Öğreniminde Çok Doğrusal Regresyon Kullanarak Araç Yakıt Emisyon Verimliliği Tahmini

Year 2022, Issue: 34, 115 - 120, 31.03.2022

Yunus Eği

https://doi.org/10.31590/ejosat.1076596

Abstract

Araç yakıt tüketimi ve emisyonu küresel ısınma ve dünya ekonomisi için büyük bir olay olmuştur. CO2 emisyonunun etkileri, Nominal Beygir Gücü (NBG), Silindir ve Rotor Sayısı (SRS), Dişli Sayısı (DS) ve Eşdeğer Test Ağırlığı (ETA) gibi motor tasarım parametrelerinin Yuvarlatılmış ve Ayarlanmış Yakıt Ekonomisine (YAYE) optimizasyonu ile en aza indirilebilir. Bu makalede, makine öğreniminde Çoklu Doğrusal Regresyon (ÇDR) kullanılarak NBG, SRS, DS ve ETA bağımsız değişkenlerinin YAYE'ye ağırlıklı etkisi ortaya çıkarılmıştır. Önerilen ÇDR yöntemi için araç verileri eğitim ve test olarak ikiye ayrılmıştır. Daha sonra yanlış tahminlere yol açan aykırı değerleri ortadan kaldırmak için eğitim verilerine veri temizleme işlemi uygulanmıştır. Önerilen yöntem, bağımlı değişken YAYE ile ilişkisi olan değişkenleri karşılaştırmak ve aramak için korelasyon katsayısını belirlemektedir. Korelasyon analizinde önemsiz parametreler bulunmadığından ÇDR eğitimi tüm parametreler dikkate alınarak gerçekleştirilmiştir. Son olarak, işlenen veriler ÇDR modeli oluşturmak için eğitilmiştir. Elde edilen model Varyans (ANOVA) analizi ile değerlendirilmiştir. ANOVA'ya göre, bağımlı değişken YAYE ile bağımsız değişkenler DS, ETA ve NBG arasında sırasıyla p değeri 4.0994e-60, 1.5887e-48 ve 2.5494e-31 arasında anlamlı bir ilişki vardır. Ayrıca, DS ETA ve NBG'nin p değerleri 227.73, 220.87 ve 152.41 F test sonuçları ile desteklenir. Öte yandan, elde edilen model ayrıca 0.031276 p değeri ve 4.94 F testi ile SRS'den nispeten daha az etkilenir. Sonuç olarak, ortaya çıkan ÇDR modeli, araç parametrelerinin CO2 emisyonlarını etkilediğini ortaya çıkardığı için yeni araç tasarımlarında kullanılabilir.

Keywords

Yakıt verimliliği, Makine Öğrenimi, Çoklu lineer Regresyon, CO2 Emisyonu

Vehicle Fuel Emission Efficiency Estimation Using Multi-Linear Regression in Machine Learning

Abstract

Vehicle fuel consumption and emission have been a great deal for global warming and the world economy. The impacts of CO2 emission can be minimized through optimization of engine design parameters such as Rated horsepower(RHP), Number of Cylinders and Rotors(NCR), Number of Gears(NG), and Equivalent Test Weight(ETW) to the Rounded and Adjusted Fuel Economy (RAFE). This article explorers the weighted impact of the independent variables RHP, NCR, NG, and ETW to RAFE using Multi-Linear Regression(MLR) in machine learning. For the proposed MLR method, the vehicle data is divided into two as training and testing. Then, the data cleanup process was applied to the training data to eliminate outliers that led to incorrect predictions. The proposed method determines the correlation coefficient to compare and seek the variables having less relationships with the dependent variable RAFE. Since there are no insignificant parameters in correlation analysis, MLR training was carried out by taking into account all parameters. Finally, the processed data are trained to create a multi-linear regression model. The obtained model is evaluated through Analysis of Variance(ANOVA). According to the ANOVA, there is a significant relationship between the dependent variable RAFE and the independent variables NG, ETW, and RHP with a p-value of 4.0994e-60, 1.5887e-48, and 2.5494e-31, respectively. Moreover, p-values of NG, ETW, and RHP are supported with F-test results of 227.73, 220.87, and 152.41. On the other hand, the obtained model is also relatively less affected by NCR, with a p-value of 0.031276 and an F-test of 4.94. As a result, the resulting MLR model can be used in new vehicle designs as it reveals which vehicle parameters affect CO2 emissions.

Keywords

Fuel efficiency, Machine Learning, Multi-linear Regression, CO2 Emission.

References

• Kan, Z., Tang, L., Kwan, M. P., Zhang, X. (2018). Estimating vehicle fuel consumption and emissions using GPS big data. International journal of environmental research and public health, 15(4), 566.
• He, H., Liang, X. Z., Wuebbles, D. J. (2018). Effects of emissions change, climate change and long-range transport on regional modeling of future US particulate matter pollution and speciation. Atmospheric Environment, 179, 166-176.
• Hula, A., Maguire, A., Bunker, A., Rojeck, T., Harrison, S. (2021). The 2021 EPA Automotive Trends Report: Greenhouse Gas Emissions, Fuel Economy, and Technology since 1975 (No. EPA-420-R-21-023).
• Tan, Z., Wu, Y., Gu, Y., Liu, T., Wang, W., Liu, X. (2022). An overview on implementation of environmental tax and related economic instruments in typical countries. Journal of Cleaner Production, 330, 129688.
• Choi, Y. Y., Liu, Y., Huang, L. (2015). Safer or Cheaper? Household Safety Concerns, Vehicle Choices, and the Costs of Fuel Economy Stan- dards (No. 330-2016-14033).
• Qaemi, M., Heravi, G. (2012). Sustainable Energy Performance Indicators of Green Building in Developing Countries. In Construction Research Congress 2012: Construction Challenges in a Flat World (pp. 1961-1970).
• Shamsuddin, M. S., Zulkifli, A. F. H. (2021). Prediction of Performance and Emission of CNG-Diesel Dual Fuel Engine using Response Surface Methodology. Progress in Engineering Application and Technology, 2(2), 790–809. Retrievedfromhttps://publisher.uthm.edu.my/periodicals/index.php/peat/article/view/704
• Nguyen TTT, Wilson BG. Fuel consumption estimation for kerbside municipal solid waste (MSW) collection activities. Waste Management Research. 2010;28(4):289 297. doi:10.1177/0734242X09337656
• Treiber, M., Kesting, A., Thiemann, C. (2008). How much does traffic congestion increase fuel consumption and emissions? Applying a fuel consumption model to the NGSIM trajectory data. In 87th Annual Meeting of the Transportation Research Board, Washington, DC (Vol. 71, pp. 1-18).
• Eyceyurt, E., Zec, J. (2020). Uplink Throughput Prediction in Cellular Mobile Networks. International Journal of Electronics and Communication Engineering, 14(6), 149-153.
• McCartt, A. T., Hu, W. (2017). Effects of vehicle power on passenger vehicle speeds. Traffic injury prevention, 18(5), 500-507.
• Dolatabadi, N., Forder, M., Morris, N., Rahmani, R., Rahnejat, H., Howell-Smith, S. (2020). Influence of advanced cylinder coatings on vehicular fuel economy and emissions in piston compression ring conjunction. Applied Energy, 259, 114129.
• Nascimento, T. P., Saska, M. (2019). Position and attitude control of multi-rotor aerial vehicles: A survey. Annual Reviews in Control, 48, 129-146.
• Triantafyllopoulos, G., Kontses, A., Tsokolis, D., Ntziachristos, L., Samaras, Z. (2017). Potential of energy efficiency technologies in reducing vehicle consumption under type approval and real-world conditions. Energy, 140, 365-373.
• Thomas, J. (2016). Vehicle efficiency and tractive work: rate of change for the past decade and accelerated progress required for US fuel economy and CO2 regulations. SAE International Journal of Fuels and Lubricants, 9(1), 290-305.
• Dreyer, S. J., Teisl, M. F., McCoy, S. K. (2015). Are acceptance, support, and the factors that affect them, different? Examining perceptions of US fuel economy standards. Transportation Research Part D: Transport and Environment, 39, 65-75
• Zhao, Q., Caiafa, C. F., Mandic, D. P., Chao, Z. C., Nagasaka, Y., Fujii, N., ... Cichocki, A. (2012). Higher order partial least squares (HOPLS): a generalized multilinear regression method. IEEE transactions on pattern analysis and machine intelligence, 35(7), 1660-1673.
• Adler, J., Parmryd, I. (2010). Quantifying colocalization by correlation: the Pearson correlation coefficient is superior to the Mander’s overlap coefficient. Cytometry Part A, 77(8), 733-742.
• Plonsky, L., Ghanbar, H. (2018). Multiple regression in L2 research: A methodological synthesis and guide to interpreting R2 values. The Modern Language Journal, 102(4), 713-731.
• B. J., Dehghani, H., Shamsi, R. (2020). Predicting silver price by applying a coupled multiple linear regression (MLR) and imperialist competitive algorithm (ICA). Metaheuristic Comput Appl, 1(1), 101-114.
• Rouder, J. N., Engelhardt, C. R., McCabe, S., Morey, R. D. (2016). Model comparison in ANOVA. Psychonomic bulletin review, 23(6), 1779-1786