Research Article
BibTex RIS Cite

Alternatif Yakıt Karışımlarının Egzoz Emisyonları Üzerindeki Etkisini Öngörmek İçin Makine Öğrenme Yöntemlerinin Kullanılması

Year 2022, Issue: 34, 273 - 279, 31.03.2022
https://doi.org/10.31590/ejosat.1081539

Abstract

Makine öğrenimi, veriye dayalı öğrenmeyi sağlayan algoritmaların tasarım ve geliştirme süreçleriyle ilgilenen bir bilimdir. Makine öğrenmesi yöntemleri, geçmiş verileri kullanarak yeni veri tahmin süreçleri için en uygun modeli bulmaya çalışır. Bu çalışmada, 1-Propanol, 2-Propanol, AVGAS ve benzin yakıtı kullanılarak hacimce %5, %10, %15 yakıt karışımları ile motor denemelerinden elde edilen veriler kullanılmıştır. Elde edilen veriler %100 benzin değerleri ile karşılaştırılmıştır. Çalışmada direkt enjeksiyonlu ve turboşarjlı 4 silindirli bir motor kullanıldı. Elde edilen ölçüm sonuçları ile makine öğrenmesinde kullanılmak üzere bir veri tabanı oluşturulmuştur. Oluşturulan veri tabanı ile ANN, GBA, SVM ve AB makine öğrenmesi modelleri üzerinde tahmin işlemleri gerçekleştirilmiştir. Çalışma sonunda CO, CO2, HC, O2 değerlerinin tahmini için en uygun modelin R2 değeri 0,99999 olan YSA olduğu bulunmuştur. NO değeri için R2 değeri 0.9996 ile AB yönteminin kullanıldığı belirlendi. CO değerinin tahmin sürecinde GBA ve AB yöntemleri 0,99 R2'den daha yüksek bir değere sahip oldukları için kullanılabilecek diğer makine öğrenmesi yöntemleridir. CO2, HC ve O2 ve çıkış değeri tahmin sürecinde GBA ve AB 0,99 R2'den daha yüksek bir değere sahip oldukları için YSA yerine kullanılabilecek diğer yöntemlerdir. AB 0.99 R2 değeri ile NO değeri tahmini için kullanılabilecek başka bir makine öğrenmesi yöntemi olduğu tespit edilmiştir.

References

  • Y. Qian, J. Guo, Y. Zhang, W. Tao, and X. Lu, (2018). “Combustion and emission behavior of N-propanol as partially alternative fuel in a direct injection spark ignition engine,” Appl. Therm. Eng., vol. 144, pp. 126–136, doi: 10.1016/J.APPLTHERMALENG.2018.08.044.
  • M. S. Gökmen, İ. Doğan, and H. Aydoğan, (2021). “Yanıt Yüzey Metodolojisi Kullanılarak 1-Propanol/Benzin Yakıt Karışımlarının Egzoz Emisyonlarına Etkisinin Araştırılması,” Eur. J. Sci. Technol., no. 24, pp. 67–74, doi: 10.31590/ejosat.898563.
  • G. R. Gawale and G. Naga Srinivasulu, (2020). “Experimental investigation of propanol dual fuel HCCI engine performance: Optimization of propanol mass flow rate, impact of butanol blends (B10/B20/B30) as fuel substitute for diesel,” Fuel, vol. 279, p. 118535, doi: 10.1016/J.FUEL.2020.118535.
  • M. Mourad and K. R. M. Mahmoud, (2018). “Performance investigation of passenger vehicle fueled by propanol/gasoline blend according to a city driving cycle,” Energy, vol. 149, pp. 741–749, doi: 10.1016/J.ENERGY.2018.02.099.
  • X. Liu, H. Wang, Z. Zheng, J. Liu, R. D. Reitz, and M. Yao, (2016). “Development of a combined reduced primary reference fuel-alcohols (methanol/ethanol/propanols/butanols/n-pentanol) mechanism for engine applications,” Energy, vol. 114, pp. 542–558, doi: 10.1016/J.ENERGY.2016.08.001.
  • A. Kimya, “Ataman Kimya,” (2019). https://atamankimya.com.
  • Shell, “Shell,” (2010). https://www.shell.com/business-.
  • A. C. Müller and S. Guido, (2020). Introduction to Machine Learning with Python.
  • A. U. Osarogiagbon, F. Khan, R. Venkatesan, and P. Gillard, (2021). “Review and analysis of supervised machine learning algorithms for hazardous events in drilling operations,” Process Saf. Environ. Prot., vol. 147, pp. 367–384, doi: 10.1016/J.PSEP.2020.09.038.
  • T. Hastie, R. Tibshirani, and J. Friedman, (2008). The Elements of Statistical Learning.
  • S. Raschka, D. Julian, and J. Hearty, (2016). Python : deeper insights into machine learning : leverage benefits of machine learning techniques using Python : a course in three modules.
  • U. Ozkaya and L. Seyfi, (2015). "Dimension optimization of microstrip patch antenna in X/Ku band via artificial neural network" Procedia-Social and Behavioral Sciences, 195, pp. 2520-2526.
  • Q. Liu, X. Wang, X. Huang, and X. Yin, (2020). “Prediction model of rock mass class using classification and regression tree integrated AdaBoost algorithm based on TBM driving data,” Tunn. Undergr. Sp. Technol., vol. 106, no. August, p. 103595, doi: 10.1016/j.tust.2020.103595.
  • V. Vapnik, S. E. Golowich, and A. Smola, (1997). “Support vector method for function approximation, regression estimation, and signal processing,” Adv. Neural Inf. Process. Syst., pp. 281–287.
  • H. Zhong, J. Wang, H. Jia, Y. Mu, and S. Lv, (2019). “Vector field-based support vector regression for building energy consumption prediction,” Appl. Energy, vol. 242, no. September 2018, pp. 403–414, doi: 10.1016/j.apenergy.2019.03.078.
  • B. Dong, C. Cao, and S. E. Lee, (2005). “Applying support vector machines to predict building energy consumption in tropical region,” Energy Build., vol. 37, no. 5, pp. 545–553, doi: 10.1016/J.ENBUILD.2004.09.009.
  • J. Lin, C. Cheng, and K.-W. Chau, (2006). “Using support vector machines for long-term discharge prediction,” Hydrol. Sci. J., vol. 51, no. 4, pp. 599–612, doi: 10.1623/hysj.51.4.599.
  • P. Golbayani, I. Florescu, and R. Chatterjee, (2020). “A comparative study of forecasting corporate credit ratings using neural networks, support vector machines, and decision trees,” North Am. J. Econ. Financ., vol. 54, p. 101251, doi: 10.1016/J.NAJEF.2020.101251.
  • A. Domínguez-Sáez, G. A. Rattá, and C. C. Barrios, (2018). “Prediction of exhaust emission in transient conditions of a diesel engine fueled with animal fat using Artificial Neural Network and Symbolic Regression,” Energy, vol. 149, pp. 675–683, doi: 10.1016/J.ENERGY.2018.02.080.

Using Machine Learning Methods to Predict the Effect of Alternative Fuel Mixtures on Exhaust Emissions

Year 2022, Issue: 34, 273 - 279, 31.03.2022
https://doi.org/10.31590/ejosat.1081539

Abstract

Machine learning is a science that deals with the design and development processes of algorithms that enable data-based learning. Machine learning methods try to find the most suitable model for new data prediction processes by using the past data. In this study, the data obtained from the engine trials with fuel mixtures of 5%, 10%, 15% by volume using 1-Propanol, 2-Propanol, AVGAS and gasoline fuel were used. Obtained data were compared with 100% gasoline values. In the study, a 4-cylinder engine with direct injection and turbocharging was used. With the obtained measurement results, a database was created to be used in machine learning. With the created database, estimation processes were carried out on ANN, GBA, SVM and AB machine learning models. At the end of the study, it was found that the most suitable model for the estimation of CO, CO2, HC, O2 values was ANN with an R2 value of 0.9999. For the NO value, it was determined that the AB method was used with an R2 value of 0.9996. In the estimation process of the CO value, GBA and AB methods are other machine learning methods that can be used as they have a higher value than 0.99 R2. CO2, HC and O2, and in the output value estimation process, GBA and AB are other methods that can be used instead of ANN as they have a higher value than 0.99 R2. It has been found that there is another machine learning method that can be used for NO value estimation, with an AB 0.99 R2 value.

References

  • Y. Qian, J. Guo, Y. Zhang, W. Tao, and X. Lu, (2018). “Combustion and emission behavior of N-propanol as partially alternative fuel in a direct injection spark ignition engine,” Appl. Therm. Eng., vol. 144, pp. 126–136, doi: 10.1016/J.APPLTHERMALENG.2018.08.044.
  • M. S. Gökmen, İ. Doğan, and H. Aydoğan, (2021). “Yanıt Yüzey Metodolojisi Kullanılarak 1-Propanol/Benzin Yakıt Karışımlarının Egzoz Emisyonlarına Etkisinin Araştırılması,” Eur. J. Sci. Technol., no. 24, pp. 67–74, doi: 10.31590/ejosat.898563.
  • G. R. Gawale and G. Naga Srinivasulu, (2020). “Experimental investigation of propanol dual fuel HCCI engine performance: Optimization of propanol mass flow rate, impact of butanol blends (B10/B20/B30) as fuel substitute for diesel,” Fuel, vol. 279, p. 118535, doi: 10.1016/J.FUEL.2020.118535.
  • M. Mourad and K. R. M. Mahmoud, (2018). “Performance investigation of passenger vehicle fueled by propanol/gasoline blend according to a city driving cycle,” Energy, vol. 149, pp. 741–749, doi: 10.1016/J.ENERGY.2018.02.099.
  • X. Liu, H. Wang, Z. Zheng, J. Liu, R. D. Reitz, and M. Yao, (2016). “Development of a combined reduced primary reference fuel-alcohols (methanol/ethanol/propanols/butanols/n-pentanol) mechanism for engine applications,” Energy, vol. 114, pp. 542–558, doi: 10.1016/J.ENERGY.2016.08.001.
  • A. Kimya, “Ataman Kimya,” (2019). https://atamankimya.com.
  • Shell, “Shell,” (2010). https://www.shell.com/business-.
  • A. C. Müller and S. Guido, (2020). Introduction to Machine Learning with Python.
  • A. U. Osarogiagbon, F. Khan, R. Venkatesan, and P. Gillard, (2021). “Review and analysis of supervised machine learning algorithms for hazardous events in drilling operations,” Process Saf. Environ. Prot., vol. 147, pp. 367–384, doi: 10.1016/J.PSEP.2020.09.038.
  • T. Hastie, R. Tibshirani, and J. Friedman, (2008). The Elements of Statistical Learning.
  • S. Raschka, D. Julian, and J. Hearty, (2016). Python : deeper insights into machine learning : leverage benefits of machine learning techniques using Python : a course in three modules.
  • U. Ozkaya and L. Seyfi, (2015). "Dimension optimization of microstrip patch antenna in X/Ku band via artificial neural network" Procedia-Social and Behavioral Sciences, 195, pp. 2520-2526.
  • Q. Liu, X. Wang, X. Huang, and X. Yin, (2020). “Prediction model of rock mass class using classification and regression tree integrated AdaBoost algorithm based on TBM driving data,” Tunn. Undergr. Sp. Technol., vol. 106, no. August, p. 103595, doi: 10.1016/j.tust.2020.103595.
  • V. Vapnik, S. E. Golowich, and A. Smola, (1997). “Support vector method for function approximation, regression estimation, and signal processing,” Adv. Neural Inf. Process. Syst., pp. 281–287.
  • H. Zhong, J. Wang, H. Jia, Y. Mu, and S. Lv, (2019). “Vector field-based support vector regression for building energy consumption prediction,” Appl. Energy, vol. 242, no. September 2018, pp. 403–414, doi: 10.1016/j.apenergy.2019.03.078.
  • B. Dong, C. Cao, and S. E. Lee, (2005). “Applying support vector machines to predict building energy consumption in tropical region,” Energy Build., vol. 37, no. 5, pp. 545–553, doi: 10.1016/J.ENBUILD.2004.09.009.
  • J. Lin, C. Cheng, and K.-W. Chau, (2006). “Using support vector machines for long-term discharge prediction,” Hydrol. Sci. J., vol. 51, no. 4, pp. 599–612, doi: 10.1623/hysj.51.4.599.
  • P. Golbayani, I. Florescu, and R. Chatterjee, (2020). “A comparative study of forecasting corporate credit ratings using neural networks, support vector machines, and decision trees,” North Am. J. Econ. Financ., vol. 54, p. 101251, doi: 10.1016/J.NAJEF.2020.101251.
  • A. Domínguez-Sáez, G. A. Rattá, and C. C. Barrios, (2018). “Prediction of exhaust emission in transient conditions of a diesel engine fueled with animal fat using Artificial Neural Network and Symbolic Regression,” Energy, vol. 149, pp. 675–683, doi: 10.1016/J.ENERGY.2018.02.080.
There are 19 citations in total.

Details

Primary Language English
Subjects Engineering
Journal Section Articles
Authors

Samet Bilban 0000-0002-9035-0690

Hasan Aydoğan 0000-0003-1404-6352

Early Pub Date January 30, 2022
Publication Date March 31, 2022
Published in Issue Year 2022 Issue: 34

Cite

APA Bilban, S., & Aydoğan, H. (2022). Using Machine Learning Methods to Predict the Effect of Alternative Fuel Mixtures on Exhaust Emissions. Avrupa Bilim Ve Teknoloji Dergisi(34), 273-279. https://doi.org/10.31590/ejosat.1081539