Soft-sensor for the water content of dregs in rotary dryer kiln based on hybrid chaos optimization algorithm
基于混沌混合优化的回转干燥窑出料含水量软测量

It is difficult to control the process for rotary dryer kiln because the reliable online measurement for the water content of dregs is hardly available.Based on analysis of the drying process of rotary dryer kiln,this paper proposes a distributed RBF neutral network soft-sensor model for water content of dregs and a new hybrid optimal algorithm.The input space is divided into multi-subspace by using prior knowledge and fuzzy clustering.For the RBF network with each subspace,the number of hidden nodes is determined by using the fuzzy c-mean(FCM) clustering algorithm and clustering validity criteria,the learning of center vector adopts the hybrid optimization algorithm combining the chaos optimization with FCM.Experiments of acquiring the sample data are designed.The model has been built and successfully used in the inference control of rotary dryer kiln.