Performance and emission prediction of a compression ignition engine fueled with biodiesel-diesel blends: A combined application of ANN and RSM based optimization

Aydın, Mustafa; Uslu, Samet; Çelik, Mustafa

doi:10.1016/j.fuel.2020.117472

Cited by 155 publications

(52 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is also possible to notice that the results in Table 2 has a greater deviation than the reference works [7][8][9][10][11], the reason for this is probably because several items can impact the result of _ : Exhaust gas flow rate to equipment; engine production of PM (surely not perfectly repeatable); engine service equipment (dyno, cooling water and fuel temperature, combustion air conditioning); power measurement (speed and torque); exhaust gas flow rate measurement (or combustion air flow rate and fuel flow rate); sampling filters conditioning chamber (temperature and humidity stability and cleanliness); micro-balance accuracy and stability, and when adding up more items like: different laboratories, different days, different measuring equipment, for sure a larger deviation will occur.…”

Section: Discussionmentioning

confidence: 86%

“…The errors observed in the random forests model are higher than the emissions prediction models built in [7][8][9][10][11]. Several reasons may have contributed to this: the references analyses were carried out in a controlled environment, the same laboratory, the same engine, tests running in sequence, while this research was performed in a wide field, three laboratories were considered, different engines, tests took place on different days.…”

Section: Discussionmentioning

confidence: 98%

“…In such context, machine learning algorithms have been the subject of several analyzes to reduce manual labor and predict parameters. In reference [7], the authors build an artificial neural networks (ANN) based on data of tests of the parameters NOx, HC, CO and smoke. The R 2 value between test and train data are 0.9771, 0.8663, 0.8917 and 0.9858 respectively.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Predição da Emissão de Particulado Utilizando Algoritmo de Aprendizagem de Máquina

Dellaroza¹,

Lodi²,

Luersen³

2021

Blucher Engineering Proceedings

View full text Add to dashboard Cite

One of the requirements of diesel engines certification process is that the engine do not exceed the specific particulate emissions limit in cycle ( _ ). To calculate the _ , a manual process is required. The total amount of mass impregnated in the particulate filter is obtained by weighting the filter on a balance after each test. Therefore, it is not possible to obtain it without human intervention. In order to allow test rigs to operate in automatic mode, without an operator conducting the tests, an automatic way of calculating _ is required. Thus, the aim of this work is to develop a _ prediction model that does not require human intervention. For this, a machine learning approach, based on the random forests algorithm, is used. Data collected from 2012 to 2019 from three test cells of 11 and 13 liters diesel engines of an automotive company, summing up 2500 valid test results, are used as input. This data are employed to train the algorithm and build a prediction model. The prediction model is then validated using another 72 validation tests results. The accuracy of the final model considering a confidence interval of 95% is ±3,00 mg/kWh for the European Transient Cycle, and ±1,96 mg/kWh for the European Stationary Cycle.

show abstract

Section: Discussionmentioning

confidence: 86%

Section: Discussionmentioning

confidence: 98%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Predição da Emissão de Particulado Utilizando Algoritmo de Aprendizagem de Máquina

Dellaroza¹,

Lodi²,

Luersen³

2021

Blucher Engineering Proceedings

View full text Add to dashboard Cite

show abstract

“…Nowadays, diesel engines are selected in many sectors due to their high economy, superior efficiency, and minimal fuel prices [1]- [3]. Diesel engines are one of the biggest consumers of fossil fuels in the world and emissions from these engines are one of the main suppliers of pollution in the environment [4]- [7].…”

Section: Introductionmentioning

confidence: 99%

Analysis of the effects of cetane improver addition to diesel on engine performance and emissions

Şimşek

Uslu

2021

International Journal of Automotive Engineering and Technologies

Self Cite

View full text Add to dashboard Cite

The high cetane number of the fuel used in diesel engines is extremely important as it provides some improvements in combustion in the cylinder. Therefore, the addition of cetane improver to diesel fuel has been highly preferred in recent years. In this study, the effects of 2-ethylhexyl nitrate (EHN) addition, a cetane improver, on compression ignition engine performance and emissions were analyzed at various engine loads. Four different fuels were used in the experiments as 100% diesel (D100), 99% diesel + 1% EHN (D99EHN1), 98% diesel + 2% EHN (D99EHN2) and 97% diesel + 3% EHN (D99EHN3). The results obtained from the experiments showed that the addition of 2-EHN positively affected the brake thermal efficiency (BTHE), hydrocarbon (HC) and carbon monoxide (CO) values, while the brake specific fuel consumption (BSFC), nitrogen oxide (NOx) and smoke emission levels were negatively affected. With high engine load, 2-EHN supplement marginally rises NOx emissions but significantly declines HC and CO emissions. EHN addition had small impacts on BSFC. Compared to D100 fuel, the highest BTHE value was obtained by D99EHN2 fuel, with an increase of 11.57% at 3000-Watt load value. With the D97EHN3 fuel, compared to diesel, HC emission decreased 60.61%, while CO emission decreased 31.25%. The results show that the 2-EHN cetane improver can be used successfully in a diesel engine.

show abstract

“…Experiment is needed to measure the suitability of a new type of fuel for use in internal combustion engines. For this reason, both the number of experiments, the time spent, and the costs of the experiment have increased considerably in recent years [25,26]. To prevent this, in other words, to reduce the number of experiments, computer applications have been developed that can simulate many more experiments using a certain number of experiment data.…”

Section: Introductionmentioning

confidence: 99%

Improving the Running Conditions of Diesel Engine with Grape Seed Oil Additives by Response Surface Design

Uslu

Yeşilyurt

2020

International Journal of Automotive Science and Technology

Self Cite

View full text Add to dashboard Cite

In this study, an optimization study was carried out by using Response Surface Methodology (RSM) to determine the optimum conditions by im-proving the working conditions in a single cylinder diesel engine using fuel blends created by mixing the biodiesel obtained from grape seed oil (GSO) to diesel in different proportions (5%, 10% and 15% by vol.). Experiments were carried out with three different fuel mixtures with three different injection pressures (200, 225 and 250 bar) at three different engine loads (400, 1000 and 1600-Watt). Since the minimum number of experiments proposed by the RSM application is 20 for optimization according to three different fac-tors and three different levels of each factor, an RSM model was created from the experiment data obtained by performing 20 trials. While the GSO ratio, the injection pressure and engine load was determined as input factors, brake specific fuel consumption (BSFC), exhaust gas temperature (EGT), carbon monoxide (CO), hydrocarbon (HC), nitrogen oxides (NOx) and smoke were chosen as responses on the RSM model. Considering the findings taken from the RSM model, the working conditions in which the best output can be obtained from the engine; it has been determined as 13% GSO percentage, 245 bar injection pressure and 850-W engine load. The study to verify the re-sults obtained from the optimization study reveals that the results were ob-tained with an error of less than 9%.

show abstract

Performance and emission prediction of a compression ignition engine fueled with biodiesel-diesel blends: A combined application of ANN and RSM based optimization

Cited by 155 publications

References 30 publications

Predição da Emissão de Particulado Utilizando Algoritmo de Aprendizagem de Máquina

Predição da Emissão de Particulado Utilizando Algoritmo de Aprendizagem de Máquina

Analysis of the effects of cetane improver addition to diesel on engine performance and emissions

Improving the Running Conditions of Diesel Engine with Grape Seed Oil Additives by Response Surface Design

Contact Info

Product

Resources

About