Oxidative Cracking of <i>n</i>-Hexane to Light Olefins over VO_<i>x</i>/MgO-γAl₂O₃ Using Lattice Oxygen: Performance Evaluation and Machine Learning Modeling

This study investigates VOx/MgO-γAl2O3 in the oxidative cracking ofn-hexane to produce light olefins in the absence of gas-phase oxygen. The catalysts were prepared with varying mass ratios of MgO/γAl2O3(1:2, 1:1, and 2:1), while the VOx loading was maintained at 10 wt %. Among the synthesized catalysts, VOx/MgO-γAl2O3 1:1 showed superior catalytic activity, with 89.1% n-hexane conversion and 92.6% light olefin selectivity. Introducing an appropriate amount of MgO enhanced the dispersion of VOx active species, balanced the acidity, and suppressed the oxidation of hydrocarbons. Additionally, a machine learning model was developed to predict oxidative cracking products’ yields. The model, based on 44 data points from this study and literature, predicted n-hexane conversion, olefin yield, carbon oxide yield, methane yield, and paraffin yield using catalyst formulations, temperature, and time as inputs. The model showed a high correlation (R2) of 0.99 and RMSE values between 1.6 and 8.5, highlighting its strong predictive capability.