The Optimization of Fuzzy Neural Network Based on Artificial Fish Swarm Algorithm

To better solve the optimization problem of fuzzy neural network (FNN), a kind of method based on artificial fish swarm algorithm (AFSA) is proposed in this paper. Aiming at the structure optimization problem of FNN, AFSA-FNN1 is established and realizes the simplification of fuzzy rules. Aiming at the parameter optimization problem of FNN, AFSA-FNN2 is built and realizes the acquisition of parameters of membership function (MF) automatically. The proposed method uses for path planning of the robot, simulation results show that the optimized FNN can enhance the smoothness of the path.

I. Introduction

FNN is a kind of multilayer forward network, which uses distributed structure of neural network (NN) to connect the basic function of the fuzzy logic controller (FLC) together, so FNN has two kinds of advantages of NN and FLC. FNN is different from other types of NN, which can take advantage of the expert's knowledge and make all parameters have definite physical meaning. FNN is different from the ordinary fuzzy logic controller, the determination and adjustment of the input and output membership functions and extraction of fuzzy rules can be completed by self-learning ability of neural network.