No abstract

Abstract-Fuel injection system is a promising technology that enhances positively the fuel economy, engine performances and emission reduction, as compared to the conventional carburetor system. Currently, motorcycles using carburetor system are widely used as a mean of transportation especially in urban areas. This conventional fuelling system produces more harmful emissions and consumes more fuel compared to the fuel injection system. It is therefore desirable to have a fuel injection system that can easily be retrofitted to the current on-road motorcycles. This paper presents a review and comparative study using 1-D simulation software -GT-Power, on electronic fuel injection (EFI) system between port-fuel injection (PFI) and direct injection (GDI) system for retrofitment purpose of small 125cc 4-stroke gasoline engine. From this study, PFI system has been selected based on its high brake power, brake torque, and brake mean effective pressure with low brake specific fuel consumption.Index Terms-Fuel injection system, retrofitment, small gasoline engine.

Most motorcycles in developing countries use carburetor systems as the fuel delivery method especially for models with the cubic capacity of less than 125cc. However, small gasoline fuelled engines operating using carburetor system suffer from low operating efficiency, waste of fuel and produce higher level of hazardous emissions to the environment. In this study, an electronic control unit (ECU) is designed and simulated for a retrofit fuel injection (FIS) system. The ECU is targeted to have a simple design, reliable and offers all of the necessary functions of the modern ECU. The simulation results shows that the designed ECU can determine the injection period as close to the proposed value and can drive the injector efficiently based on the generated PWM pulse.

In a modern small gasoline engine fuel injection system, the load of the engine is estimated based on the measurement of the manifold absolute pressure (MAP) sensor, which took place in the intake manifold. This paper present a more economical approach on estimating the MAP by using only the measurements of the throttle position and engine speed, resulting in lower implementation cost. The estimation was done via two-stage multilayer feed-forward neural network by combining Levenberg-Marquardt (LM) algorithm, Bayesian Regularization (BR) algorithm and Particle Swarm Optimization (PSO) algorithm. Based on the results found in 20 runs, the second variant of the hybrid algorithm yields a better network performance than the first variant of hybrid algorithm, LM, LM with BR and PSO by estimating the MAP closely to the simulated MAP values. By using a valid experimental training data, the estimator network that trained with the second variant of the hybrid algorithm showed the best performance among other algorithms when used in an actual retrofit fuel injection system (RFIS). The performance of the estimator was also validated in steady-state and transient condition by showing a closer MAP estimation to the actual value.