Özgün YÜCEL, Meltem KASAPOĞLU ÇALIK, Ebubekir Sıddık AYDIN

TORREFİYE VE PİROLİZ EDİLMİŞ ODUN PELETİNİN PROSES SICAKLIĞININ, KISA ANALİZİNİN MAKİNE ÖĞRENMESİ DESTEKLİ YAKIN KIZILÖTESİ SPEKTROSKOPİSİ İLE TAHMİNİ

Yakın Kızılötesi (NIR) Spektroskopi, gıda, petrokimya, ilaç ve tarım endüstrilerindeki malzemeleri karakterize etmek için zaman ve maliyet açısından etkin bir yöntemdir. Karbon içeren malzemelerin yakın analizi ve ısıl işlemlerin malzeme üzerindeki etkinliğinin araştırılması özellikle zaman alan bir süreçtir. Bu çalışmada, biyokütle ve ısıl işlem sıcaklığının yakın analizini tahmin etmek için dört regresyon yöntemi olan karar ağacı regresyonu, destek vektör regresyonu ve rassal orman regresyonunun iki versiyonu kullanılmıştır. Deneysel çabayı azaltmak ve ısıl işlem görmüş biyokütle hammaddesinin karakterizasyonunu teorik olarak sunmak için etkili bir yöntem önerilmiştir. Tahmin sonuçları, odun peletinin NIR spektrum değerlerini kalibre eden SVR ve ENS2 regresyon yöntemlerinin kül ve uçucu madde için 0.880- 0.984 belirleme katsayısı (R2) ve 0.444- 5.308 RMSE ile iyi performans elde ettiğini göstermektedir. Bu çalışma, entegre NIR spektroskopisine sahip makine öğrenmesine dayalı regresyon yöntemlerinin biyokütlenin hızlı karakterizasyon için alternatif bir yöntem olarak umut verici olduğunu göstermektedir. Mevcut çalışmanın bir başka olası uygulaması, biyokütle endüstrisinde tam otomatik yakıt kalitesi değerlendirme sisteminden önce işlenmiş yakıt tanıma sistemleri için kullanılabilmesidir.

PREDICTION OF PROXIMATE ANALYSIS AND PROCESS TEMPERATURE OF TORREFIED AND PYROLYZED WOOD PELLETS BY NEAR-INFRARED SPECTROSCOPY COUPLED WITH MACHINE LEARNING

Near-Infrared (NIR) Spectroscopy is a time and cost-effective method to characterize the materials in the food, petrochemical, pharmaceutical, and agricultural industries. Proximate analysis of the carbon-containing materials and investigating the effectiveness of the heat treatments on the material are a particularly time-consuming process. This work presents the four regression methods, i.e., decision tree regression, support vector regression and two versions of ensembles of decision trees to predict the proximate analysis of biomass and heat treatment temperature. Thus, effective method has been proposed to reduce experimental effort and present the characterization of heat-treated biomass feedstock theoretically. Prediction results show that SVR and ENS2 regression methods calibrating the NIR spectra to the values of wood pellet properties achieved good performance with the coefficient of determination (R2) of 0.880- 0.984 and RMSE of 0.444- 5.308 for ash and volatile matter. This study suggests that machine learning-based regression methods with integrated NIR spectroscopy of biomass is promising as an alternative method for rapid characterization. Another possible application of the current study is that it can be used for processed fuel recognition prior to a fully automated fuel quality assessment system in the biomass industry.

PDF

___

1. (IEA), I.E.A.,"Market Report Series: Renewables 2018", Analysis and Forecasts to 2023, Paris, France. 2018.
2. Aghaalikhani, A., et al.,"Detailed modelling of biomass steam gasification in a dual fluidized bed gasifier with temperature variation", Renewable Energy, 143, 703- 718, 2019.
3. Ali, M., et al.,"Spectroscopic studies of the ageing of cellulosic paper", Polymer, 42(7), 2893-2900, 2001.
4. Aliano-Gonzalez, M.J., et al.,"A screening method based on Visible-NIR spectroscopy for the identification and quantification of different adulterants in high-quality honey", Talanta, 203, 235-241, 2019.
5. Almeida, G., Brito, J.O.,Perré, P.,"Alterations in energy properties of eucalyptus wood and bark subjected to torrefaction: the potential of mass loss as a synthetic indicator", Bioresource technology, 101(24), 9778-9784, 2010.
6. Alves, A., et al.,"Calibration of NIR to assess lignin composition (H/G ratio) in maritime pine wood using analytical pyrolysis as the reference method", Holzforschung, 60(1), 29-31, 2006.
7. Ausloos, J., et al., "Designing-by-Debate: A Blueprint for Responsible Data-Driven Research & Innovation", in Responsible Research and Innovation Actions in Science Education, Gender and Ethics, Springer, 2018.
8. Aydin, E.S., Yucel, O.,Sadikoglu, H.,"Experimental study on hydrogen-rich syngas production via gasification of pine cone particles and wood pellets in a fixed bed downdraft gasifier", International Journal of Hydrogen Energy, 44(32), 17389-17396, 2019.
9. Azadeh, A., Arani, H.V.,Dashti, H.,"A stochastic programming approach towards optimization of biofuel supply chain", Energy, 76, 513-525, 2014.
10. Balabin, R.M.,Safieva, R.Z.,"Gasoline classification by source and type based on near infrared (NIR) spectroscopy data", Fuel, 87(7), 1096-1101, 2008.
11. Bassett, K., Liang, C.,Marchessault, R.,"The infrared spectrum of crystalline polysaccharides. IX. The near infrared spectrum of cellulose", Journal of Polymer Science Part A: General Papers, 1(5), 1687-1692, 1963.
12. Bellazzi, R.,Zupan, B.,"Predictive data mining in clinical medicine: current issues and guidelines", International journal of medical informatics, 77(2), 81-97, 2008.
13. Berndes, G., Hoogwijk, M.,Van den Broek, R.,"The contribution of biomass in the future global energy supply: a review of 17 studies", Biomass and bioenergy, 25(1), 1-28, 2003.
14. Breiman, L.,"Bagging predictors", Machine learning, 24(2), 123-140, 1996.
15. Castillo, R., et al.,"Supervised pattern recognition techniques for classification of Eucalyptus species from leaves NIR spectra", Journal of the Chilean Chemical Society, 53(4), 1709-1713, 2008.
16. Cortes, C.,Vapnik, V.,"Support-vector networks", Machine learning, 20(3), 273-297, 1995.
17. Freund, Y.,Schapire, R.E. Schapire R: Experiments with a new boosting algorithm. in In: Thirteenth International Conference on ML. Citeseer, 1996.
18. Fujimoto, T., et al.,"Application of near infrared spectroscopy for estimating wood mechanical properties of small clear and full length lumber specimens", Journal of Near Infrared Spectroscopy, 16(6), 529-537, 2007.
19. Fujimoto, T., Yamamoto, H.,Tsuchikawa, S.,"Estimation of wood stiffness and strength properties of hybrid larch by near-infrared spectroscopy", Applied spectroscopy, 61(8), 882-888, 2007.
20. Guenther, N.,Schonlau, M.,"Support Vector Machines", The Stata Journal: Promoting communications on statistics and Stata, 16(4), 917-937, 2016.
21. Khan, F.M.,Zubek, V.B. "Support vector regression for censored data (SVRc): a novel tool for survival analysis". in 2008 Eighth IEEE International Conference on Data Mining. IEEE, 2008.
22. Kuo, P.-C., Wu, W.,Chen, W.-H.,"Gasification performances of raw and torrefied biomass in a downdraft fixed bed gasifier using thermodynamic analysis", Fuel, 117, 1231-1241, 2014.
23. Lehmann, J.,Joseph, S., "Biochar for environmental management: an introduction", in Biochar for environmental management, Routledge. p. 33-46, 2015.
24. Lestander, T.A., et al.,"Characterization of fast pyrolysis bio-oil properties by near-infrared spectroscopic data", Journal of Analytical and Applied Pyrolysis, 133, 9-15, 2018.
25. Luypaert, J., Massart, D.,Vander Heyden, Y.,"Nearinfrared spectroscopy applications in pharmaceutical analysis", Talanta, 72(3), 865-883, 2007.
26. Ma, T., et al.,"Rapid identification of wood species by near-infrared spatially resolved spectroscopy (NIR-SRS) based on hyperspectral imaging (HSI)", Holzforschung, 73(4), 323-330, 2019.
27. Melkior, T., et al.,"NMR analysis of the transformation of wood constituents by torrefaction", Fuel, 92(1), 271- 280, 2012.
28. Mitsui, K., Inagaki, T.,Tsuchikawa, S.,"Monitoring of hydroxyl groups in wood during heat treatment using NIR spectroscopy", Biomacromolecules, 9(1), 286-288, 2007.
29. Mohammadi, K., et al.,"Support vector regression based prediction of global solar radiation on a horizontal surface", Energy Conversion and Management, 91, 433- 441, 2015.
30. Mutlu, A.Y.,Yucel, O.,"An artificial intelligence based approach to predicting syngas composition for downdraft biomass gasification", Energy, 165, 895-901, 2018.
31. Nefeslioglu, H., et al.,"Assessment of landslide susceptibility by decision trees in the metropolitan area of Istanbul, Turkey", Mathematical Problems in Engineering, 2010.
32. Porep, J.U., Kammerer, D.R.,Carle, R.,"On-line application of near infrared (NIR) spectroscopy in food production", Trends in Food Science & Technology, 46(2), 211-230, 2015.
33. Rokach, L.,"Ensemble-based classifiers", Artificial Intelligence Review, 33(1-2), 1-39, 2010.
34. Rousset, P., et al.,"Characterisation of the torrefaction of beech wood using NIRS: Combined effects of temperature and duration", Biomass and bioenergy, 35(3), 1219-1226, 2011.
35. Safarian, S., Unnþórsson, R.,Richter, C.,"A review of biomass gasification modelling", Renewable and Sustainable Energy Reviews, 110, 378-391, 2019.
36. Sandak, A., Sandak, J.,Negri, M.,"Relationship between near-infrared (NIR) spectra and the geographical provenance of timber", Wood science and technology, 45(1), 35-48, 2011.
37. Schimleck, L., et al.,"Comparison of methods for estimating mechanical properties of wood by NIR spectroscopy", Journal of Spectroscopy, 2018.
38. Schwanninger, M., et al.,"Application of Fourier transform near infrared spectroscopy (FT-NIR) to thermally modified wood", Holz als Roh-und Werkstoff, 62(6), 483-485, 2004.
39. Schwanninger, M., Rodrigues, J.C.,Fackler, K.,"A review of band assignments in near infrared spectra of wood and wood components", Journal of Near Infrared Spectroscopy, 19(5), 287-308, 2011.
40. So, C.-L., et al.,"Near Infrared Spectroscopy in the Forest Products Industry, Forest Products Journal", Forest Products Journal, 54(3), 6-16, 2004.
41. Solomon, S., et al.,"Irreversible climate change due to carbon dioxide emissions", Proceedings of the National Academy of Sciences, 106(6), 1704-1709, 2009.
42. Tang, Z.,Maclennan, J., "Data mining with SQL Server 2005". John Wiley & Sons, 2005.
43. Tsuchikawa, S.,"A review of recent near infrared research for wood and paper", Applied Spectroscopy Reviews, 42(1), 43-71, 2007.
44. Tsuchikawa, S., Yonenobu, H.,Siesler, H.,"Nearinfrared spectroscopic observation of the ageing process in archaeological wood using a deuterium exchange method", Analyst, 130(3), 379-384, 2005.
45. van der Ploeg, T., Austin, P.C.,Steyerberg, E.W.,"Modern modelling techniques are data hungry: a simulation study for predicting dichotomous endpoints", BMC medical research methodology, 14(1), 137, 2014.
46. Vapnik, V., "The nature of statistical learning theory", Springer science & business media, 2013.
47. Via, B.K., Adhikari, S.,Taylor, S.,"Modeling for proximate analysis and heating value of torrefied biomass with vibration spectroscopy", Bioresource technology, 133, 1-8, 2013.
48. Workman Jr, J.,Weyer, L., "Practical guide and spectral atlas for interpretive near-infrared spectroscopy", CRC press, 2012.
49. Xu, M., et al.,"Decision tree regression for soft classification of remote sensing data", Remote Sensing of Environment, 97(3), 322-336, 2005.
50. Yang, H.,Sheng, K.,"Characterization of biochar properties affected by different pyrolysis temperatures using visible-near-infrared spectroscopy", ISRN Spectroscopy, 2012.
51. Yeh, T.-F., Chang, H.-m.,Kadla, J.F.,"Rapid prediction of solid wood lignin content using transmittance nearinfrared spectroscopy", Journal of Agricultural and food chemistry, 52(6), 1435-1439, 2004.
52. Yucel, O., Aydin, E.S.,Sadikoglu, H.,"Comparison of the different artificial neural networks in prediction of biomass gasification products", International Journal of Energy Research, 43(11),5992-6003, 2019.