A Genetically Optimized Fuzzy Neural Network for Ship Controllers

Author

Sui, Jianghua ; Lin, Yejin ; Ren, Guang

Author_Institution

Marine Eng. Coll., Dalian Maritime Univ.

fYear

2006

fDate

25-28 June 2006

Firstpage

1367

Lastpage

1371

Abstract

A novel approach has been promoted for fuzzy neural ship controllers. An RBF neural network and GA optimization are employed in a fuzzy neural controller to deal with the nonlinearity, time varying and uncertain factors. Utilizing the designed network to substitute the conventional fuzzy inference, the rule base and membership functions can be auto-adjusted by GA optimization. The parameters of neural network can be decreased by using union-rule configuration in the hidden layer of the network. The performance of controller is evaluated by the system simulation conducted with Simulink tools, by which satisfactory results were obtained

Keywords

control system analysis; fuzzy control; genetic algorithms; neurocontrollers; nonlinear control systems; radial basis function networks; ships; time-varying systems; uncertain systems; GA optimization; RBF neural network; Simulink tools; auto function adjustment; controller performance evaluation; fuzzy neural controllers; genetic algorithms; nonlinear systems; ship controllers; time varying systems; uncertain systems; union-rule configuration; Control systems; Design optimization; Fuzzy control; Fuzzy logic; Fuzzy neural networks; Fuzzy systems; Marine vehicles; Mechatronics; Neural networks; Radial basis function networks; Fuzzy control; Genetic algorithm; RBF network; Ship control; Union rule;

fLanguage

English

Publisher

ieee

Conference_Titel

Mechatronics and Automation, Proceedings of the 2006 IEEE International Conference on

Conference_Location

Luoyang, Henan

Print_ISBN

1-4244-0465-7

Electronic_ISBN

1-4244-0466-5

Type

conf

DOI

10.1109/ICMA.2006.257827

Filename

4026287