The Experts below are selected from a list of 360 Experts worldwide ranked by ideXlab platform
A Jamali - One of the best experts on this subject based on the ideXlab platform.
-
modelling and multi objective optimization of a variable valve timing Spark Ignition engine using polynomial neural networks and evolutionary algorithms
Energy Conversion and Management, 2007Co-Authors: Kazem Atashkari, Mustafa Golcu, N Narimanzadeh, Abolfazl Khalkhali, A JamaliAbstract:Abstract The main reason for the efficiency decrease at part load conditions for four-stroke Spark-Ignition (SI) engines is the flow restriction at the cross-sectional area of the intake system. Traditionally, valve-timing has been designed to optimize operation at high engine-speed and wide open throttle conditions. Several investigations have demonstrated that improvements at part load conditions in engine performance can be accomplished if the valve-timing is variable. Controlling valve-timing can be used to improve the torque and power curve as well as to reduce fuel consumption and emissions. In this paper, a group method of data handling (GMDH) type neural network and evolutionary algorithms (EAs) are firstly used for modelling the effects of intake valve-timing (Vt) and engine speed (N) of a Spark-Ignition engine on both developed engine torque (T) and fuel consumption (Fc) using some experimentally obtained training and test data. Using such obtained polynomial neural network models, a multi-objective EA (non-dominated sorting genetic algorithm, NSGA-II) with a new diversity preserving mechanism are secondly used for Pareto based optimization of the variable valve-timing engine considering two conflicting objectives such as torque (T) and fuel consumption (Fc). The comparison results demonstrate the superiority of the GMDH type models over feedforward neural network models in terms of the statistical measures in the training data, testing data and the number of hidden neurons. Further, it is shown that some interesting and important relationships, as useful optimal design principles, involved in the performance of the variable valve-timing four-stroke Spark-Ignition engine can be discovered by the Pareto based multi-objective optimization of the polynomial models. Such important optimal principles would not have been obtained without the use of both the GMDH type neural network modelling and the multi-objective Pareto optimization approach.
-
modelling and multi objective optimization of a variable valve timing Spark Ignition engine using polynomial neural networks and evolutionary algorithms
Energy Conversion and Management, 2007Co-Authors: Kazem Atashkari, Mustafa Golcu, N Narimanzadeh, Abolfazl Khalkhali, A JamaliAbstract:The main reason for the efficiency decrease at part load conditions for four-stroke Spark-Ignition (SI) engines is the flow restriction at the cross-sectional area of the intake system. Traditionally, valve-timing has been designed to optimize operation at high engine-speed and wide open throttle conditions. Several investigations have demonstrated that improvements at part load conditions in engine performance can be accomplished if the valve-timing is variable. Controlling valve-timing can be used to improve the torque and power curve as well as to reduce fuel consumption and emissions. In this paper, a group method of data handling (GMDH) type neural network and evolutionary algorithms (EAs) are firstly used for modelling the effects of intake valve-timing (Vt) and engine speed (N) of a Spark-Ignition engine on both developed engine torque (T) and fuel consumption (Fc) using some experimentally obtained training and test data. Using such obtained polynomial neural network models, a multi-objective EA (non-dominated sorting genetic algorithm, NSGA-II) with a new diversity preserving mechanism are secondly used for Pareto based optimization of the variable valve-timing engine considering two conflicting objectives such as torque (T) and fuel consumption (Fc). The comparison results demonstrate the superiority of the GMDH type models over feedforward neural network models in terms of the statistical measures in the training data, testing data and the number of hidden neurons. Further, it is shown that some interesting and important relationships, as useful optimal design principles, involved in the performance of the variable valve-timing four-stroke Spark-Ignition engine can be discovered by the Pareto based multi-objective optimization of the polynomial models. Such important optimal principles would not have been obtained without the use of both the GMDH type neural network modelling and the multi-objective Pareto optimization approach.
A. Ramesh - One of the best experts on this subject based on the ideXlab platform.
-
Effect of swirl on the performance and combustion of a biogas fuelled Spark Ignition engine
Energy Conversion and Management, 2013Co-Authors: E. Porpatham, A. Ramesh, Bedhannan NagalingamAbstract:The influence of swirl on the performance, emissions and combustion in a constant speed Spark Ignition (SI) engine was studied experimentally. A single cylinder diesel engine was modified to operate as a biogas operated Spark Ignition engine. The engine was operated at 1500 rpm at throttle opening of 25% and 100% at various equivalence ratios. The tests covered a range of equivalence ratios from rich to lean operating limits and also at an optimum compression ratio of 13:1 with normal and masked intake valve to enhance swirl. The Spark timing was set to MBT (Minimum advance for Best Torque). It was found that masked valve configuration enhanced the power output and brake thermal efficiency at full throttle. The lean limit of combustion also got extended. Heat release rates indicated enhanced combustion rates with masked valve, which are mainly responsible for the improvement in thermal efficiency. NO level increased with masked valve as compared to normal configuration. The Spark timings were to be retarded by about 6 CA and 4 CA when compared to normal configuration at 25% and 100% throttle respectively.
-
hydrogen fueled Spark Ignition engine with electronically controlled manifold injection an experimental study
Renewable Energy, 2008Co-Authors: Hari R Ganesh, V Subramanian, A. Ramesh, J. M. Mallikarjuna, V Balasubramanian, R. P. SharmaAbstract:In this work, a single cylinder conventional Spark Ignition engine was converted to operate with hydrogen using the timed manifold fuel injection technique. A solenoid operated gas injector was used to inject hydrogen into the inlet manifold at the specified time. A dedicated electronic circuit developed for this work was used to control the injection timing and duration. The Spark timing was set to minimum advance for best torque (MBT). The engine was operated at the wide-open throttle condition. For comparison of results, the same engine was also run on gasoline.
-
effect of water injection and Spark timing on the nitric oxide emission and combustion parameters of a hydrogen fuelled Spark Ignition engine
International Journal of Hydrogen Energy, 2007Co-Authors: V Subramanian, J. M. Mallikarjuna, A. RameshAbstract:One of the main problems with hydrogen fuelled internal combustion engines is the high NO level due to rapid combustion. Use of diluents with the charge and retardation of the Spark Ignition timing can reduce NO levels in Hydrogen fuelled engines. In this work a single cylinder hydrogen fuelled engine was run at different equivalence ratios at full throttle. NO levels were found to rise after an equivalence ratio of 0.55, maximum value was about 7500 ppm. High reductions in NO emission were not possible without a significant drop in thermal efficiency with retarded Spark Ignition timings. Drastic drop in NO levels to even as low as 2490 ppm were seen with water injection. In spite of the reduction in heat release rate (HRR) no loss in brake thermal efficiency (BTE) was observed. There was no significant influence on combustion stability or HC levels.
Mustafa Golcu - One of the best experts on this subject based on the ideXlab platform.
-
modelling and multi objective optimization of a variable valve timing Spark Ignition engine using polynomial neural networks and evolutionary algorithms
Energy Conversion and Management, 2007Co-Authors: Kazem Atashkari, Mustafa Golcu, N Narimanzadeh, Abolfazl Khalkhali, A JamaliAbstract:The main reason for the efficiency decrease at part load conditions for four-stroke Spark-Ignition (SI) engines is the flow restriction at the cross-sectional area of the intake system. Traditionally, valve-timing has been designed to optimize operation at high engine-speed and wide open throttle conditions. Several investigations have demonstrated that improvements at part load conditions in engine performance can be accomplished if the valve-timing is variable. Controlling valve-timing can be used to improve the torque and power curve as well as to reduce fuel consumption and emissions. In this paper, a group method of data handling (GMDH) type neural network and evolutionary algorithms (EAs) are firstly used for modelling the effects of intake valve-timing (Vt) and engine speed (N) of a Spark-Ignition engine on both developed engine torque (T) and fuel consumption (Fc) using some experimentally obtained training and test data. Using such obtained polynomial neural network models, a multi-objective EA (non-dominated sorting genetic algorithm, NSGA-II) with a new diversity preserving mechanism are secondly used for Pareto based optimization of the variable valve-timing engine considering two conflicting objectives such as torque (T) and fuel consumption (Fc). The comparison results demonstrate the superiority of the GMDH type models over feedforward neural network models in terms of the statistical measures in the training data, testing data and the number of hidden neurons. Further, it is shown that some interesting and important relationships, as useful optimal design principles, involved in the performance of the variable valve-timing four-stroke Spark-Ignition engine can be discovered by the Pareto based multi-objective optimization of the polynomial models. Such important optimal principles would not have been obtained without the use of both the GMDH type neural network modelling and the multi-objective Pareto optimization approach.
-
modelling and multi objective optimization of a variable valve timing Spark Ignition engine using polynomial neural networks and evolutionary algorithms
Energy Conversion and Management, 2007Co-Authors: Kazem Atashkari, Mustafa Golcu, N Narimanzadeh, Abolfazl Khalkhali, A JamaliAbstract:Abstract The main reason for the efficiency decrease at part load conditions for four-stroke Spark-Ignition (SI) engines is the flow restriction at the cross-sectional area of the intake system. Traditionally, valve-timing has been designed to optimize operation at high engine-speed and wide open throttle conditions. Several investigations have demonstrated that improvements at part load conditions in engine performance can be accomplished if the valve-timing is variable. Controlling valve-timing can be used to improve the torque and power curve as well as to reduce fuel consumption and emissions. In this paper, a group method of data handling (GMDH) type neural network and evolutionary algorithms (EAs) are firstly used for modelling the effects of intake valve-timing (Vt) and engine speed (N) of a Spark-Ignition engine on both developed engine torque (T) and fuel consumption (Fc) using some experimentally obtained training and test data. Using such obtained polynomial neural network models, a multi-objective EA (non-dominated sorting genetic algorithm, NSGA-II) with a new diversity preserving mechanism are secondly used for Pareto based optimization of the variable valve-timing engine considering two conflicting objectives such as torque (T) and fuel consumption (Fc). The comparison results demonstrate the superiority of the GMDH type models over feedforward neural network models in terms of the statistical measures in the training data, testing data and the number of hidden neurons. Further, it is shown that some interesting and important relationships, as useful optimal design principles, involved in the performance of the variable valve-timing four-stroke Spark-Ignition engine can be discovered by the Pareto based multi-objective optimization of the polynomial models. Such important optimal principles would not have been obtained without the use of both the GMDH type neural network modelling and the multi-objective Pareto optimization approach.
-
artificial neural network based modeling of variable valve timing in a Spark Ignition engine
Applied Energy, 2005Co-Authors: Mustafa Golcu, Yakup Sekmen, Perihan Erduranli, Sahir M SalmanAbstract:Variable valve-timing and lift are significant operating and design parameters affecting the performance and emissions in Spark-Ignition (SI) engines. Previous investigations have demonstrated that improvements in engine performance can be accomplished if the valve timing is variable. Traditionally, valve timing has been designed to optimize operation at high engine-speed and wide-open throttle conditions. Controlling valve timing can improve the torque and power curve of a given engine. Variable valve-timing can be used to reduce fuel consumption and increase engine performance. Intake valve-opening timing was changed from 10° crankshaft angle (CA) to 30° CA for both advance and retard with 10° CA intervals to the original opening timing. In this study, artificial neural-networks (ANNs) are used to determine the effects of intake valve timing on the engine performance and fuel economy. Experimental studies were completed to obtain training and test data. Intake valve-timing and engine speed have been used as the input layer; engine torque and fuel consumption have been used as the output layer. For the torque testing data, root mean squared-error (RMSE), fraction of variance (R2) and mean absolute percentage error (MAPE) were found to be 0.9017%, 0.9920% and 7.2613%, respectively. Similarly, for the fuel consumption, RMSE, R2 and MAPE were 0.2860%, 0.9299% and 7.5448%, respectively. With these results, we believe that the ANN can be used for the prediction of engine performance as an appropriate method for Spark-Ignition (SI) engines.
Kazem Atashkari - One of the best experts on this subject based on the ideXlab platform.
-
modelling and multi objective optimization of a variable valve timing Spark Ignition engine using polynomial neural networks and evolutionary algorithms
Energy Conversion and Management, 2007Co-Authors: Kazem Atashkari, Mustafa Golcu, N Narimanzadeh, Abolfazl Khalkhali, A JamaliAbstract:Abstract The main reason for the efficiency decrease at part load conditions for four-stroke Spark-Ignition (SI) engines is the flow restriction at the cross-sectional area of the intake system. Traditionally, valve-timing has been designed to optimize operation at high engine-speed and wide open throttle conditions. Several investigations have demonstrated that improvements at part load conditions in engine performance can be accomplished if the valve-timing is variable. Controlling valve-timing can be used to improve the torque and power curve as well as to reduce fuel consumption and emissions. In this paper, a group method of data handling (GMDH) type neural network and evolutionary algorithms (EAs) are firstly used for modelling the effects of intake valve-timing (Vt) and engine speed (N) of a Spark-Ignition engine on both developed engine torque (T) and fuel consumption (Fc) using some experimentally obtained training and test data. Using such obtained polynomial neural network models, a multi-objective EA (non-dominated sorting genetic algorithm, NSGA-II) with a new diversity preserving mechanism are secondly used for Pareto based optimization of the variable valve-timing engine considering two conflicting objectives such as torque (T) and fuel consumption (Fc). The comparison results demonstrate the superiority of the GMDH type models over feedforward neural network models in terms of the statistical measures in the training data, testing data and the number of hidden neurons. Further, it is shown that some interesting and important relationships, as useful optimal design principles, involved in the performance of the variable valve-timing four-stroke Spark-Ignition engine can be discovered by the Pareto based multi-objective optimization of the polynomial models. Such important optimal principles would not have been obtained without the use of both the GMDH type neural network modelling and the multi-objective Pareto optimization approach.
-
modelling and multi objective optimization of a variable valve timing Spark Ignition engine using polynomial neural networks and evolutionary algorithms
Energy Conversion and Management, 2007Co-Authors: Kazem Atashkari, Mustafa Golcu, N Narimanzadeh, Abolfazl Khalkhali, A JamaliAbstract:The main reason for the efficiency decrease at part load conditions for four-stroke Spark-Ignition (SI) engines is the flow restriction at the cross-sectional area of the intake system. Traditionally, valve-timing has been designed to optimize operation at high engine-speed and wide open throttle conditions. Several investigations have demonstrated that improvements at part load conditions in engine performance can be accomplished if the valve-timing is variable. Controlling valve-timing can be used to improve the torque and power curve as well as to reduce fuel consumption and emissions. In this paper, a group method of data handling (GMDH) type neural network and evolutionary algorithms (EAs) are firstly used for modelling the effects of intake valve-timing (Vt) and engine speed (N) of a Spark-Ignition engine on both developed engine torque (T) and fuel consumption (Fc) using some experimentally obtained training and test data. Using such obtained polynomial neural network models, a multi-objective EA (non-dominated sorting genetic algorithm, NSGA-II) with a new diversity preserving mechanism are secondly used for Pareto based optimization of the variable valve-timing engine considering two conflicting objectives such as torque (T) and fuel consumption (Fc). The comparison results demonstrate the superiority of the GMDH type models over feedforward neural network models in terms of the statistical measures in the training data, testing data and the number of hidden neurons. Further, it is shown that some interesting and important relationships, as useful optimal design principles, involved in the performance of the variable valve-timing four-stroke Spark-Ignition engine can be discovered by the Pareto based multi-objective optimization of the polynomial models. Such important optimal principles would not have been obtained without the use of both the GMDH type neural network modelling and the multi-objective Pareto optimization approach.
Changming Gong - One of the best experts on this subject based on the ideXlab platform.
-
assessment of ultra lean burn characteristics for a stratified charge direct injection Spark Ignition methanol engine under different high compression ratios
Applied Energy, 2020Co-Authors: Changming Gong, Zilei Zhang, Jingzhen Sun, Fenghua LiuAbstract:Abstract Lean burn is one of the most important characteristics of a stratified-charge direct-injection Spark-Ignition engine. In this study, a non-uniform 10-hole × 0.30 mm spray-line distribution nozzle was chosen to achieve stratified-charge of the methanol/air mixture. The mixture formation, combustion, and emissions characteristics of a stratified-charge direct-injection Spark-Ignition methanol engine under five global equivalence ratios and three high-compression ratios were simulated to assess its ultra-lean burn characteristics. The results showed that the equivalence ratio of the stratified-charge direct-injection Spark-Ignition methanol engine for stable combustion at high compression ratio was as low as 0.20. The Ignition delay and combustion duration decreased as the compression ratio increased at high equivalence ratio, and vice versa at low equivalence ratio. The stratified-charge direct-injection Spark-Ignition methanol engine greatly reduced nitric oxide emissions under ultra-lean combustion. The unburned methanol, carbon monoxide, and soot emissions increased slowly as equivalence ratio decreased at all compression ratios and equivalence ratio >0.25. The indicated thermal efficiency decreased with decreasing compression ratio at high equivalence ratio, and vice versa at low equivalence ratio. For an equivalence ratio of 0.67, the indicated thermal efficiency at compression ratio of 14 was approximately 14.9% lower than at compression ratio of 16. However, for an equivalence ratio of 0.20, the indicated thermal efficiency at compression ratio of 14 was approximately 13.5% higher than at compression ratio of 16. The compression ratio of 14 was more favorable for the stratified-charge direct-injection Spark-Ignition methanol engine to achieve ultra-lean burn and find practical application.
-
improvement of fuel economy of a direct injection Spark Ignition methanol engine under light loads
Fuel, 2011Co-Authors: Changming Gong, Kuo Huang, Yan SuAbstract:Abstract The effects of Ignition system, compression ratio, and methanol injector configuration on the brake thermal efficiency (BTE) and combustion of a high-compression direct-injection Spark-Ignition methanol engine under light loads were investigated experimentally, and its BTE was compared with its diesel counterpart. The experimental results showed that these factors significantly affect the fuel economy under light load. The BTE of a methanol engine using a high-energy multi-Spark-Ignition system is on average 25% higher than that of one using a single-Spark-Ignition system at a brake mean effective pressures (BMEP) of 0.11–0.29 MPa and an engine speed of 1600 rpm. Decreasing the compression ratio of the methanol engine from 16:1 to 14:1 markedly increases the BTE under low loads and decreases the BTE at high loads. For the methanol engine, using an injector of a 10-hole × 0.30 mm nozzle decreases the Ignition delay and improves the fuel economy compared to when an injector of a 7-hole × 0.45 mm nozzle is used. The combustion duration using an injector of a 7-hole × 0.45 mm nozzle is much longer than that with one of a 10-hole × 0.30 mm nozzle under light loads. As a result, the BTE for a methanol engine with optimal parameters is improved by 27% compared to that for a methanol engine without optimized parameters at a BMEP of 0.17 MPa and an engine speed of 1600 rpm, but the BTE of the optimized methanol engine is 20% lower than that of its diesel counterpart under these operating conditions.
