Description:
本文在分析城市交通信号控制研究现状和交叉口交通信号控制原理、评价方
法的基础上,设计了单交叉口交通信号两级模糊控制系统。分级模糊控制能有效
减少模糊规则数,易于提取模糊规则,适合于交通状况复杂的城市交叉口交通信
号控制。但它存在难以由人工合理定义全部模糊隶属度函数的问题。为此本文进
一步采用遗传算法对两级模糊控制器中模糊隶属度函数进行优化。本文提出的方
法具有分级模糊控制的优点,同时可以使模糊隶属度的选取更为合理,获得更好
的控制效果。对一个四相位单交叉口,利用MATLAB在不同的交通条件下进行
了仿真,并利用交通仿真软件PARAMICS进行了可视化仿真。仿真结果表明该
方法能有效降低通行车辆在交叉口的平均等待时间,明显优于传统控制方法-After analyzing the city-traffic developments,the grade crossings control theory
its method of evaluation,the paper designs a traffic signal two-stage fuzzy control
tem for single intersection.Two-stage fuzzy controller,which is easy to acquire
zy rules and can greatly decrease the number of fuzzy rules,is very suitable to
plex urban intersection control.But it still presents a difficulty for deciding all the
bership functions correctly only by human experience.Therefor,to solve this
blem,a technique using genetic algorithm to modify its fuzzy membership
ctions is proposed.This method not only possesses the advantages of hierarchical
zy control,but also can change its membership functions adaptively to an optimal
ing in different traffic situations as well,and in this way the currency power of the
an intersection is improved.For a single urban intersection with four-phase,
ulation of different traffic condition is processed by using MATLAB.Moreover,
ble simulation is proce Platform: |
Size: 312320 |
Author:刚子 |
Hits:
Description: Design of a graphical interface for NS-2
Study of sensors networks with Ad-hoc support
Implementation of Fuzzy controller inside Queue objects
Implementation of Genetic Routing inside NS-2 Platform: |
Size: 287744 |
Author:hassan |
Hits:
Description: :针对能够采用仿射非线性表示的含有未建模动态的SISO非线性系统,讨论了一种基于神经网络的自适应
控制方法.该方法对受控对象的已知部分.采用反馈线性化方法设计控制器,用神经网络在线补偿未建模动态及
外部干扰等引起的误差,从而实现自适应控制。对具有未建模动态的双车倒立摆设计了输出反馈自适应控制系
统.仿真表明该方法是有效的。 -A discussion is devoted to design neural network adaptive control scheme of the SISO (single
input and single output)nonlinear system with unmodeled dynamics.According to the known part of
the plant.feedback Iinearization method iS used to design the controller.The error resulted from the un~
modeled dynamics and the external disturbance is compensated by online neural network.The neural
networks are designed as a five layer fuzzy neural network and its construction is optimized by genetic al—
gorithms.It has been used to approtimate the nonlinear function of system and to compesate the error of
unmodeled dynamic.The design of neural network adaptive controller has better performances.The
method is verified by the digital simulation of tWO—·cart with inverted·-pendulum system and unmodeled
dynamics. Platform: |
Size: 163840 |
Author: |
Hits:
Description: 一种新的PID型模糊神经网络控制器的研究,
带Smith预估器的改进遗传算法
-A New PID-type Fuzzy Neural Network Controller based on Genetic Algorithm with improved Smith Predictor Platform: |
Size: 621568 |
Author:徐文 |
Hits: