Soft Sensor of Naphtha Dry Point Based on Adaptive Immune Clustering RBF Networks Assembly

摘要

Based on the artificial immunology, a hybrid algorithm to design the RBF networks assembly is proposed. An artificial immune mechanism for data clustering is used to adaptively classify the data sample and simultaneously specify the amount and initial position of the RBF centers according to input data set. The degrees of membership are used for combining these models to obtain the final result. The algorithm used in the soft sensor of naphtha dry point can obviously improve the measurement accuracy of the frequent change of the crude oil. It has higher approaching precision and better generalization capability than the common RBFN method.