Artificial Bee Colony Algorithm With Tree-Seed Searching For Modeling Multivariable Systems Using Grnn

In this paper, an artificial bee colony algorithm with tree-seed searching (tsABC) is proposed for modeling multivariable systems using GRNN. In the tsABC, the local search operator of tree-seed algorithm is added to the onlooker bee phase of ABC. The optimization results with some benchmark functions show the effectiveness of tsABC. tsABC based GRNN (tsABC-GRNN) is adopted to model the crude oil fractionation process. The simulation results show that the proposed modeling method can reflect the characteristics of the real process.