Efficient and Simplified Modeling for Kerosene Processing Quality Detection Using Partial Least Squares-Discriminant Analysis Regression

Hayder M.  Issa; Rezan H. Hama Salih

doi:10.14500/aro.11515

Hayder M. Issa Department of Chemistry, University of Garmian, Kalar, Sulaymaniyah Province, 46021,Kurdistan Region – F.R. Iraq http://orcid.org/0000-0002-0857-0097
Rezan H. Hama Salih Department of Chemistry, University of Garmian, Kalar, Sulaymaniyah Province, 46021,Kurdistan Region – F.R. Iraq https://orcid.org/0000-0001-6755-7549

Keywords: Supervised discrimination technique, Modeling, Kerosene processing, Quality control, PLS-DA, Machine learning tool

Abstract

Kerosene from various refineries and crudes is used for heating and other purposes in many countries like Iraq; therefore, it is important to identify its source to recognize and tax any adulteration. In this study, a fast classification technique for kerosene marketed in Iraq was developed with the goal of identifying its quality. The samples were categorized using a supervised partial least squares discriminant analysis (PLS-DA) approach. Multivariate analyses using agglomerative hierarchal clustering and principal component analysis were utilized to identify outliers and sample dissimilarities. The dataset was divided into calibration and prediction sets. The prediction set was used to evaluate the model’s separation performance. The Q² cross-validation was applied. The PLS-DA models achieved significant accuracy, sensitivity, and specificity, showing strong segregation ability, notably for the calibration set (100% accuracy and 1.00 sensitivity). It was found that kerosene processing can be classified rapidly and non-destructively without the need for complicated analyses, demonstrating the best results for classification even when compared with the classification outcomes of other fuels. This PLS-DA approach has never been looked at before for process quality detection, and the results are comparable to direct kerosene classification with soft independent modeling of class analogy and support vector machines.

Downloads

Download data is not yet available.

Author Biographies

Hayder M. Issa, Department of Chemistry, University of Garmian, Kalar, Sulaymaniyah Province, 46021,Kurdistan Region – F.R. Iraq

Hayder M. Issa is an Assistant Professor at the Department of Chemistry, College of Science, University of Garmian. He got the B.Sc. degree in Chemical Engineering (University of Baghdad in 1993), the M.Sc. degree in Chemical Engineering (University of Baghdad in 1996) and the Ph.D. degree in Process and Environmental Engineering (University of Toulouse 3, France in 2013). His research interests are in Process Modeling and Simulation, Oil and Gas Processing, Water and Wastewater Plant Design, and Environmental Processing. Dr. Hayder is a member of Iraqi Engineers Union, Kurdistan Engineers Society, and Kurdistan Physicists and Chemists Society.

Rezan H. Hama Salih, Department of Chemistry, University of Garmian, Kalar, Sulaymaniyah Province, 46021,Kurdistan Region – F.R. Iraq

Rezan H. Hama Salih is a Lecturer at the Department of Chemistry, College of Science, University of Garmian. She got the B.Sc. degree in Chemistry (University of Garmian in 2013), the M.Sc. degree in Organic Chemistry (University of Salaheddin-Erbil in 2016). Her research interests are in Organic Synthesis, Hydrocarbon Functional Groups, and Oil and Gas. Mrs. Rezan is a member of Kurdistan Physicists and Chemists Society.

References

Abdullah, Z.F., and Daij, M.A., 2021. Analytical study of oil refining in the North refineries company for the period 2013-2019. Journal of Al-Frahedis Arts, 13(46), pp.131-159.

Ali, J.A., and Khodakarami, L., 2015. Optimal oil pipeline route in Kurdistan Region Taq Taq-Bazian refinery as case study. International Journal of Engineering Trends and Technology, 23(5), pp.257-262. DOI: https://doi.org/10.14445/22315381/IJETT-V23P248

ASTM D4057 - 19, 2019. Standard Practice for Manual Sampling of Petroleum and Petroleum Products. ASTM International, West Conshohocken, PA.ASTM E1655-17, 2018. Standard Practices for Infrared Multivariate Quantitative Analysis. ASTM International, West Conshohocken, PA.

Barra, I., Kharbach, M., Bousrabat, M., Cherrah, Y., Hanafi, M., Qannari, E.M., and Bouklouze, A., 2020. Discrimination of diesel fuels marketed in Morocco using FTIR, GC-MS analysis and chemometrics methods. Talanta, 209, p.120543. DOI: https://doi.org/10.1016/j.talanta.2019.120543

Coates, J., 2000. Interpretation of infrared spectra, a practical approach. In: Encyclopedia of Analytical Chemistry. John Wiley and Sons Ltd., Chichester, UK. DOI: https://doi.org/10.1002/9780470027318.a5606

Comesaña-García, Y., Cavado-Osorio, A., Linchenat-Dennes, E., and Dago-Morales, Á., 2013. Classification of kerosene using physicochemical data and multivariate techniques. Revista CENIC Ciencias Químicas, 44, pp.13-22.

Dadson, J., Pandam, S., and Asiedu, N., 2018. Modeling the characteristics and quantification of adulterants in gasoline using FTIR spectroscopy and chemometric calibrations. Cogent Chemistry, 4(1), p.1482637. DOI: https://doi.org/10.1080/23312009.2018.1482637

Dago Morales, Á., Cavado Osorio, A., Fernández Fernández, R., and Dennes, E.L., 2008. Development of a SIMCA model for classification of kerosene by infrared spectroscopy. Química Nova, 31, pp.1573-1576. DOI: https://doi.org/10.1590/S0100-40422008000600049

De Paulo, J.M., Barros, J.E.M., and Barbeira, P.J.S., 2014. Differentiation of gasoline samples using flame emission spectroscopy and partial least squares discriminate analysis. Energy and Fuels, 28(7), pp.4355-4361. DOI: https://doi.org/10.1021/ef5003827

Hanley, J.A., 1998. Receiver operating characteristic (ROC) curves. In: Armitage, P., and Colton, Y., (eds.). Encyclopedia of Biostatistics. Wiley, Chichester.

ISO 4259-3, 2020. Petroleum and Related Products - Precision of Measurement Methods and Results - Part 3: Monitoring and Verification of Published Precision data in Relation to Methods of Test. ISO - International Organization for Standardization, Geneve.

ISO 5725-2, 2019. Accuracy (Trueness and Precision) of Measurement Methods and Results - Part 2: Basic Method for the Determination of Repeatability and Reproducibility of a Standard Measurement Method. ISO - International Organization for Standardization, Geneve.

Issa, H.M., 2024. Prediction of octane numbers for commercial gasoline using distillation curves: A comparative regression analysis between principal component and partial least squares methods. Petroleum Science and Technology, 42(10), pp.1233-1249. DOI: https://doi.org/10.1080/10916466.2022.2143814

Kaiser, M.J., 2017. A review of refinery complexity applications. Petroleum Science, 14(1), pp.167-194. DOI: https://doi.org/10.1007/s12182-016-0137-y

Kaltschmitt, T., and Deutschmann, O., 2012. Chapter 1 - Fuel processing for fuel cells. In: Sundmacher, K., (ed.). Advances in Chemical Engineering. Academic Press, Cambridge. DOI: https://doi.org/10.1016/B978-0-12-386874-9.00001-4

Karim, A.R., Khanaqa, P., and Shukur, D.A., 2017. Kurdistan crude oils as feedstock for production of aromatics. Arabian Journal of Chemistry, 10, pp.S2601-S2607. DOI: https://doi.org/10.1016/j.arabjc.2013.09.038

Kennard, R.W., and Stone, L.A., 1969. Computer aided design of experiments. Technometrics, 11(1), pp.137-148. DOI: https://doi.org/10.1080/00401706.1969.10490666

Khanmohammadi, M., Garmarudi, A.B., Ghasemi, K., and De La Guardia, M., 2013. Quality based classification of gasoline samples by ATR-FTIR spectrometry using spectral feature selection with quadratic discriminant analysis. Fuel, 111, pp.96-102. DOI: https://doi.org/10.1016/j.fuel.2013.04.001

Lam, N.L., Smith, K.R., Gauthier, A., and Bates, M.N., 2012. Kerosene: A review of household uses and their hazards in low- and middle-income countries. Journal of Toxicology and Environmental Health, Part B, 15(6), pp.396-432. DOI: https://doi.org/10.1080/10937404.2012.710134

Mallick, J., Talukdar, S., Alsubih, M., Ahmed, M., Islam, A.R.M.T., Shahfahad, and Thanh, N.V., 2022. Proposing receiver operating characteristic-based sensitivity analysis with introducing swarm optimized ensemble learning algorithms for groundwater potentiality modelling in Asir region, Saudi Arabia. Geocarto International, 37(15), pp.4361-4389. DOI: https://doi.org/10.1080/10106049.2021.1878291

Mazivila, S.J., Mitsutake, H., Santana, F.B.D., Gontijo, L.C., Santos, D.Q., and Borges Neto, W., 2015. Fast classification of different oils and routes used in biodiesel production using mid infrared spectroscopy and PLS2-DA. Journal of the Brazilian Chemical Society, 26(4), pp.642-648. DOI: https://doi.org/10.5935/0103-5053.20150020

Mohammadi, M., Khanmohammadi Khorrami, M., Vatani, A., Ghasemzadeh, H., Vatanparast, H., Bahramian, A., and Fallah, A., 2020. Rapid determination and classification of crude oils by ATR-FTIR spectroscopy and chemometric methods. Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy, 232, p.118157. DOI: https://doi.org/10.1016/j.saa.2020.118157

Naman, S., Jamil, L.A., Al-Gulami, F., Simo, S., and Ali, M.K., 2019. Evaluation of crude oils and natural gases of Kurdistan-Iraq by catalytic improvements to lighter oils using local clays. WIT Transactions on Ecology and the Environment, 222, pp.81-91. DOI: https://doi.org/10.2495/EQ180081

Pontes, M.J.C., Pereira, C.F., Pimentel, M.F., Vasconcelos, F.V.C., and Silva, A.G.B., 2011. Screening analysis to detect adulteration in diesel/biodiesel blends using near infrared spectrometry and multivariate classification. Talanta, 85(4), pp.2159-2165. DOI: https://doi.org/10.1016/j.talanta.2011.07.064

Roy, P.P., and Roy, K., 2008. On some aspects of variable selection for partial least squares regression models. QSAR and Combinatorial Science, 27(3), pp.302-313. DOI: https://doi.org/10.1002/qsar.200710043

Tanaka, G.T., De Oliveira Ferreira, F., Ferreira Da Silva, C.E., Flumignan, D.L., and De Oliveira, J.E., 2011. Chemometrics in fuel science: Demonstration of the feasibility of chemometrics analyses applied to physicochemical parameters to screen solvent tracers in Brazilian commercial gasoline. Journal of Chemometrics, 25(9), pp.487-495. DOI: https://doi.org/10.1002/cem.1394