The melt index (MI) is considered as one of the most important quality variables to determine propylene product specifications. Reliable prediction of the MI is significant in practical propylene polymerization (PP) processes. This paper presents novel predictive fuzzy functions (FF), combining the particle swarm optimization (PSO) algorithm and weighted least squares support vector machines (WLS-SVM) to infer MI from real PP process variables, where the FF utilize WLS-SVM for regression models to calculate the parameters and the PSO algorithm further optimizes the model. Research on the proposed FF model is carried out with the data from a real PP plant and the results are compared among the standard SVM, FF-LS-SVM, FF-WLS-SVM, and PSO-FF-WLS-SVM models. The results show that the model developed here can be a powerful tool for online MI prediction.