This paper investigated a soft sensor modeling approach based on radial basis function networks (RBFN). A fuzzy c-means (FCM) clustering algorithm is used to classify training vectors into several clusters, each cluster is trained by a radial basis function network, and membership values are used for combining several network outputs to obtain the final result. In the online stage, membership values are computed using an adaptive fuzzy clustering algorithm for the new vector. The proposed approach has been applied to the slab temperature estimation in a practical walking beam reheating furnace. Simulation results show that the approach is effective.