Ehsan Azimirad - Department of electrical and computer engineering,Tarbiat Moallem University of Sabzevar, Sabzevar, Iran
Javad Haddadnia - Department of electrical and computer engineering,Tarbiat Moallem University of Sabzevar, Sabzevar, Iran

This paper presents a novel expert system in multilane urban traffic network by fuzzy logic. The modeling and controling of isolated signalized intersection is done by fuzzy sets theory. The controller is developed based on the waiting time and vehicles queue length at current green phase, and vehicles queue lengths at the other phases. The controller controls the traffic light timings and phase sequence to ensure smooth flow of traffic with minimal waiting time and queue length. Usually fuzzy traffic controllers are optimized to maximize traffic flows/minimize traffic waiting time under typical traffic conditions. Consequentially, these are not the optimal traffic controllers under exceptional traffic cases such as roadblocks and road accidents. In this research, we apply State-space equations to formulate the average waiting time vehicles in traffic network at fixed time control and propose a novel expert system by fuzzy modeling and new fuzzy traffic controller that can optimally control traffic flows under both normal and exceptional traffic conditions. In the end, by comparing the experimental result obtained by the Fixed-time Controller and Fuzzy Traffic Controller which improves significant performance for proposed fuzzy expert system, we confirmed the efficiency of our intelligent controller based fuzzy inference system.

expert system, fuzzy model, state-space equations, fuzzy traffic controller