Neural network soft sensor modeling method based on adaptive fuzzy clustering

A neural network soft sensor modeling method based on fuzzy clustering is presented. The training data set is separated into several clusters with different centers, the number of fuzzy cluster is decided automatically, and the clustering centers are modified using an adaptive fuzzy clustering algorithm in the online stage. This method can reduce the calculation remarkably and has good prediction accuracy. The proposed method has been applied to the slab temperature estimation in a practical walking beam reheating furnace. Simulation results show that the method can deal with the measuring problem of the slab temperature in heating process online.