scholarly journals Prediction ofNOxEmissions from a Direct Injection Diesel Engine Using Artificial Neural Network

2012 ◽  
Vol 2012 ◽  
pp. 1-8 ◽  
Author(s):  
J. Mohammadhassani ◽  
Sh. Khalilarya ◽  
M. Solimanpur ◽  
A. Dadvand
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Diesel Engine ◽  
Fuel Injection ◽  
Error Function ◽  
Direct Injection ◽  
Direct Injection Diesel Engine ◽  
Air Temperatures ◽  
Test Engine ◽  
Artificial Neural

In the present study, artificial neural network is used to model the relationship between NOxemissions and operating parameters of a direct injection diesel engine. To provide data for training and testing the network, a 6-inline-cylinder, four-stroke, diesel test engine is used and tested for various engine speeds, mass fuel injection rates, and intake air temperatures. 80% of a total of 144 obtained experimental data is employed for training process. In addition, 10% of the data (randomly selected) is used for network validation and the remaining data is employed for testing the accuracy of the network. The mean square error function is used for evaluating the performance of the network. The results show that the artificial neural network can efficiently be used to predict NOxemissions from the tested engine with about 10% error.

Computational optimization of reactivity controlled compression ignition combustion to achieve high efficiency and clean combustion

2020 ◽  
pp. 146808742093173 ◽  
Author(s):  
Avilash Jain ◽  
Anand Krishnasamy ◽  
Pradeep V
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Fuel Injection ◽  
Direct Injection ◽  
Network Models ◽  
Compression Ignition ◽  
Neural Network Models ◽  
Reactivity Controlled Compression Ignition ◽  
Artificial Neural ◽  
Artificial Neural Network Models

One of the major limitations of reactivity controlled compression ignition is higher unburned hydrocarbon and carbon monoxide emissions and lower thermal efficiency at part load operating conditions. In the present study, a combined numerical approach using a commercial three-dimensional computational fluid dynamics code CONVERGE along with artificial neural network and genetic algorithm is presented to address the above limitation. A production light-duty diesel engine is modified to run in reactivity controlled compression ignition by replacing an existing mechanical fuel injection system with a flexible electronic port fuel injection and common rail direct injection systems. The injection schedules of port fuel injection and direct injection injectors are controlled using National Instruments port and direct injection driver modules. Upon validation of combustion and emission parameters, parametric investigations are carried out to establish the effects of direct-injected diesel fuel timing start of injection (SOI), premixed fuel ratio and intake charge temperature on the engine performance and emissions in reactivity controlled compression ignition. The results obtained show that the start of injection timing and intake charge temperature significantly influence combustion phasing, while the premixed fuel ratio controls mixture reactivity and combustion quality. By utilizing the data generated with the validated computational fluid dynamics models, the artificial neural network models are trained to predict the engine exhaust emissions and efficiency. The artificial neural network models for gross indicated efficiency and oxides of nitrogen (NOx) are then coupled with genetic algorithm to maximize gross indicated efficiency while keeping the NOx and soot emissions within Euro VI emission limits. By optimizing the start of injection timing, premixed fuel ratio and intake charge temperature simultaneously using the artificial neural network models coupled with genetic algorithm, 19% improvement in gross indicated efficiency, 60% and 64% reduction in hydrocarbon and carbon monoxide emissions, respectively, are obtained in reactivity controlled compression ignition compared to the baseline case.

Explorative Investigation on Cashew Nut Shell Liquid Biodiesel blended with Ethanol and Hydrogen in Direct Injection (DI) Diesel Engine and prediction through Artificial Neural Network

2021 ◽  
Author(s):  
Thanigaivelan V ◽  
Lavanya R
Keyword(s):  
Diesel Engine ◽  
Diesel Fuel ◽  
Direct Injection ◽  
Cashew Nut Shell Liquid ◽  
Single Cylinder ◽  
Direct Injection Diesel Engine ◽  
Cashew Nut ◽  
Di Diesel Engine ◽  
Artificial Neural ◽  
Cashew Nut Shell

Abstract Emission from the DI diesel engine is series setback for environment viewpoint. Intended for that investigates for alternative biofuel is persuaded. The important hitches with the utilization of biofuels and their blends in DI diesel engines are higher emanations and inferior brake-thermal efficiency as associated to sole diesel fuel. In this effort, Cashew nut shell liquid (CNSL) biodiesel, hydrogen and ethanol (BHE) mixtures remained verified in a direct-injection diesel engine with single cylinder to examine the performance and discharge features of the engine. The ethanol remained supplemented 5%, 10% and 15% correspondingly through enhanced CNSL as well as hydrogen functioned twin fuel engine. The experiments done in a direct injection diesel engine with single-cylinder at steadystate conditions above the persistent RPM (1500RPM). Throughout the experiment, emissions of pollutants such as fuel consumption rate (SFC), hydrocarbons (HC), carbon monoxide (CO), nitrogen oxides (NOx) and pressure of the fuel were also measured. cylinders. The experimental results show that, compared to diesel fuel, the braking heat of the biodiesel mixture is reduced by 26.79-24% and the BSFC diminutions with growing addition of ethanol from the CNSL hydrogen mixture. The BTE upsurges thru a rise in ethanol proportion with CNSL hydrogen mixtures. Finally, the optimum combination of ethanol with CNSL hydrogen blends led to the reduced levels of HC and CO emissions with trivial upsurge in exhaust gas temperature and NOx emissions. This paper reconnoiters the routine of artificial neural networks (ANN) to envisage recital, ignition and discharges effect.

Artificial Neural Network Learning of Nonstationary Behavior in Time Series

2003 ◽  
Vol 13 (02) ◽  
pp. 103-109 ◽  
Author(s):  
María I. Széliga ◽  
Pablo F. Verdes ◽  
Pablo M. Granitto ◽  
H. Alejandro Ceccatto
Keyword(s):  
Neural Network ◽  
Time Series ◽  
Artificial Neural Network ◽  
Error Function ◽  
Input Parameter ◽  
Input Unit ◽  
Validation Data ◽  
Neural Network Learning ◽  
Secular Evolution ◽  
Artificial Neural

We refine and complement a previously-proposed artificial neural network method for learning hidden signals forcing nonstationary behavior in time series. The method adds an extra input unit to the network and feeds it with the proposed profile for the unknown perturbing signal. The correct time evolution of this new input parameter is learned simultaneously with the intrinsic stationary dynamics underlying the series, which is accomplished by minimizing a suitably-defined error function for the training process. We incorporate here the use of validation data, held out from the training set, to accurately determine the optimal value of a hyperparameter required by the method. Furthermore, we evaluate this algorithm in a controlled situation and show that it outperforms other existing methods in the literature. Finally, we discuss a preliminary application to the real-world sunspot time series and link the obtained hidden perturbing signal to the secular evolution of the solar magnetic field.

Sign in / Sign up

Export Citation Format

Share Document