潜艇垂直面运动自适应神经网络模糊控制仿真  

Simulation of ANFIS Control for the Motion of Submarine in Vertical Plane

作　　者：赵阳[1] 邢继峰[1] 

机构地区：[1]海军工程大学船舶与动力学院,湖北武汉430033

出　　处：《计算机仿真》2009年第6期26-29,共4页Computer Simulation

摘　　要：神经网络控制和模糊控制技术的广泛应用为潜艇自动舵控制器的设计提供了新的思路。而模糊规则的提取和隶属函数的学习是模糊推理系统设计中重要而困难的问题,自适应神经网络模糊推理系统(ANFIS)结合模糊控制和神经网络控制的优点,基于sugeno模糊模型采用反向传播法和最小二乘法调整模糊推理系统的参数,并自动产生模糊规则。利用方法对潜艇垂直面运动自动舵控制器进行了设计和仿真。从仿真结果来看,自适应神经网络模糊控制器能较好的实现对潜艇垂直面运动的操纵控制,是一种很好的控制方法。The wide use of neural networks and fuzzy control provides a new way to design the control method for auto - pilot of submarine. Extraction of fuzzy rules and learning of parameters of membership functions play an essential role in the design of a fuzzy inference system but they are difficult. The Adaptive Network - based Fuzzy Inference System（ANFIS） has the advantages of both neural networks and fuzzy control. The ANFIS method is based on Sugeno fuzzy model and has a structure similar to neural network by adjusting the parameters of the fuzzy inference system with backpropagation algorithm and least - square method and producing fuzzy rules automatically. This paper designs a controller of auto - pilot for the motion of submarine in vertical plane, and a good simulation result is abtained.

关 键 词：潜艇 操纵 深度 自适应神经网络模糊系统 仿真 

分 类 号：U666.153[交通运输工程—船舶及航道工程]