Development and validation of a GEP model to predict the performance and exhaust emission parameters of a CRDI assisted single cylinder diesel engine coupled with EGR. (15th February 2015)

• Record Type: Journal Article
• Authors: Roy, Sumit; Ghosh, Ashmita; Das, Ajoy Kumar; Banerjee, Rahul
• Is Part Of: Applied energy. Volume 140(2015:Feb. 15)
• Page Start: 52
• Page End: 64
• Publication Date: 2015-02-15
• Subjects: ANN Artificial Neural Network -- BDO baseline diesel operation -- BP brake power -- BSFC brake specific fuel consumption -- BTDC before top dead centre -- BTE brake thermal efficiency -- CO2 carbon-di-oxide -- CI compression ignition -- CRDI common rail diesel injection -- DI direct injection -- EGR Exhaust Gas Recirculation -- ETs Expression Trees -- FIP fuel injection pressure -- GA genetic algorithm -- GEP Gene Expression Programming -- GP Genetic Programming -- IC internal combustion -- MAPE Mean Absolute Percentage Error -- MSE Mean Square Error -- NOx oxides of nitrogen -- PM particulate matter -- ppm parts per million -- R correlation coefficient -- RMSE Root Mean Square Error; Gene Expression Programming -- Artificial Neural Network -- CRDI -- EGR -- Engine performance -- Exhaust emissions; Power (Mechanics) -- Periodicals; Energy conservation -- Periodicals; Energy conversion -- Periodicals; 621.042
• DOI: 10.1016/j.apenergy.2014.11.065
• Languages: English
• ISSNs: 0306-2619

Abstract

Graphical abstract: Highlights: CRDI/high pressure fuel injection reduces PM and BSFC with the penalty of increase in NOx emissions. EGR operation at lowest injection duration case of CRDI operation reduces NOx. GEP modelling of BSFC, BTE, CO2, NOx and PM. Gene Expression Programming is capable in predicting performance and emission parameters of the experimental engine. GEP performed better when compared with ANN. Abstract: Gene Expression Programming was employed to express the relationship between the inputs and the outputs of a single cylinder four-stroke CRDI engine coupled with EGR. The performance and emission parameters (BSFC, BTE, CO2, NOx and PM) have been modelled by Gene Expression Programming where load, fuel injection pressure, EGR and fuel injected per cycle were chosen as input parameters. From the results it was found that the GEP can consistently emulate actual engine performance and emission characteristics proficiently even under different modes of CRDI operation with EGR with significant accuracy. Moreover, the GEP obtained results were also compared with an ANN model, developed on the same parametric ranges. The comparison of the obtained results showed that the GEP model outperforms the ANN model in predicting the desired response variables.