摘要
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。
The chaos control of freeway mainline was studied by using variable speed limits and fuzzy-neural networks （FNN） based on subtractive clustering. Based on the tmcertainty and nonlinearity of traffic system, the thought of establishing the knowledge base of mainline chaos controller for freeway by using data mining technology was proposed. The chaos control principle of mainline variable speed limits in freeway was briefly introduced. The T-S FNN chaos controller was designed, where traffic density, upstream traffic volume and maximal Lyapunov exponent were selected as the input variables and the mainline speed upper limit was selected as the output variable of the controller. Subtractive clustering was used to determine the controller structure, including the extracting of fuzzy n.des and generating initial parameters. The radius of the clustering centers was optimized by genetic algorithm, and the parameters of the fuzzy controller were optimized by using fuzzy neural network. The simulation result indicates that order motion on freeway can be realized by using the mainline intelligent chaos controller designed by the presented method to suppress traffic jam and enhance traffic volume.
出处
《公路交通科技》
CAS
CSCD
北大核心
2012年第7期124-131,共8页
Journal of Highway and Transportation Research and Development
基金
国家自然科学基金项目(50478088)
河北省自然科学基金项目(E2011202073)
