The increasing demands for fuel economy and emission reduction have led to the development of lean/diluted combustion strategies for modern Spark Ignition(SI)engines.The new generation of SI engines requires higher sp...The increasing demands for fuel economy and emission reduction have led to the development of lean/diluted combustion strategies for modern Spark Ignition(SI)engines.The new generation of SI engines requires higher spark energy and a longer discharge duration to improve efficiency and reduce the backpressure.However,the increased spark energy gives negative impacts on the ignition system which results in deterioration of the spark plug.Therefore,a numerical model was used to estimate the spark energy of the ignition system based on the breakdown voltage.The trend of spark energy is then recognized by implementing the classification method.Significant features were identified from the Information Gain(IG)scoring of the statistical analysis.k-Nearest Neighbor(KNN),Artificial Neural Network(ANN),and SupportVector Machine(SVM)models were studied to identify the best classifier for the classification stage.For all classifiers,the entire featured dataset was randomly divided into standardized parameter values of training and testing data sets with the ratio of 70-30 for each class.It was shown in the study that the KNN classifier acquired the highest Classification Accuracy(CA)of 94.1%compared to ANN and SVM that score 77.3%and 87.9%on the test data,respectively.展开更多
Based on the principle of thermal conduction, three metal alloys （stainless steel, copper-tungsten and graphite） were chosen as the material of the high impulse current discharging switch. Experimental results indic...Based on the principle of thermal conduction, three metal alloys （stainless steel, copper-tungsten and graphite） were chosen as the material of the high impulse current discharging switch. Experimental results indicate that the mass loss and surface erosion morphology of the electrode are related with the electrode material （conductivity σ, melting point Tin, density p and thermal capacity c） and the impulse transferred charge （or energy） per impulse for the same total impulse transferred charge. The experimental results indicate that the mass loss of stainless steel, copper-tungsten and graphite are 380.10 μg/C, 118.10 μg/C and 81.90 μg/C respectively under the condition of a total impulse transferred charge of 525 C and a transferred charge per impulse of 10.5 C. Under the same impulse transferred charge, the mass loss of copper-tungsten（118.10 μg/C） with the transferred charge per impulse at 10.5 C is far larger than the mass loss （38.61μg/C） at a 1.48 C transferred charge per impulse. The electrode erosion mechanism under high energy impulse arcs is analyzed briefly and it is suggested that by selecting high conductive metal or metal alloy as the electrode material of a high energy impulse spark gap switch and setting high erosion resistance material at the top of the electrode, the mass loss of the electrode can be reduced and the life of the switch prolonged.展开更多
基金The authors would like to express their gratitude to the sponsorship by Universiti Malaysia Pahang under Research University Grants RDU1903101 and PGRS2003142 for laboratory facilities and financial aid.
文摘The increasing demands for fuel economy and emission reduction have led to the development of lean/diluted combustion strategies for modern Spark Ignition(SI)engines.The new generation of SI engines requires higher spark energy and a longer discharge duration to improve efficiency and reduce the backpressure.However,the increased spark energy gives negative impacts on the ignition system which results in deterioration of the spark plug.Therefore,a numerical model was used to estimate the spark energy of the ignition system based on the breakdown voltage.The trend of spark energy is then recognized by implementing the classification method.Significant features were identified from the Information Gain(IG)scoring of the statistical analysis.k-Nearest Neighbor(KNN),Artificial Neural Network(ANN),and SupportVector Machine(SVM)models were studied to identify the best classifier for the classification stage.For all classifiers,the entire featured dataset was randomly divided into standardized parameter values of training and testing data sets with the ratio of 70-30 for each class.It was shown in the study that the KNN classifier acquired the highest Classification Accuracy(CA)of 94.1%compared to ANN and SVM that score 77.3%and 87.9%on the test data,respectively.
文摘Based on the principle of thermal conduction, three metal alloys （stainless steel, copper-tungsten and graphite） were chosen as the material of the high impulse current discharging switch. Experimental results indicate that the mass loss and surface erosion morphology of the electrode are related with the electrode material （conductivity σ, melting point Tin, density p and thermal capacity c） and the impulse transferred charge （or energy） per impulse for the same total impulse transferred charge. The experimental results indicate that the mass loss of stainless steel, copper-tungsten and graphite are 380.10 μg/C, 118.10 μg/C and 81.90 μg/C respectively under the condition of a total impulse transferred charge of 525 C and a transferred charge per impulse of 10.5 C. Under the same impulse transferred charge, the mass loss of copper-tungsten（118.10 μg/C） with the transferred charge per impulse at 10.5 C is far larger than the mass loss （38.61μg/C） at a 1.48 C transferred charge per impulse. The electrode erosion mechanism under high energy impulse arcs is analyzed briefly and it is suggested that by selecting high conductive metal or metal alloy as the electrode material of a high energy impulse spark gap switch and setting high erosion resistance material at the top of the electrode, the mass loss of the electrode can be reduced and the life of the switch prolonged.
