A Comparative Study of Machine Learning Methods for Pyrolysis Yield Prediction

Document Type : Regular Article

Authors

1 Process Design and Simulation Research Centre, School of Chemical Engineering, College of Engineering, University of Tehran, Iran

2 1Process Design and Simulation Research Centre, School of Chemical Engineering, College of Engineering, University of Tehran, Iran

3 College of Engineering, University of Tehran

4 Process Engineering Advanced Research Lab (PEARL), Department of Chemical Engineering, Polytechnique Montreal, c.p. 6079, Succ. Centre-ville, Montreal, Canada

5 Department of Chemical Engineering, Indian Institute of Technology Delhi, Hauz Khas, New Delhi, India

Abstract
This paper presents a machine learning-based approach for accurately predicting pyrolysis product yields. Methods such as Linear Regression (LR), K-Nearest Neighbors (KNN), Decision Tree (DT), Support Vector Regression (SVR), Random Forest (RF), and Neural Networks (NN) leverage operating conditions and/or ultimate/proximate analysis data, eliminating the need for reaction kinetics. This innovative approach offers a broader range and higher accuracy of feedstock compared to traditional kinetics-based methods. The KNN model demonstrated superior performance, achieving a correlation coefficient greater than 0.998 and an RMSE of 0.64. These findings provide valuable insights for engineers and practitioners, facilitating the efficient design and operation of pyrolysis units.The selectivity exhibited a notable increase from 2.46 to 5.27. This improvement in selectivity can primarily be attributed to the significantly higher increase in the solubility coefficient of CO2 compared to that of CH4.

Keywords

Subjects


[1] H. W. Ryu, D. H. Kim, J. Jae, S. S. Lam, E. D. Park, and Y. K. Park, 2020. Recent advances in catalytic co-pyrolysis of biomass and plastic waste for the production of petroleum-like hydrocarbons, Bioresource technology, 310, 123473. https://doi.org/10.1016/j.biortech.2020.123473
[2] C. Telmo, J. Lousada, and N. Moreira, Proximate analysis, backwards stepwise regression between gross calorific value, ultimate and chemical analysis of wood, Bioresource technology, 101 (2010) 3808-3815. https://doi.org/10.1016/j.biortech.2010.01.021
[3] D. Ferdous, A. K. Dalai, S. K. Bej, and R. W. Thring, Pyrolysis of lignins: Experimental and kinetics studies, Energy and Fuels, 16 (2002) 1405–1412. https://doi.org/10.1021/ef0200323
[4] X. Ling, D. Lu, J. Wang, M. Liang, S. Zhang, W. Ren, J. Chen, P. Ouyang, Investigation of the kinetics and mechanism of the glycerol chlorination reaction using gas chromatography-mass spectrometry, Journal of the Serbian Chemical Society, 75 (2010) 101-112. https://doi.org/10.2298/JSC1001101L
[5] C. Jia, Y. Li, S. Zhang, T. Fei, and S. Pang, 2018. Thermogravimetric analysis, kinetic study, and pyrolysis–GC/MS analysis of 1,1ʹ-azobis-1,2,3-triazole and 4,4ʹ-azobis-1,2,4-triazole, Chemistry Central Journal, 12, 1. https://doi.org/10.1186/s13065-018-0381-x
[6] Y. A. Dahawi, A. Abdulrazik, M. Nizam, A. Seman, M. Aizudin, A. Aziz, M. Yusri, M. Yunus, Aspen Plus Simulation of Bio-Char Production from a Biomass-Based Slow Pyrolysis Process, Key Engineering Materials, 797 (2019) 336–341. https://doi.org/10.4028/www.scientific.net/KEM.797.336
[7] H. Y. Ismail, A. Abbas, F. Azizi, and J. Zeaiter, Pyrolysis of waste tires: A modeling and parameter estimation study using Aspen Plus®, Waste management, 60 (2017) 482–493. https://doi.org/10.1016/j.wasman.2016.10.024
[8] P. Basu and P. Kaushal, Modeling of pyrolysis and gasification of biomass in fluidized beds: A review, Chemical Product and Process Modeling, 4 (2009) 1. https://doi.org/10.2202/1934-2659.1338
[9] D. Rangel-Martinez, K.D.P Nigam, L.A Ricardez-Sandoval. Machine learning on sustainable energy: A review and outlook on renewable energy systems, catalysis, smart grid and energy storage, Chemical Engineering Research and Design, 174 (2021) 414-441. https://doi.org/10.1016/j.cherd.2021.08.013
[10] B. R. Hough, D. A. C. Beck, D. T. Schwartz, and J. Pfaendtner, Application of machine learning to pyrolysis reaction networks: Reducing model solution time to enable process optimization, Computers & Chemical Engineering, 104 (2017) 56–63. https://doi.org/10.1016/j.compchemeng.2017.04.012
[11] X. Zhu, Y. Li, and X. Wang, 2019. Machine learning prediction of biochar yield and carbon contents in biochar based on biomass characteristics and pyrolysis conditions, Bioresource technology, 288, 121527. https://doi.org/10.1016/j.biortech.2019.121527
[12] A. P. Singh Chouhan and S. P. Singh, Prediction of bio-oil production from biomass by using experimental pyrolysis technique and theoretical estimation by using machine learning techniques, Plant Archives, 20 (2020) 2673–2677.
[13] F. Cheng, H. Luo, and L. M. Colosi, 2020. Slow pyrolysis as a platform for negative emissions technology: An integration of machine learning models, life cycle assessment, and economic analysis, Energy Conversion and Management, 223, 113258. https://doi.org/10.1016/j.enconman.2020.113258
[14] Q. Tang, Y. Chen, H. Yang, M. Liu, H. Xiao, Z. Wu, H. Chen, S. R. Naqvi, Prediction of Bio-oil Yield and Hydrogen Contents Based on Machine Learning Method: Effect of Biomass Compositions and Pyrolysis Conditions, Energy and Fuels, 34 (2020) 11050–11060. https://doi.org/10.1021/acs.energyfuels.0c01893
[15] C. M. Bishop, Pattern Recognition and Machine Learning. Springer, New York, 2006.
[16] L. T. Ford and J. A. Key, Experimental study of effect of pressure on healing of bone, AMA Archives of Surgery, 69 (1954) 627–634. https://doi.org/10.1001/archsurg.1954.01270050031008
[17] D. Y. C. Leung, X. L. Yin, Z. L. Zhao, B. Y. Xu, and Y. Chen, Pyrolysis of tire powder: Influence of operation variables on the composition and yields of gaseous product, Fuel Processing Technology, 79 (2002) 141–155. https://doi.org/10.1016/S0378-3820(02)00109-1
[18] P. T. Williams, S. Besler, and D. T. Taylor, The pyrolysis of scrap automotive tyres. The influence of temperature and heating rate on product composition, Fuel, 69 (1990) 1474–1482. https://doi.org/10.1016/0016-2361(90)90193-T
[19] A. M. Cunliffe and P. T. Williams, Composition of oils derived from the batch pyrolysis of tyres, Journal of Analytical and applied Pyrolysis, 44 (1998) 131–152. https://doi.org/10.1016/S0165-2370(97)00085-5
[20] M. F. Laresgoiti, B. M. Caballero, I. De Marco, A. Torres, M. A. Cabrero, and M. J. Chomón, Characterization of the liquid products obtained in tyre pyrolysis, Journal of analytical and applied pyrolysis, 71 (2004) 917–934. https://doi.org/10.1016/j.jaap.2003.12.003
[21] S. Galvagno, S. Casu, T. Casabianca, A. Calabrese, and G. Cornacchia, Pyrolysis process for the treatment of scrap tyres: Preliminary experimental results, Waste Management, 22 (2002) 917–923. https://doi.org/10.1016/S0956-053X(02)00083-1
[22] X. Zhang, T. Wang, L. Ma, and J. Chang, Vacuum pyrolysis of waste tires with basic additives, Waste Management, 28 (2008) 2301–2310. https://doi.org/10.1016/j.wasman.2007.10.009
[23] C. Díez, O. Martínez, L. F. Calvo, J. Cara, and A. Morán, Pyrolysis of tyres. Influence of the final temperature of the process on emissions and the calorific value of the products recovered, Waste Management, 24 (2004) 463–469. https://doi.org/10.1016/j.wasman.2003.11.006
[24] C. Berrueco, E. Esperanza, F. J. Mastral, J. Ceamanos, and P. García-Bacaicoa, Pyrolysis of waste tyres in an atmospheric static-bed batch reactor: Analysis of the gases obtained, Journal of Analytical and Applied Pyrolysis, 74 (2005) 245–253. https://doi.org/10.1016/j.jaap.2004.10.007
[25] J. D. Martínez, N. Puy, R. Murillo, T. García, M. V. Navarro, and A. M. Mastral, Waste tyre pyrolysis - A review, Renewable and sustainable energy reviews, 23 (2013) 179–213. https://doi.org/10.1016/j.rser.2013.02.038
[26] M. Kyari, A. Cunliffe, and P. T. Williams, Characterization of oils, gases, and char in relation to the pyrolysis of different brands of scrap automotive tires, Energy and Fuels, 19 (2005) 1165–1173. https://doi.org/10.1021/ef049686x
[27] X. Wang, S. R. A. Kersten, W. Prins, and W. P. M. Van Swaaij, Biomass pyrolysis in a fluidized bed reactor. Part 2: Experimental validation of model results, Ind. Eng. Chem. Res., 44 (2005) 8786–8795. https://doi.org/10.1021/ie050486y
[28] Ö. Onay, S. H. Beis, and Ö. M. Koçkar, Pyrolysis of walnut shell in a well-swept fixed-bed reactor, Energy Sources, 26 (2004) 771–782. https://doi.org/10.1080/00908310490451402
[29] I. Demiral and S. Şensöz, Fixed-bed pyrolysis of hazelnut (Corylus Avellana L.) bagasse: Influence of pyrolysis parameters on product yields, Energy Sources, Part A: Recovery, Utilization, and Environmental Effects, 28 (2006) 1149–1158. https://doi.org/10.1080/009083190966126
[30] J. K. Sarkar and Q. Wang, 2020. Different pyrolysis process conditions of South Asian waste coconut shell and characterization of gas, bio-char, and bio-oil, Energies, 13, 8. https://doi.org/10.3390/en13081970
[31] T. Rout, D. Pradhan, R. K. Singh, and N. Kumari, Exhaustive study of products obtained from coconut shell pyrolysis, Journal of environmental chemical engineering, 4 (2016) 3696-3705. https://doi.org/10.1016/j.jece.2016.02.024
[32] W. T. Tsai, M. K. Lee, and Y. M. Chang, Fast pyrolysis of rice straw, sugarcane bagasse and coconut shell in an induction-heating reactor, Journal of analytical and applied pyrolysis, 76 (2006) 230–237. https://doi.org/10.1016/j.jaap.2005.11.007
[33] L. Qin, Y. Shao, Z. Hou, and E. Jiang, Effect of temperature on the physicochemical characteristics of pine nut shell pyrolysis products in a screw reactor, Energy Sources, Part A Recover. Utilization, and Environmental Effects, 42 (2020) 2831–2843. https://doi.org/10.1080/15567036.2019.1618993
[34] J. M. Encinar and J. F. González, Pyrolysis of synthetic polymers and plastic wastes. Kinetic study, Fuel Processing Technology, 89 (2008) 678–686. https://doi.org/10.1016/j.fuproc.2007.12.011
[35] S. Şensöz and M. Can, Pyrolysis of pine (Pinus Brutia Ten.) chips: 1. Effect of pyrolysis temperature and heating rate on the product yields, Energy Sources, 24 (2002) 347–355. https://doi.org/10.1080/00908310252888727
[36] M. Garcia-Perez, X. S. Wang, J. Shen, M. J. Rhodes, F. Tian, W. J. Lee, H. Wu, C. Z. Li, Fast pyrolysis of oil mallee woody biomass: Effect of temperature on the yield and quality of pyrolysis products, Industrial & engineering chemistry research, 47 (2008) 1846–1854. https://doi.org/10.1021/ie071497p
[37] A. López, I. de Marco, B. M. Caballero, M. F. Laresgoiti, and A. Adrados, Influence of time and temperature on pyrolysis of plastic wastes in a semi-batch reactor, Chemical Engineering Journal, 173 (2011) 62–71. https://doi.org/10.1016/j.cej.2011.07.037
[38] X. Wang, Q. Jin, J. Zhang, Y. Li, S. Li, H. Mikulčić, M. Vujanović, H. Tan, N. Duić, Soot formation during polyurethane (PU) plastic pyrolysis: The effects of temperature and volatile residence time, Energy Conversion and Management, 164 (2018) 353–362. https://doi.org/10.1016/j.enconman.2018.02.082
[39] J. Yu, L. Sun, C. Berrueco, B. Fidalgo, N. Paterson, and M. Millan, Influence of temperature and particle size on structural characteristics of chars from Beechwood pyrolysis, Journal of Analytical and Applied Pyrolysis, 130 (2017) 249–255. https://doi.org/10.1016/j.jaap.2018.01.018
[40] P. Das and P. Tiwari, The effect of slow pyrolysis on the conversion of packaging waste plastics (PE and PP) into fuel, Waste Management, 79 (2018) 615–624. https://doi.org/10.1016/j.wasman.2018.08.021
[41] S. H. Beis, Ö. Onay, and Ö. M. Koçkar, Fixed-bed pyrolysis of safflower seed: Influence of pyrolysis parameters on product yields and compositions, Renewable energy, 26 (2002) 21–32. https://doi.org/10.1016/S0960-1481(01)00109-4
[42] B. Xu and A. Li, 2017. Effect of high-pressure on pine sawdust pyrolysis: Products distribution and characteristics, AIP Conference Proceedings, 1864, 020116. https://doi.org/10.1063/1.4992933
[43] G. Lopez, M. Olazar, R. Aguado, G. Elordi, M. Amutio, M. Artetxe, J. Bilbao, Vacuum pyrolysis of waste tires by continuously feeding into a conical spouted bed reactor, Industrial & engineering chemistry research, 49 (2010) 8990–8997. https://doi.org/10.1021/ie1000604
[44] I. Cortes-Ciriano and A. Bender, Improved Chemical Structure-Activity Modeling Through Data Augmentation, Journal of chemical information and modeling, 55 (2015) 2682–2692. https://doi.org/10.1021/acs.jcim.5b00570