The catalytic naphtha reforming process is one of the most significant processes in the petrochemical industry. This process is notable for its function of transforming petroleum refinery naphtha from crude oil with low octane ratings into high-octane premium blending stocks, namely, gasoline or aromatic hydrocarbons. This process consists of many units along with complicated chemical reactions, which leads to large-scale and strong coupling, with time variation and nonlinearity to some extent. Under such circumstances, it remains a great challenge to control and optimize the catalytic reforming process. To evaluate the current operational status of the catalytic reforming process, there is a need for online assessment of some key quality-related indices for engineers as a reference. Among these indices, research octane number (RON) barrel is widely used for the evaluation of gasoline quality. However, traditional measurement methods are often time-consuming, labor-consuming, and expensive. To overcome such drawbacks, a data-driven predictive model for the prediction of RON barrel values is proposed in this study. Considering data from real industry are often contaminated with noise and other uncertain factors, conventional data-driven prediction methods may fail in the extraction of useful process information. Meanwhile, missing data is also commonly observed in real industrial samples. To deal with these problems, the proposed predictive model employs a semisupervised learning-based just-in-time learning framework. Different from traditional just-in-time learning frameworks, variable selection is taken into consideration in the proposed framework, in addition to sample selection. And both selection approaches proceed on the basis of the symmetric Kullback-Leibler divergence, which measures the distributional dissimilarities among samples or variables, to reduce the noise influence. Additionally, variational Bayesian principal component analysis, which is known as an effective generative model, is exploited to alleviate the missing data problem. Eventually, a novel nonlinear slow feature analysis algorithm, namely, locally weighted slow feature analysis, is put forward to model the time variance and nonlinearity of this process. To better validate the efficiency and superiority of the proposed method, an industrial case study is conducted with data collected from a real industrial catalytic reforming process, where missing data percentage ranges from 0.1 to 10%. The qualitative and quantitative results demonstrate that the proposed technique can outperform some conventional data-driven methods.