network with 1-9-4 topology (one hidden layer which includes 9 neurons) and for second output, optimum network with 1-6-4 topology (one hidden layer including 6 neurons) was prepared. After the simulation process using A, operating conditions were optimized using Genetic Algorithm based on maximum yield of C 2 + . The optimum conditions were obtained as reaction temperature=850°C, GHSV=22464 cm 3 g -1 h -1 , diluents gas=30 (mol %) and CH 4 /O 2 ratio= 4. 33.03% of methane conversion, 71.07% of C 2 + product selectivity, 23/47% of C 2 + yield and 2/073 of C 2 H 4 /C 2 H 6 ratio were obtained under these optimum conditions. Experimental runs under optimum conditions were done at Research Institute of Petroleum Industry (RIPI) and the results obtained were compared with the simulated values obtained from the model. The average error from comparing experimental and simulated values for methane conversion, C 2 + products selectivity, yield of C 2 + and C 2 H 4 /C 2 H 6 ratio, was estimated as 2.73%, 10/66%, 5.48% and 10.28% respectively. Keywords: Oxidative Coupling of Methane (OCM); Mn/Na 2 WO 4 /SiO 2 catalyst; A Optimization; Genetic algorithm
