Thermo-catalytic methane decomposition is a prospective route for producing CO_x free hydrogen. In this study, Bayesian regularization and Levenberg-Marquardt trained multilayer perceptron neural networks were employed in predictive modeling of hydrogen production by thermo-catalytic methane decomposition. Based on the non-linear relationship between the reaction temperature, weight of the catalysts, time of stream, calcination temperature, calcination time, specific volume, and the hydrogen yield, the various topology was configured for the neural network and tested to determine the artificial neuron that would result in the best model performance. The Levenberg-Marquardt trained neural network displayed the best performance with the model topology of 7–16-1 compared with the Bayesian regularization trained network. The model topology of 7–16-1 represents the input units, hidden neuron, and the output unit. The predicted hydrogen yield by the 7–16-1 configured neural network was in strong agreement with the observed value, evidenced by the coefficient of determination (R²) of 0.953 and mean square error of 0.03. A predicted hydrogen yield of 86.56 vol.% was obtained at the reaction temperature of 700 °C, 0.5 g catalyst weight, calcination temperature of 600 °C, calcination time of 240 min, catalyst specific surface area of 24.1 m²/g, the pore volume of 0.03 cm³/g, and 160 min time on stream which is at proximity with the observed value of 84 vol.%. The sensitivity analysis revealed that all the input parameters have varying levels of importance on the model output. However, the intrinsic properties of the catalysts (specific surface area, and the pore volume) have the most significant influence on the predicted hydrogen yield.

热催化甲烷分解是产生CO _x的潜在途径游离氢。在这项研究中，贝叶斯正则化和Levenberg-Marquardt训练的多层感知器神经网络被用于通过热催化甲烷分解制氢的预测模型。基于反应温度，催化剂重量，物流时间，煅烧温度，煅烧时间，比容和氢气产率之间的非线性关系，为神经网络配置了各种拓扑结构，并进行了测试以确定人工神经元，将导致最佳模型性能。与贝叶斯正则化训练网络相比，Levenberg-Marquardt训练的神经网络在7–16-1的模型拓扑中显示出最佳性能。7–16-1的模型拓扑表示输入单位，隐藏的神经元和输出单位。²）为0.953，均方误差为0.03。在700°C的反应温度，0.5 g的催化剂重量，600°C的煅烧温度，240 min的煅烧时间，24.1 m ² / g的催化剂比表面积下，预计的氢气产率为86.56 vol。％。孔体积为0.03 cm ³ / g，运行时间为160分钟，与84体积％的观测值接近。敏感性分析表明，所有输入参数对模型输出的重要性都有不同程度的影响。但是，催化剂的固有性质（比表​​面积和孔体积）对预测的氢收率影响最大。