Search Results

The emerging Variable Valve Timing (VVT) technology complicates the estimation of air flow rate because both intake and exhaust valve timings significantly affect engine's gas exchange and air flow rate. In this paper, we propose to use Artificial Neural Networks (ANN) to model the air flow rate through a 2.4 liter VVT engine with independent intake and exhaust camshaft phasers. The procedure for selecting the network architecture and size is combined with the appropriate training methodology to maximize accuracy and prevent overfitting. After completing the ANN training based on a large set of dynamometer test data, the multi-layer feedforward network demonstrates the ability to represent air flow rate accurately over a wide range of operating conditions. The ANN model is implemented in a vehicle with the same 2.4 L engine using a Rapid Prototype Controller.

A comprehensive model for sprays emerging from high-pressure swirl injectors in DISI engines has been developed accounting for both primary and secondary atomization. The model considers the transient behavior of the pre-spray and the steady-state behavior of the main spray. The pre-spray modeling is based on an empirical solid cone approach with varying cone angle. The main spray modeling is based on the Liquid Instability Sheet Atomization (LISA) approach, which is extended here to include the effects of swirl. Mie Scattering, LIF, PIV and Laser Droplet Size Analyzer techniques have been used to produce a set of experimental data for model validation. Both qualitative comparisons of the evolution of the spray structure, as well as quantitative comparisons of spray tip penetration and droplet sizes have been made. It is concluded that the model compares favorably with data under atmospheric conditions.

Wall wetting of injected fuel onto the intake manifold and cylinder wall causes unpredictable transient behavior of air-fuel mixing which results in a significant emission of unburned hydrocarbon (HC) emission during cold start operation. Heated exhaust gas oxygen (HEGO) sensors cannot measure the air-fuel ratio (A/F) of exhaust gas during cold start condition. Precise and fast estimation of air/fuel ratio of the exhaust gas is required to elucidate the wall wetting phenomena and subsequent HC formation. Refined A/F estimation can enable the control of fuel injection minimizing HC emissions during cold start conditions so that HC emissions can be minimized. A new estimator for A/F of the exhaust gas has been developed. The A/F estimator described in this study utilizes measured exhaust gas temperature and general engine parameters such as engine speed, airflow, coolant temperature, etc.