Adaptive fine pollutant discharge control for motor vehicles tunnels under traffic state transition

Traffic flow dynamics is an important issue for implementing effective pollutant discharge control of tunnels. Longitudinal ventilation using jet fans is the most popular system for pollutant discharge control of tunnels. Nowadays, jet fans equipped with the frequency conversion technology in the tunnel can shorten the control cycle and even conduct manipulation of step-less jet speeds. The longitudinal ventilation system has considerable inertia and non-linear characteristics, which are partly resulted from traffic flow dynamics such as traffic state transition. Therefore in this study an adaptive control method based on the artificial neural-network theory is proposed to be tailored to the traffic state transition. The model is based on aerodynamic equations and takes vehicle speed and density as main system disturbances, whose value can be determined by fundamental diagram when having incomplete field traffic data. The proposed controller can also cope with the parameters and uncertainties of the time-varying model. The authors simulation results show that the adaptive control method can track the desirable system output effectively whenever the traffic condition changes gently or dramatically. The results also show that their method performs better than the common-used proportional integral derivative controller in terms of system adaptability following the traffic state transition.