Based on the polymerizing technique and its thermal equilibrium mechanism for polyvinyl chloride (PVC), soft-sensor modeling of PVC polymerizing production processes is important and necessary for stabilizing and optimizing the PVC polymerizing production process. According to the principle that multiple models can enhance the overall accuracy and robustness of a predicative model, a multi T-S fuzzy neural network soft-sensing model combining with fuzzy c-means (FCM) clustering algorithm is proposed to predict the conversion rate and velocity of vinyl chloride monomer (VCM) in the PVC polymerizing production process. Firstly, the principal component analysis (PCA) method is adopted to select the auxiliary variables of the soft-sensing model in order to reduce the model dimensionality. Then, a hybrid optimization algorithm utilizing the harmony search (HS) and least square method is proposed to optimize the structure parameters of the T-S fuzzy neural network. Ultimately, simulation results show that the proposed model can significantly enhance the predictive accuracy and robustness of the technical-and-economic indexes and satisfy the real-time control requirements of PVC polymerizing production process.