Fossil fuel-based vehicles represent the largest percentage of the world’s active fleet, therefore, despite all the issues gasoline is linked to, it is directly involved in people’s daily lives. There is effort made by the companies to reduce the cost of producing and distributing gasoline to maximize profit, and the use of illegal techniques is not uncommon. One example is the adulteration of that fuel with ethanol, which can lead to damage to the engine’s components when the machines are not properly equipped to handle ethanol. There is a need for an easy, fast, and effective way to detect this solvent in gasoline-ethanol blends; the present paper aims to present a method based on infrared imaging processing, principal component analysis and machine learning algorithms to classify images of operating engines regarding the content of ethanol that was introduced as fuel blended with gasoline. The study concluded that Artificial Neural Networks, Support Vector Machines, K-Nearest Neighbors and Decision Tree algorithms are capable of classifying the images with accuracies of 93.5%, 93.2%, 97.0%, and 96.8%, respectively.
TakeshitaEVRezendeRVPde SouzaS, et al. Influence of solvent addition on the physicochemical properties of Brazilian gasoline. Fuel2008; 87(10-11): 2168–2177. https://doi.org/10.1016/j.fuel.2007.11.003
8.
SolankiTJainSKGoyalA. Analysis on emissions of gasoline engine with different ethanol blends at different compression ratio. YMER Digital2022; 21: 18–28.
9.
MohamadBSzepesiGLBolloB. Effect of ethanol-gasoline fuel blends on the exhaust emissions and characteristics of SI engines. In: Proceedings of the 2nd VAE 2018, vehicle and automotive engineering 2, 2018, pp. 29–41. Springer. https://doi.org/10.1007/978-3-319-75677-6_3
10.
MohammedMKBallaHHAl-DulaimiZMH, et al. Effect of ethanol-gasoline blends on SI engine performance and emissions. Case Stud Therm Eng2021; 25: 100891. https://doi.org/10.1016/j.csite.2021.100891
11.
StepienZ. Study of the various factors influencing deposit formation and operation of gasoline engine injection systems. IOP Conf Ser Mater Sci Eng2016; 148(1): 012052. https://doi.org/10.1088/1757-899x/148/1/012052
12.
GonçalvesACFerreiraRLPretoE, et al. Analysis of the influence of gasoline adulteration on lubricant degradation and internal combustion engine performance. ACS Omega2022; 7(38): 34012–34021. https://doi.org/10.1021/acsomega.2c03207
13.
FadairoASEkoh-ChukwukaluJAdeyemiGA, et al. A fast and cost-efficient method to detect ethanol as adulterant in gasoline. MethodsX2020; 7: 100974. https://doi.org/10.1016/j.mex.2020.100974
14.
Goulart IsoppoVSangiogo GilEGonçalvesPFB, et al. Highly fluorescent lipophilic 2,1,3-benzothiadiazole fluorophores as optical sensors for tagging material and gasoline adulteration with ethanol. Sens Actuators B Chem2020; 309: 127701. https://doi.org/10.1016/j.snb.2020.127701
15.
PedrosoMPde GodoyLAFerreiraEC, et al. Identification of gasoline adulteration using comprehensive two-dimensional gas chromatography combined to multivariate data processing. J Chromatogr A2008; 1201(2): 176–182. https://doi.org/10.1016/j.chroma.2008.05.092
16.
BezerraACDMSilvaDDOMatosGHMD, et al. Quantification of anhydrous ethanol and detection of adulterants in commercial Brazilian gasoline by Raman spectroscopy. Instrum Sci Technol2019; 47(1): 90–106. https://doi.org/10.1080/10739149.2018.1470535
17.
RomanelSACunhaDACastroEVR, et al. Time domain nuclear magnetic resonance (TD-NMR): a new methodology to quantify adulteration of gasoline. Microchem J2018; 140: 31–37. https://doi.org/10.1016/j.microc.2018.03.041
18.
Brazilian Association of Technical Standards. ABNT NBR 13992:2015. Automotive gasoline — determination of anhydrous ethanol content (EAC). Brazilian Association of Technical Standards; 2015.
19.
TongKWangZSiL, et al. A novel pipeline leak recognition method of mine air compressor based on infrared thermal image using IFA and SVM. Appl Sci2020; 10(17): 5991. https://doi.org/10.3390/app10175991
20.
JiaZLiuZVongCM, et al. A rotating machinery fault diagnosis method based on feature learning of thermal images. IEEE Access2019; 7: 12348–12359. https://doi.org/10.1109/access.2019.2893331
21.
YounusAMWidodoAYangBS. Evaluation of thermography image data for machine fault diagnosis. Nondestructive Test Eval2010; 25(3): 231–247. https://doi.org/10.1080/10589750903473617
22.
LiWZhuoYBaoJ, et al. A data-based soft-sensor approach to estimating raceway depth in ironmaking blast furnaces. Powder Technol2021; 390: 529–538. https://doi.org/10.1016/j.powtec.2021.05.072
23.
GonzalezRC. Digital image processing. Prentice Hall; 2002.
24.
BłażejRSawickiMKirjanówAKozłowskiTKoniecznaM. Automatic analysis of thermograms as a means for estimating technical of a gear system. Diagn2016; 17(2): 43–48.
25.
PeerMSPeerMN. Experimental investigation on engine characteristics fueled with waste HDPE oil and study on NOx emission variation using thermal imager. Environ Sci Pollut Res2019; 26: 3436–3446. https://doi.org/10.1007/s11356-018-3830-0
26.
ShameerPMRameshK. Experimental evaluation on performance, combustion behavior and influence of in-cylinder temperature on NOx emission in a DI diesel engine using thermal imager for various alternate fuel blends. Energy2017; 118: 1334–1344. https://doi.org/10.1016/j.energy.2016.11.017
27.
MancarusoESequinoLVagliecoBM. Infrared imaging in internal combustion engines: advanced techniques for vapor phase visualization and CO2 detection. J Phys Conf Ser2020; 1589(1): 012018. https://doi.org/10.1088/1742-6596/1589/1/012018
28.
BukkarapuKRKrishnasamyA. Evaluating the feasibility of machine learning algorithms for combustion regime classification in biodiesel-fueled homogeneous charge compression ignition engines. Fuel2024; 374: 132406. https://doi.org/10.1016/j.fuel.2024.132406
29.
AbusaleemAAbualigahRDalhoumEA, et al. Combined mean median filter for image enhancement. AIP Conf Proc2023; 2979(1): 020001. https://doi.org/10.1063/5.0177743
30.
KhudhairZNKhdiarANEl AbbadiNK, et al. Color to grayscale image conversion based on singular value decomposition. IEEE Access2023; 11: 54629–54638. https://doi.org/10.1109/access.2023.3279734
31.
YagleAE. Image processing for engineers. Michigan Publishing, 2018.
32.
AAGoshtasby (ed) Advances in computer vision and pattern recognition. Springer, 2012.
33.
MarquesO. Practical image and video processing using MATLAB. Wiley-IEEE Press, 2011.
34.
BJähne (ed.). Digital image processing. 5th ed. Springer, 2002.
35.
OtsuN. A threshold selection method from gray-level histograms. Automatica1975; 11(285-296): 23–27.
36.
ChoudharyAGoyalDLethaSS. Infrared thermography-based fault diagnosis of induction motor bearings using machine learning. IEEE Sens J2021; 21(2): 1727–1734. https://doi.org/10.1109/jsen.2020.3015868
TanmaySAlokMKingshukC, et al. Detection of edibility of amla (Emblica officinalis) through PCA based image analysis. Econ Comput Econ Cybern Stud Res2022; 56(2): 77–94. https://doi.org/10.24818/18423264/56.2.22.06
41.
LozanovYTzvetkovaSPetleshkovA. Use of machine learning techniques for classification of thermographic images. In: Proceedings of the 12th electrical engineering faculty conference (BulEF), 2020. IEEE. https://doi.org/10.1109/BulEF51036.2020.9326046
