ANFIS-based Self-learning Expert System for Weapon Target Assignment Problem

Abstract

In this paper, we propose an efficient algorithm to solve the weapon target assignment (WTA) problem combining the advantages of rule-based with that of traditional optimization methods. The main ideal of the proposed algorithm is building an adaptive neuro-fuzzy inference system (ANFIS) to obtain an original assignment scheme, and then the original scheme is used to initialize particles in discrete particle swarm optimization (DPSO). With the original assignment scheme provided by ANFIS, it can solve the problem of converging to local optimum with random initialization in DPSO efficiently. At last, a numerical simulation is proposed to illustrate the efficiency of the method in this paper.