The paper presents the results of the experimental research which was carried out on the spark ignition engine, experimental model, fuelled with hydrogen by direct injection method, using qualitative load adjustment m...The paper presents the results of the experimental research which was carried out on the spark ignition engine, experimental model, fuelled with hydrogen by direct injection method, using qualitative load adjustment method for engine running control. Also, the hydrogen injection solution at the beginning of the compression stroke, after the inlet valve closing, assures the cylinder cooling by inlet air avoiding in that way uncontrolled ignition phenomena and inlet back fire. Using this fueling method avoided the abnormally hydrogen combustion phenomena＇s for stoichiometric dosage operating conditions, achieving -30 % engine power increase. Hydrogen engine runs with very lean mixtures, due to engine load qualitative adjustment, a dosage value that leads to a reduction of the engine power with -25% from maximum power value. This provides a higher engine efficiency at low loads, the best results was obtained for λ=2- 4 air-fuel ratio values. The influence of the mixture quality on burning process, on polluting and energetically engine performances at the fuelling with hydrogen using direct injection method are presented. Because of the higher combustion temperature, the NOx emission level is higher for λ=1 - 2 comparative to gasoline fuelled engine, but decreases a lot for leaner mixture values, λ〉2.5.展开更多
This article presents an Artificial Neural Network （ANN） architecture to model the Electrical Discharge Machining （EDM） process. It is aimed to develop the ANN model using an input-output pattern of raw data colle...This article presents an Artificial Neural Network （ANN） architecture to model the Electrical Discharge Machining （EDM） process. It is aimed to develop the ANN model using an input-output pattern of raw data collected from an experimental of EDM process, whereas several research objectives have been outlined such as experimenting machining material for selected gap current, identifying machining parameters for ANN variables and selecting appropriate size of data selection. The experimental data （input variables） of copper-electrode and steel-workpiece is based on a selected gap current where pulse on time, pulse off time and sparking frequency have been chosen at optimum value of Material Removal Rate （MRR）. In this paper, the result has significantly demonstrated that the ANN model is capable of predicting the MRR with low percentage prediction error when compared with the experimental result.展开更多
文摘The paper presents the results of the experimental research which was carried out on the spark ignition engine, experimental model, fuelled with hydrogen by direct injection method, using qualitative load adjustment method for engine running control. Also, the hydrogen injection solution at the beginning of the compression stroke, after the inlet valve closing, assures the cylinder cooling by inlet air avoiding in that way uncontrolled ignition phenomena and inlet back fire. Using this fueling method avoided the abnormally hydrogen combustion phenomena＇s for stoichiometric dosage operating conditions, achieving -30 % engine power increase. Hydrogen engine runs with very lean mixtures, due to engine load qualitative adjustment, a dosage value that leads to a reduction of the engine power with -25% from maximum power value. This provides a higher engine efficiency at low loads, the best results was obtained for λ=2- 4 air-fuel ratio values. The influence of the mixture quality on burning process, on polluting and energetically engine performances at the fuelling with hydrogen using direct injection method are presented. Because of the higher combustion temperature, the NOx emission level is higher for λ=1 - 2 comparative to gasoline fuelled engine, but decreases a lot for leaner mixture values, λ〉2.5.
文摘This article presents an Artificial Neural Network （ANN） architecture to model the Electrical Discharge Machining （EDM） process. It is aimed to develop the ANN model using an input-output pattern of raw data collected from an experimental of EDM process, whereas several research objectives have been outlined such as experimenting machining material for selected gap current, identifying machining parameters for ANN variables and selecting appropriate size of data selection. The experimental data （input variables） of copper-electrode and steel-workpiece is based on a selected gap current where pulse on time, pulse off time and sparking frequency have been chosen at optimum value of Material Removal Rate （MRR）. In this paper, the result has significantly demonstrated that the ANN model is capable of predicting the MRR with low percentage prediction error when compared with the experimental result.
