Highway Speed Limit Control, Ramp Control Study

With the rapid development of social economy and the prevalence of cars, freeway traffic congestion has become serious social problems that puzzle the governments around the world. In order to effectively solve the problems of freeway traffic, it is necessary to build more roads. On the other hand, it is needed to regulate and control traffic volume properly, and to make traffic flow move in order. Speed limit control and on-ramp control are considered as two important components of freeway traffic control. For the drawbacks of traditional traffic control techniques, intelligent control is applied to freeway traffic in this paper. Several intelligent methods of speed limit control and on-ramp control have been studied in detail. The main contribution can be stated as follows:1. The neural network model for speed limit of traffic flow is built. The control for speed limit is of great importance in the freeway traffic control. In order to improve the control accuracy of speed limit, a modeling method of Elman neural network is put forward. The principle of Elman network is formulated and the Elman network model for speed limit of traffic flow is built based on such information as the number of vehicles on the freeway, the performance of the road surface, and the weather conditions. The node numbers of the input layer, context layer, hidden layer and output layer of the Elman network are selected as 2, 12, 12 and 1 respectively. Levenberg-Marquardt algorithm is used to train the network, and the simulation is carried out in contrast to the RBF network. Simulation results show that the training errors for the Elman network and the RBF network are 9.99769×10-9 and 2.38112×10-4 respectively. Compared with the RBF network, the Elman network has stronger adaptation and better generalization ability, and can build speed limit model more accurately. It is found to be potentially applicable in practice.2. The genetic algorithm is used to optimize the PI controller for freeway ramp metering. First the optimization procedures with genetic algorithm are given, and the objective of ramp metering is formulated. Then the freeway traffic flow model is built, and the parameters of an on-ramp PI controller are optimized with genetic algorithm. Simulation results show that the optimization method is of high performance. It is very effective to freeway ramp metering3. In conjunction with the advantages of fuzzy logic in processing language information and PI control in processing error, a fuzzy-PI mix controller is designed for freeway ramp metering, and genetic algorithm is used to optimize the PI parameters. Density error and error variation are chosen as the input variables of fuzzy controller, and triangle curves are used for the membership functions of the fuzzy variables. Nine fuzzy control rules are also established. Simulation results show that the mix controller has better dynamic and steady-state performance compared with PI controller, and can achieve a desired traffic density along the mainline of a freeway.