The Effect of an Active Thermal Coating on Efficiency and Emissions from a High Speed Direct Injection Diesel Engine

Papaioannou, Nick; Leach, Felix; Davy, Martin; Gilchrist, Robert

doi:10.4271/2020-01-0807

Cited by 2 publications

(3 citation statements)

References 22 publications

(40 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is also worth noting the small size of the error bars (<20 arbitrary NO x units), which highlights the accuracy of the experimental data as well as the good repeatability of the ANN model. These results are in agreement with the emissions' performance of the thermally coated piston where very small differences were observed in terms of NO x when compared to the baseline engine configuration [27]. Furthermore, the 14 input parameters to the ANN model for Configuration 1, showed very small deviation from the baseline configuration, implying that the model is exposed to conditions that are already trained for, thus resulting in the small errors observed.…”

Section: Testing the Baseline Ann Model With New Data From Different Engine Configurationssupporting

confidence: 84%

“…More specifically, different piston materials, cylinder heads, injector types, nozzle types and injection strategies were all tested using a combination of the above parameters. The experimental findings for these configurations are detailed in literature [26,27]. Table 2 shows the engine configurations that were tested in this work, along with the baseline configuration.…”

Section: Experimental Apparatusmentioning

confidence: 99%

“…It is worth noting that the piston bowl design was the same between the different configurations, as was the compression ratio, and only the piston material was altered. Configuration 1, used an aluminium piston which employed an active thermal coating as a method of improving thermal efficiency [27]. This coating allows the piston surface temperature to better follow the instantaneous in-cylinder temperature, due to a combination of low heat capacity and thermal conductivity, thus reducing the heat transferred to the piston walls.…”

Section: Experimental Apparatusmentioning

confidence: 99%

See 2 more Smart Citations

Prediction of NOx Emissions for a Range of Engine Hardware Configurations Using Artificial Neural Networks

Papaioannou

Fang

Leach

et al. 2020

ASME 2020 Internal Combustion Engine Division Fall Technical Conference

Self Cite

View full text Add to dashboard Cite

The predictive ability of artificial neural networks where a large number of experimental data are available, has been studied extensively. Studies have shown that ANN models are capable of accurately predicting NOx emissions from engines under various operating conditions and different fuel types when trained well. One of the major advantages of an ANN model is its ability to relearn when new experimental data is available, thus continuously improving its accuracy. The present work explored the potential of an ANN model to predict NOx emissions for various engine configurations outside its training envelop. This work also looked into quantifying the amount of new data required to improve the accuracy of the model when exposed to unknown conditions. The chosen ANN model was constructed using data from a high-speed direct injection diesel engine and is capable of accurate NOx emissions over a wide range of operating conditions. The optimized network utilized 14 input parameters and is using 6 neurons in a single hidden layer feed-forward neural network. Experimental data from the various engine configurations tested, were then used to predict NOx from the existing ANN model. The results indicate that when the new data are within the baseline training envelop, the ANN model is capable of accurate NOx prediction even when there are substantial changes in engine configuration such as piston material. Similar results were also observed when the injector nozzle is changed. However, the model’s performance drops significantly when new data, outside the baseline training envelop, were employed indicating that additional training is required. As such, various methods for retraining the ANN model were explored with the selected method showing the best compromise between new-data accuracy and old-data accuracy retention. The retrained ANN model developed was found to be an effective tool in predicting NOx emissions for different engine configurations and operating conditions.

show abstract

Section: Testing the Baseline Ann Model With New Data From Different Engine Configurationssupporting

confidence: 84%

Section: Experimental Apparatusmentioning

confidence: 99%

Section: Experimental Apparatusmentioning

confidence: 99%

See 1 more Smart Citation