Skip to Main Content
This research is distinctive in terms of using a Recurrent Neuro-Fuzzy Network (RNFN) structure as an intelligent approach for fuel injection control of Spark Ignition (SI) Engines. This control problem is very sensitive because the dynamics of intake manifold air-fuel flow is severely nonlinear and multivariable. To reasonably handle such a complicated control problem, a precise experimental test has been done on a real Compressed Natural Gas (CNG) fuelled vehicle and the process input output data have been collected by running the vehicle in transient conditions. Using both process knowledge and process input output data, the nonlinear dynamics of air to fuel ratio (AFR) of CNG engine has been modeled by a RNFN estimator. Then a predictive RNFN controller has been designed based on nonlinear inverse dynamics of AFR. This control strategy has the advantage that control actions can be calculated analytically avoiding the costly and time-consuming calibration efforts required in conventional fuel injection control strategies. The results show that the response of controller is match to the measured fuel injection commands produced by the electronic control unit (ECU). This evaluated and validated the efficiency of controller. Furthermore, place the controller in a closed loop with the proposed intelligent model shows a similarity in results, in comparison with the performance of real fuel injection system and ECU in the real-time conditions.