Based On Rough Set Neural Network Model Of Traffic Flow And Ramp Control

Freeway traffic control is considered as an important component of intelligent transportation system, while the control of on-ramp is the most extensive expressway strategy. The on-ramps include isolated control and coordinated control according to their correlation. A research on intelligent freeway on-ramp metering approaches and the model of highway traffic flow was conducted according to some characteristics of the freeway traffic state. The main contents and results are as follows:1. Rough set is a powerful mathematics tool, which can deal with fuzzy and uncertain knowledge, and neural network has the ability to approach any nonlinear function precisely. A dynamic modeling method is presented using the rough sets and Elman network integrated technology for complex system. The method is applied to build the freeway traffic flow model. The simulation results prove the validity of this method.2. A proportional-integral control method based on particle swarm optimization (PSO) is proposed to regulate the number of vehicles entering a freeway entrance point. First, the objective of ramp metering is determined, and the freeway traffic flow model is built. Then the particle swarm algorithm is formulated. In conjunction with nonlinear feedback theory, PSO based PI controller for on-ramp metering is designed. Finally, the controller is simulated in MATLAB software. The result shows that the controller designed has fast response, and good dynamic and steady-state performance. This method has a good effect on freeway ramp metering.3. The composition control method based on cerebella model articulation controller (CMAC) and PID controller is proposed to regulate the number of vehicles entering a freeway entrance point. The algorithm of the composition controller of CMAC and PID is formulated. In conjunction with nonlinear feedback theory, the on-ramp metering rate of a freeway is determined by using the composition controller. Finally, the control system is simulated in MATLAB software and fuzzy logic controller is also chosen in contrast to the composition controller. The result shows that the composition controller improves evidently on the aspects of response speed and dynamic performance. It can achieve a desired traffic density along the mainline of a freeway, and can make vehicles travel more efficiently and safely. This method provides a novel and practical way to realize freeway on-ramp metering.4. A parameter adjustment method of PID controller with BP neural network is developed and applied to freeway on-ramp metering. The learning algorithm of BP neural network for adjusting the proportional, integral and differential coefficients is formulated in detail. Based on the traffic flow model and in conjunction with nonlinear feedback theory, an on-ramp PID controller regulated by BP neural network is designed. According to real-time traffic status, BP neural network is used to adjust the PID parameters dynamically in order to minimize the performance index defined in terms of the density tracking errors. Finally, the controller is simulated in MATLAB software. The results show that the controller designed has good dynamic and steady-state performance. It can achieve a desired traffic density along the mainline of a freeway and thus avoid traffic congestion. This approach is quite effective to freeway on-ramp metering.5. A multilayer control structure and PSO algorithm are used for coordinated ramp control on freeways. The macroscopic model to describe the evolution of freeway traffic flow is built and the PSO algorithm is formulated. The control system is vertically decomposed into three layers: The adaptation layer to specify the values of disturbances and to adjust the parameters of traffic models, the coordination layer to determine the desired traffic density in each freeway section according to the current traffic state, and the direct control layer to keep the actual values of the traffic density in the vicinity of the nominal trajectories via PI control. PSO algorithm is used to find the optimal PI parameters of the direct control layer. Simulation results show that the control system is of good performance. It can eliminate traffic jams, maintain traffic flow stability, and make vehicles travel more efficiently and safely.