| Article ID | Journal | Published Year | Pages | File Type |
|---|---|---|---|---|
| 108776 | Journal of Transportation Systems Engineering and Information Technology | 2008 | 6 Pages |
On the basis of traffic flow characteristics in urban intersections, this paper presents a signal control scheme that can transform the multi-phase sequences adaptively. In this control scheme, the length of the green-light phase motorcade is compared with that of the red-light phase motorcade; it is then decides whether the phase is to be changed or not. When the green light phase does not need to be changed, a fuzzy neural network is used to control the length of the delay of green lights. This study not only takes the fuzzy control and neural network control advantageous, but also presents an algorithm in which the phase sequence is changeable. Thus, a multi-phase and phase sequence-changeable control scheme is achieved in the intersection. Simulation results show that the designed fuzzy neural network controller can reduce the average delay of vehicles effectively, and meet the demand of real-time control.
