Search Results

In this work Artificial Neural Networks (ANN) technique has been used to predict NOx emissions and Indicated Thermal Efficiency (ITE) for a direct injection Hydrogen engine, which is equipped with water direct injection system for NOx control. ANN has been used as a mathematical tool that learns from the experimental data obtained under different operating conditions. Feed forward multilayer perception network is used for nonlinear mapping between the input and output parameters. Different backpropagation training algorithms, activation functions and several rules are used to assess the percentage error between the target and the predicted values. As good correlations between measured and predicted NOx emissions and engine ITE are obtained, a step further using the ANN as an optimization tool has been performed.

The present work examines experimentally the effect of different direct water injection strategies on NOx emissions and performance in a direct injection hydrogen fueled engine. Three water injection strategies were considered including; injection at the suction, compression and expansion strokes. Both injection timing as well as quantity were varied for each strategy. The water injection configuration relative to the spark plug has been also evaluated. The results showed that water injection during expansion stroke has a minor effect on NOx emissions, which has been already formed. Noticeable effect could be achieved when water is injected at the later stages of the compression stroke. Reduction of NOx emissions is strongly dependent on the injection timing as well as quantity of the injected water. Optimum injection timing, for maximum NOx reduction, advances with the increase of the quantity of water being injected.