Abstract
The pyrolysis process enables the transformation of plastic waste into products such as oil, solid residue, and gas at temperatures of around 300–900 °C by thermal decomposition. Conversion of such waste into valuable products depends on various factors, such as raw material composition, temperature, heating rate, residence time, and catalyst. From this point of view, in this study, predictions of gas product yield based on different pyrolysis conditions including waste types (LDPE–C/LDPE), temperature (400–600–800 °C), heating rate (5–10–20 °C/min), type of catalyst (zeolite-clay-sludge) and amount of catalyst (5%, 10%, 15%, by weight) were carried out with support from the vector regression (SVR) and the Gaussian process (GPR) models using the results of experimental studies performed under various conditions. Different kernel functions were used for SVR (Linear, Quadratic, Cubic, Gaussian) and GPR (Squared Exponential, Matern 5/2, Exponential, Rational Quadratic). The Gaussian Kernel Function presented a good prediction performance (89% R2 and 0.0011 RMSE) for SVR while the Exponential Kernel Function was the most appropriate for GPR (93% R2 and 0.0011 RMSE). On the other hand, the deviations in the SVR model with linear Kernel change over a wide range of 0.25–80.85%, and the GPR model with exponential kernel show deviations close to each other in the range of 0.06–3.91%. The present study provides new information for future studies by understanding the pyrolysis process of plastic waste and predicting product yield.
Similar content being viewed by others
References
Abbas-Abadi MS, Haghighi MN, Yeganeh H (2012) The effect of temperature, catalyst, different carrier gases, and stirrer on the produced transportation hydrocarbons of LLDPE degradation in a stirred reactor. J Anal Appl Pyrolysis 95:198–204. https://doi.org/10.1016/j.jaap.2012.02.007
Abd El Aziz MAE, Hemdan AM, Ewees AA, Elhoseny M, Shehab A, Hassanien AE, Xiong S (2017) Prediction of biochar yield using adaptive neuro-fuzzy inference system with particle swarm optimization. In: 2017 IEEE PES PowerAfrica, pp 115–120. https://doi.org/10.1109/PowerAfrica.2017.7991209
Achilias DS, Roupakias C, Megalokonomos P, Lappas AA, Antonakou EV (2007) Chemical recycling of plastic wastes made from polyethylene (LDPE and HDPE) and polypropylene (PP). J Hazard Mater 149(3):536–542. https://doi.org/10.1016/j.jhazmat.2007.06.076
Acı M, Avcı M, Ac Ç (2017) Reducing simulation duration of carbon nanotube using support vector regression method. J Fac Eng Archit Gaz 32(3):901–907. https://doi.org/10.17341/gazimmfd.337642
Adrados A, De Marco I, Caballero BM, López A, Laresgoiti MF, Torres A (2012) Pyrolysis of plastic packaging waste: a comparison of plastic residuals from material recovery facilities with simulated plastic waste. Waste Manag 32(5):826–832. https://doi.org/10.1016/j.wasman.2011.06.016
Agullo J, Kumar N, Berenguer D, Kubicka D, Marcilla A, Gómez A et al (2007) Catalytic pyrolysis of low density polyethylene over H-β, HY, H-Mordenite, and H-Ferrierite zeolite catalysts: influence of acidity and structures. Kinet Catal 48(4):535–540. https://doi.org/10.1134/S002315840704009X
Ahmad MW, Mourshed M, Rezgui Y (2018) Tree-based ensemble methods for predicting PV power generation and their comparison with support vector regression. Energy 164:465–474. https://doi.org/10.1016/j.energy.2018.08.207
Almasov A, Onur M (2020) Life-Cycle optimization of the CO2 huff-N-puff process in an unconventional oil reservoir using least-squares support-vector and gaussian process regression proxies. Paper presented at the SPE annual technical conference and exhibition, virtual, October 2020. Paper Number: SPE-201721-MS. https://doi.org/10.2118/201721-MS
Al-Salem SM, Antelava A, Constantinou A, Manos G, Dutta A (2017) A review on thermal and catalytic pyrolysis of plastic solid waste (PSW). J Environ Manag 197:177–198. https://doi.org/10.1016/j.jenvman.2017.03.084
ASTM D-3172-73 Standard method for proximate analysis of coal and coke. United States: N. p., 1975
ASTM D-3173-85 Standard test method for moisture analysis sample of coal and coke. United States: N. p., 1987
ASTM D-3174-82 Standard test method for ash in the analysis sample of coal and coke. United States: N. p., 1998
ASTM D-3175-82 Standard test method for volatile matter in the analysis sample of coal and coke
Bagri R, Williams PT (2002) Catalytic pyrolysis of polyethylene. J Anal Appl Pyrolysis 63(1):29–41. https://doi.org/10.1016/S0165-2370(01)00139-5
Boisberranger et al (2021) Gaussian processes. Scikit Learn. https://scikit-learn.org/stable/modules/gaussian_process.html. Accessed 25 Nov 2021
Cao H, Xin Y, Yuan Q (2016) Prediction of biochar yield from cattle manure pyrolysis via least squares support vector machine intelligent approach. Bioresour Technol 202:158–164. https://doi.org/10.1016/j.biortech.2015.12.024
Ceylan Z (2020) Estimation of municipal waste generation of Turkey using socio-economic indicators by Bayesian optimization tuned Gaussian process regression. Waste Manag Res 38(8):840–850. https://doi.org/10.1177/0734242X20906877
Cervantes J, Garcia-Lamont F, Rodriquez-Mazahua L, Lopez A (2020) A comprehensive survey on support vector machine classification: applications, challenges and trends. Neurocomputing 408:189–215. https://doi.org/10.1016/j.neucom.2019.10.118
Chen X, Zhang H, Song Y, Xiao R (2018) Prediction of product distribution and bio-oil heating value of biomass fast pyrolysis. Chem Eng Process Process Intensif 130:36–42. https://doi.org/10.1016/j.cep.2018.05.018
Chu W, Keerthi SS, Ong CJ (2004) Bayesian support vector regression using a unified loss function. IEEE Trans Neural Netw 15(1):29–44. https://doi.org/10.1109/TNN.2003.820830
Dahlbo H, Poliakova V, Mylläri V, Sahimaa O, Anderson R (2018) Recycling potential of post-consumer plastic packaging waste in Finland. Waste Manag 71:52–61. https://doi.org/10.1016/j.wasman.2017.10.033
Demirbas A (2004) Pyrolysis of municipal of plastic wastes for recovery of gasoline-range hydrocarbons. J Anal Appl Pyrolysis 72(1):97–102. https://doi.org/10.1016/j.jaap.2004.03.001
Deng Z, Hu X, Lin X, Che Y, Xu L, Guo W (2020) Data-driven state of charge estimation for lithium-ion battery packs based on Gaussian process regression. Energy 205:118000. https://doi.org/10.1016/j.energy.2020.118000
Donaj PJ, Kaminsky W, Buzeto F, Yang W (2012) Pyrolysis of polyolefins for increasing the yield of monomers’ recovery. Waste Manag 32(5):840–846. https://doi.org/10.1016/j.wasman.2011.10.009
Elbeltagi A, Azad N, Arshad A et al (2021) Applications of Gaussian process regression for predicting blue water footprint: Case study in Ad Daqahliyah. Egypt Agric Water Manag 255:107052. https://doi.org/10.1016/j.agwat.2021.107052
Erdoğan S (2020) Recycling of waste plastics into pyrolytic fuels and their use in IC engines. Sustain Mobility. https://doi.org/10.5772/intechopen.90639
Ewees AA, Abd Elaziz M (2018) Improved adaptive neuro-fuzzy inference system using gray wolf optimization: a case study in predicting biochar yield. Int J Intell Syst Int 29(1):924–940. https://doi.org/10.1515/jisys-2017-0641
Goll MFGH, Venzon JS, Vegini AA, Eleotério JR, Tavares LBB (2018) Composites based on low-density polyethylene combined with PET coated SBS paperboard shavings. Matéria (rio De Janeiro). https://doi.org/10.1590/s1517-707620180004.0582
Gopinath S, Devan PK, Pitchandi K (2020) Production of pyrolytic oil from ULDP plastics using silica-alumina catalyst and used as fuel for DI diesel engine. RSC Adv 10(61):37266–37279. https://doi.org/10.1039/D0RA07073D
Hashemitaheri M, Mekarthy SMR, Cherukuri H (2020) Prediction of specific cutting forces and maximum tool temperatures in orthogonal machining by Support Vector and Gaussian Process Regression Methods. Procedia Manuf 48:1000–1008. https://doi.org/10.1016/j.promfg.2020.05.139
Hastie T, Tibshirani R, Friedman J (2009) The elements of statistical learnin. 2nd edn. Springer-Verlag Cited on 33.
Henrique BM, Sobreiro VA, Kimura H (2018) Stock price prediction using support vector regression on daily and up to the minute prices. J Finance Data Sci 4(3):183–201. https://doi.org/10.1016/j.jfds.2018.04.003
Hussain Z, Khatak M, Khan KM, Naz MY, AbdEl-Salam NM, Ibrahim KA (2020) Production of oil and gas through thermal and thermo-catalytic pyrolysis of waste polyethylene. Monatsh Chem 151(9):1475–1483. https://doi.org/10.1007/s00706-020-02656-9
İnce H, İmamoğlu SZ (2016) Supplier selection with support vector regression and twin support vector regression. Dogus Univ J 17(2):241–253
Jalalifar S, Masoudi M, Abbassi R, Garaniya V, Ghiji M, Salehi F (2020) A hybrid SVR-PSO model to predict a CFD-based optimised bubbling fluidised bed pyrolysis reactor. Energy 191:116414. https://doi.org/10.1016/j.energy.2019.116414
Jeswani H, Krüger C, Russ M, Horlacher M et al (2021) Life cycle environmental impacts of chemical recycling via pyrolysis of mixed plastic waste in comparison with mechanical recycling and energy recovery. Sci Total Environ 769:144483. https://doi.org/10.1016/j.scitotenv.2020.144483
Kaminsky W, Zorriqueta I-JN (2007) Catalytical and thermal pyrolysis of polyolefins. J Anal Appl Pyrolysis 79(1–2):68–374. https://doi.org/10.1016/j.jaap.2006.11.005
Khan MS, Kaneesamkandi Z (2013) Biodegradable waste to biogas: renewable energy option for the Kingdom of Saudi Arabia. Int J Innov Appl Stud 4(1):101–113
Kulkarni AK, Daneshvarhosseini S, Yoshida H (2011) Effective recovery of pure aluminum from waste composite laminates by sub-and super-critical water. J Supercrit Fluids 55(3):992–997. https://doi.org/10.1016/j.supflu.2010.09.007
Kumar AK, Singh RK, Mishra DK (2010) Thermolysis of waste plastics to liquid fuel. A suitable method for plastic waste management and manufacture of value added products: a world prospective. Renew Sust Energ Rev 14(1):233–248. https://doi.org/10.1016/j.rser.2009.07.005
Kumar S, Singh E, Mishra R, Kumar A, Caucci S (2021) Utilization of plastic wastes for sustainable environmental management: a review. Chem Sus Chem 14(19):3985–4006. https://doi.org/10.1002/cssc.202101631
Li X, Shen B, Guo Q, Gao J (2007) Effects of large pore zeolite additions in the catalytic pyrolysis catalyst on the light olefins production. Catal Today 125(3–4):270–277. https://doi.org/10.1016/j.cattod.2007.03.021
Liu Y, Mu Y, Chen K, Li Y, Guo J (2020) Daily activity feature selection in smart homes based on pearson correlation coefficient. Neural Process Lett 51:1771–1787. https://doi.org/10.1007/s11063-019-10185-8
Mahdaviara M, Rostami A, Keivanimehr F, Shahbazi K (2021) Accurate determination of permeability in carbonate reservoirs using Gaussian Process Regression. J Pet Sci Eng 196:107807. https://doi.org/10.1016/j.petrol.2020.107807
Marcilla A, Gómez-Siurana A, Valdés F (2007) Catalytic pyrolysis of LDPE over H-beta and HZSM-5 zeolites in dynamic conditions: Study of the evolution of the process. J Anal Appl Pyrolysis 79(1–2):433–442. https://doi.org/10.1016/j.jaap.2006.09.006
Mastral JF, Berrueco C, Gea M, Ceamanos J (2006) Catalytic degradation of high-density polyethylene over nanocrystalline HZSM-5 zeolite. Polym Degrad Stab 91(12):3330–3338. https://doi.org/10.1016/j.polymdegradstab.2006.06.009
Merdun H, Sezgin İV (2018) Modeling of pyrolysis product yields by artificial neural networks. Int J Renew Energy Res 8(2):1178–1188. https://doi.org/10.20508/ijrer.v8i2.7489.g7403
Miandad R, Barakat MA, Aburiazaiza AS, Rehan M, Nizami AS (2016) Catalytic pyrolysis of plastic waste: a review. Process Saf Environ Prot 102:822–838. https://doi.org/10.1016/j.psep.2016.06.022
Mighani M, Shahi A, Antonioni G (2017) Catalytic pyrolysis of plastic waste products: time series modeling using least square support vector machine and artificial neural network. In: 16th international conference on sustainable energy technologies, Set 2017, Bologna, Italy pp 1–10
Mishra N, Patra N, Pandey S, Salerno M et al (2014) Taguchi method optimization of wax production from pyrolysis of waste polypropylene. J Therm Anal Calorim 117(2):885–892. https://doi.org/10.1007/s10973-014-3793-4
Moazenzadeh R, Mohammadi B, Shamshirband S, Chau K (2018) Coupling a firefly algorithm with support vector regression to predict evaporation in northern Iran. Eng Appl Comput Fluid Mech 12(1):584–597. https://doi.org/10.1080/19942060.2018.1482476
Mumladze T, Yousef S, Tatariants M, Kriūkienė R, Makarevicius V, Lukošiūtė SI et al (2018) Sustainable approach to recycling of multilayer flexible packaging using switchable hydrophilicity solvents. Green Chem 20(15):3604–3618. https://doi.org/10.1039/C8GC01062E
Na JG, Jeong BH, Chung SH, Kim SS (2006) Pyrolysis of low-density polyethylene using synthetic catalysts produced from fly ash. J Mater Cycles Waste Manage 8(2):126–132. https://doi.org/10.1007/s10163-006-0156-7
Ofoma I (2006) Catalytic pyrolysis of polyolefins. Dissertation, Atlanta Georgia Institute of Technology. http://hdl.handle.net/1853/10439
Okan M, Aydin HM, Barsbay M (2019) Current approaches to waste polymer utilization and minimization: a review. J Chem Technol Biotechnol 94(1):8–21. https://doi.org/10.1002/jctb.5778
Onwudili JA, Insura N, Williams PT (2009) Composition of products from the pyrolysis of polyethylene and polystyrene in a closed batch reactor: effects of temperature and residence time. J Anal Appl Pyrolysis 86(2):293–303. https://doi.org/10.1016/j.jaap.2009.07.008
PAGEV (2020) Turkish plastic industry follow-up report 2020/9. https://pagev.org/turkiye-plastik-sektor-izleme-raporu-2020-9 Accessed 8 Dec 2020
Pan D, Su F, Liu C et al (2020) Research progress for plastic waste management and manufacture of value-added products. Adv Compos Hybrid Mater 3:443–461. https://doi.org/10.1007/s42114-020-00190-0
Panda AK, Alotaibi A, Kozhevnikov IV, Shiju NR et al (2020) Pyrolysis of plastics to liquid fuel using sulphated zirconium hydroxide catalyst. Waste Biomass Valoriz 11(11):6337–6345. https://doi.org/10.1007/s12649-019-00841-4
Parbat D, Chakraborty M (2020) A python based support vector regression model for prediction of COVID19 cases in India. Chaos Solitons Fract 130:109942. https://doi.org/10.1016/j.chaos.2020.109942
Park DW, Hwang EY, Kim JR, Choi JK, Kim YA, Woo HC (1999) Catalytic degradation of polyethylene over solid acid catalysts. Polym Degrad Stab 65(2):193–198. https://doi.org/10.1016/S0141-3910(99)00004-X
Pathy A, Meher S, Balasubramanian P (2020) Predicting algal biochar yield using eXtreme Gradient Boosting (XGB) algorithm of machine learning methods. Algal Res 50:102006. https://doi.org/10.1016/j.algal.2020.102006
Payne J, McKeown P, Jones MD (2019) A circular economy approach to plastic waste. Polym Degrad Stab 165:170–181. https://doi.org/10.1016/j.polymdegradstab.2019.05.014
Plastic Europe (2019) Plastics the facts 2019. https://www.plasticseurope.org/application/files/9715/7129/9584/FINAL_web_version_Plastics_the_facts2019_14102019.pdf. Accessed 10 Dec 2020
Quan Q, Hao Z, Xifeng H, Jingchun L (2020) Research on water temperature prediction based on improved support vector regression. Neural Comput Appl. https://doi.org/10.1007/s00521-020-04836-4
Schulz E, Speekenbrink M, Krause A (2018) A tutorial on Gaussian process regression: modelling, exploring, and exploiting functions. J Math Psychol 85:1–16. https://doi.org/10.1016/j.jmp.2018.03.001
Serrano DP, Aguado J, Escola JM, Rodríguez JM (2005) Influence of nanocrystalline HZSM-5 external surface on the catalytic cracking of polyolefins. J Anal Appl Pyrolysis 74(1–2):353–360. https://doi.org/10.1016/j.jaap.2004.11.037
Shabani S, Samadian S, Sattari MT, Mosavi A, Shamshirband S, Kmet T, Varkonyi-Koczy AR (2020) Modeling pan evaporation using gaussian process regression K-nearest neighbors random forest and support vector machines. Compar Anal Atmos 11(1):66. https://doi.org/10.3390/atmos11010066
Sharifzadeh M, Sikinioti-Lock A, Shah N (2019) Machine-learning methods for integrated renewable power generation: a comparative study of artificial neural networks, support vector regression, and Gaussian Process Regression. Renew Sust Energ Rev 108:513–538. https://doi.org/10.1016/j.rser.2019.03.040
Siddiqui MZ, Park YK, Kang Y, Watanabe A, Kim S, Kim YM (2019) Effective use of aluminum-plastic laminate as a feedstock for catalytic pyrolysis over micro and mesoporous catalysts. J Cleaner Prod 229:1093–1101. https://doi.org/10.1016/j.jclepro.2019.04.404
Siddiqui MN, Redhwi HH (2009) Pyrolysis of mixed plastics for the recovery of useful products. Fuel Process Technol 90:545–552. https://doi.org/10.1016/j.fuproc.2009.01.003
Sit H (2021) A quick guide to understanding Gaussian process regression (GPR) and using scikit-learn’s GPR package. Towards Data Science. https://towardsdatascience.com/quick-start-to-gaussian-process-regression-36d838810319. Accessed 25 Nov 2021
Soliman A, Farag HA, Nassef E, Amer A, ElTaweel Y (2020) Pyrolysis of low-density polyethylene waste plastics using mixtures of catalysts. J Mater Cycles Waste Manag 22(5):1399–1406. https://doi.org/10.1007/s10163-020-01028-z
Stan F, Stanciu NV, Fetecau C, Sandu IL (2019) Mechanical recycling of low-density polyethylene/carbon nanotube composites and its effect on material properties. J Manuf Sci Eng 141(9):091004. https://doi.org/10.1115/1.4044101
Sun Y, Liu L, Wang Q, Yang X, Tu X (2016) Pyrolysis products from industrial waste biomass based on a neural network model. J Anal Appl Pyrolysis 120:94–102. https://doi.org/10.1016/j.jaap.2016.04.013
Tang Q, Chen Y, Yang H, Liu M, Xiao H, Wang S et al (2021) Machine learning prediction of pyrolytic gas yield and compositions with feature reduction methods: effects of pyrolysis conditions and biomass characteristics. Bioresour Technol 339:125581. https://doi.org/10.1016/j.biortech.2021.125581
Ulutas D, Bayrakci E, Cokaygil Z, Ozkan A, Guney Y, Banar M (2014) Geotechnical, chemical and structural characterization of waste clay from boron production. Athens J Technol Eng 1(3):171–179. https://doi.org/10.30958/AJTE.1-3-1
Vapnik VN (1995) The nature of statistical learning. Theory
White RL (2006) Acid‐catalyzed cracking of polyolefins: primary reaction mechanisms. In: Feedstock recycling and pyrolysis of waste plastics: converting waste plastics into diesel and other fuels, pp 43–72. https://doi.org/10.1002/0470021543.ch2
Williams CK (1998) Computation with infinite neural networks. Neural Comput 10(5):203–1216. https://doi.org/10.1162/089976698300017412
Williams C, Rasmussen C (1995) Gaussian processes for regression. Adv Neural Inf Process Syst 8:514–520
Yergök D, Acı M (2019) An alternative approach for daily demand prediction in mass meal production: regression learner. Eur J Sci Theol Special Issue. https://doi.org/10.31590/ejosat.636368
Zhang S, Lin J, Peng Q, Wang D, Yang T, Sorooshian S, Liu X, Zhuang J (2018) Modeling and simulating of reservoir operation using the artificial neural network, support vector regression, deep learning algorithm. J Hydrol 565:720–736. https://doi.org/10.1016/j.jhydrol.2018.08.050
Zhang Y, Xu X (2020a) Relative cooling power modeling of lanthanum manganites using Gaussian process regression. RSC Adv 10(35):20646–20653. https://doi.org/10.1039/D0RA03031G
Zhang Y, Xu X (2020b) Fe-based superconducting transition temperature modeling through Gaussian process regression. J Low Temp Phys 202(1):205–218. https://doi.org/10.1007/s10909-020-02545-9
Zhang F, Zhao Y, Wang D et al (2021) Current technologies for plastic waste treatment: a review. J Cleaner Prod 282:124523. https://doi.org/10.1016/j.jclepro.2020.124523
Zhou Y, Liu Y, Wang D et al (2021) A novel combined multi-task learning and Gaussian process regression model for the prediction of multi-timescale and multi-component of solar radiation. J Cleaner Prod 284:124710. https://doi.org/10.1016/j.jclepro.2020.124710
Zhu X, Li Y, Wang X (2019) Machine learning prediction of biochar yield and carbon contents in biochar based on biomass characteristics and pyrolysis conditions. Bioresour Technol 288:121527. https://doi.org/10.1016/j.biortech.2019.121527
Acknowledgements
This study was supported by the Scientific and Technological Research Council (TUBITAK) (Project No. 117Y041), and Eskişehir Technical University Scientific Research Projects Commission under Grant Nos. 1703F074 and 19ADP167.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that they have no conflict of interest.
Additional information
Editorial responsibility: Q. Aguilar-Virgen.
Rights and permissions
About this article
Cite this article
Yapıcı, E., Akgün, H., Özkan, K. et al. Prediction of gas product yield from packaging waste pyrolysis: support vector and Gaussian process regression models. Int. J. Environ. Sci. Technol. 20, 461–476 (2023). https://doi.org/10.1007/s13762-022-04013-1
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s13762-022-04013-1