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 wider flammability limit of lean natural gas-air mixtures offers potential for operating spark ignition engines on lean air-to-fuel ratios. However, at very lean equivalence ratios, the development of the initial flame and its subsequent propagation becomes highly sensitive to physical and chemical state of the mixture. This in turn, can adversely affect engine performance, particularly the cyclic variation in the combustion process. This paper discusses the effects of lean-burn operation on the flame development durations and the cycle-by-cycle variations in a natural gas fuel injected engine. The study was conducted on a 8-cylinder, 4.6 liter, spark-ignited engine. A data acquisition system is used to acquire 300 consecutive in-cylinder pressure cycles. A heat release model was used to estimate the initial flame development time and the rapid burn duration.