城市交叉口短时交通流预测模型与算法研究-交通运输规划与管理专业论文.docxVIP

最后，针对无检测器交叉口交通流的预测问题，通过建立无检测器交叉口与有检测 器交叉口之间的联系，从而利用有检测器交叉口流量来进行预测的角度出发。第一，介 绍了常用的几类归类方法，引入了基于贝叶斯最小风险准则的 PNN 概率神经网络这一 概念，并首次将其应用在无检测器交叉口与有检测器交叉口的归类中，提出了基于 PNN 概率神经网络的交叉口分类模式的预测方法。第二，介绍了归类后的预测手段，即有线 性回归和非线性拟合，并引出了 BP 神经网络和遗传 GA 优化后的 BP 神经网络的两类 非线性拟合思路。建立了有检测器交叉口和无检测器交叉口动态联系，实现无检测器 交叉口在时间空间上的归类与短时交通流量数据的预测，并以安宁区区域路网部分交 叉口为例，验证了模型和算法的可行性。 关键词：短时交通流预测；时空依赖性；城市交叉口；组合预测模型；PNN 分类模式预 测模型 论文类型：应用研究 II - Abstract City traffic problem has already been upgrated to the biggest constraints for the sustainable debelopment of city. Intellingent transportation system (ITS) is the important method to solve this problem. The real-time accurate forecast traffic information is the basis and the key of dynamic route guidance system. However, intersection is the throat of road network traffic capacity, the locations of traffic jams and accidents, so the prection of the intersections’ traffic flow appears incereasingly important. At present, the traffic flow guidance control time span become shorter, strengthen the randomness, chaos, nonlinear and uncertainty of traffic flow. Lead to early detector intersectinons of short-term traffic flow prediction model usually cannot reflect the uncertainty and the nonlinear of traiic flow, also cannot overcome the influence of random disturbance factors on the traffic flow, forecast effect is not ideal; In most cities the number of detector intersection is amounted to less than one over ten of the whole intersection, so that non detector intersection traffic flow information is difficult to obtain, all of these have brought greater difficulty to traffic control and guidance, also makes real-time and accurate short-term traffic flow forecasting of the two kinds of intersections is becoming more urgent. In this paper, firstly, analysed and studied the domestic and foreign scholars have published the current situation, the future development trend and existing problems about the two kinds of intersections’ short-term traffic flow forecasting. Summarized