论文部分内容阅读
研究基于减法聚类的高速公路混沌系统主线可变速度模糊神经网络控制方法。针对交通系统的不确定性和非线性,提出了通过数据挖掘技术建立高速公路主线混沌控制器知识库的思想,简介了高速公路主线可变速度混沌控制原理,设计了以密度、上游车流量和最大李雅普诺夫指数作为输入,主线速度上限值作为输出的T-S模糊神经网络混沌控制器。采用减法聚类方法确定了控制器结构,包括提取模糊规则、产生控制器初始参数。使用遗传算法对聚类半径进行了优化,并采用模糊神经网络方法对控制器参数进行了优化。仿真结果表明:采用该方法设计的高速公路主线智能混沌控制器,可保持高速公路上的有序运动,从而达到抑制交通堵塞、提高道路通行能力的目的。
Research on control method of mainline variable speed fuzzy neural network based on subtractive clustering in expressway chaotic system. Aiming at the uncertainty and nonlinearity of traffic system, the idea of establishing knowledge base of mainline chaos controller of expressway by data mining technology is introduced. The principle of variable speed chaos control of mainline of highway is introduced. Based on the theory of density, traffic flow and The maximum Lyapunov exponent is taken as input and the main line speed upper limit is taken as output TS fuzzy neural network chaos controller. The subtractive clustering method is used to determine the structure of the controller, including extracting the fuzzy rules and generating the initial parameters of the controller. The genetic algorithm is used to optimize the clustering radius, and the fuzzy neural network method is used to optimize the controller parameters. The simulation results show that the main line intelligent chaos controller designed by this method can maintain the orderly movement on expressway and achieve the goal of restraining traffic jam and improving traffic capacity.