A novel kinetic model based on the free radical mechanism is used to simulate the oxidation of p-xylene (PX) in a continuous stirred-tank reactor (CSTR) under industrial operating conditions. Because this kinetic model cannot provide appropriate prediction of the influence of the reaction factors, such as catalyst concentrations, water concentrations, and temperatures, on the kinetic parameters for oxidation of PX in the laboratory semibatch reactor (SBR), the kinetic parameters that are highly nonlinear of the reaction factors are estimated by a back-propagation neural network (BPNN). Furthermore, correction coefficients are introduced to accurately evaluate the kinetic parameters based on Adaptive Immune Genetic Algorithm (AIGA) due to the significant difference between the nature of PX oxidation conducted in the laboratory SBR and in the industrial CSTR. The model with the evaluated optimum kinetic parameters is obtained, and its efficiency is validated via comparison with industrial data.