Advertisement

Neural Computing and Applications

, Volume 31, Issue 12, pp 8823–8836 | Cite as

Predictive modelling of the higher heating value in biomass torrefaction for the energy treatment process using machine-learning techniques

  • P. J. García NietoEmail author
  • E. García-Gonzalo
  • J. P. Paredes-Sánchez
  • A. Bernardo Sánchez
  • M. Menéndez Fernández
Original Article
  • 169 Downloads

Abstract

Torrefaction of biomass can be described as a mild form of pyrolysis at temperatures typically ranging between 200 and 300 °C in the absence of oxygen. Common biomass reactions during torrefaction include devolatilization, depolymerization, and carbonization of hemicellulose, lignin, and cellulose. Torrefaction of biomass improves properties like moisture content as well as calorific value. The aim of this study was to obtain a predictive model able to perform an early detection of the higher heating value (HHV) in a biomass torrefaction process. This study presents a novel hybrid algorithm, based on support vector machines (SVMs) in combination with the particle swarm optimization (PSO) technique, for predicting the HHV of biomass from operation input parameters determined experimentally during the torrefaction process. Additionally, a multilayer perceptron network (MLP) and random forest (RF) were fitted to the experimental data for comparison purposes. To this end, the most important physical–chemical parameters of this industrial process are monitored and analysed. The results of the present study are two-fold. In the first place, the significance of each physical–chemical variables on the HHV is presented through the model. Secondly, several models for forecasting the calorific value of torrefied biomass are obtained. Indeed, when this hybrid PSO–SVM-based model with cubic kernel function was applied to the experimental dataset and regression with optimal hyperparameters was carried out, a coefficient of determination equal to 0.94 was obtained for the higher heating value estimation of torrefied biomass. Furthermore, the results obtained with the MLP approach and RF-based model are worse than the best obtained with the PSO–SVM-based model. The agreement between experimental data and the model confirmed the good performance of the latter. Finally, we expose the conclusions of this study.

Keywords

Support vector machines (SVMs) Particle swarm optimization (PSO) Artificial neural networks (ANNs) Higher heating value (HHV) prediction 

Notes

Acknowledgements

Authors wish to acknowledge the computational support provided by the Department of Mathematics at University of Oviedo. Additionally, we would like to thank Anthony Ashworth for his revision of English grammar and spelling of the manuscript.

Compliance with ethical standards

Conflict of interest

The authors declare no conflict of interest.

References

  1. 1.
    de Alegría M, Mancisidor I, de Basurto D, Uraga P, de Alegría M, Mancisidor I, de Arbulo R, López P (2009) European Union’s renewable energy sources and energy efficiency policy review: the Spanish perspective. Renew Sustain Energy Rev 13(1):100–114Google Scholar
  2. 2.
    Abbasi T, Abbasi SA (2010) Biomass energy and the environmental impacts associated with its production and utilization. Renew Sustain Energy Rev 14(3):919–937Google Scholar
  3. 3.
    Kraxner F, Nordström E-M, Havlík P, Gusti M, Mosnier A, Frank S, Valina H, Fritza S, Fussa S, Kindermanna G, McCalluma I, Khabarova N, Böttchera H, Seea L, Aokia K, Schmide E, Máthég L, Obersteiner M (2013) Global bioenergy scenarios: future forest development, land-use implications, and trade-offs. Biomass Bioenergy 57:86–96Google Scholar
  4. 4.
    Shankar Tumuluru J, Sokhansanj S, Hess JR, Wright CT, Boardman RD (2011) REVIEW: a review on biomass torrefaction process and product properties for energy applications. Ind Biotechnol 7(5):384–401Google Scholar
  5. 5.
    van der Stelt MJC, Gerhauser H, Kiel JHA, Ptasinski KJ (2011) Biomass upgrading by torrefaction for the production of biofuels: a review. Biomass Bioenergy 35(9):3748–3762Google Scholar
  6. 6.
    Bach Q-V, Skreiberg Ø (2016) Upgrading biomass fuels via wet torrefaction: a review and comparison with dry torrefaction. Renew Sustain Energy Rev 54:665–677Google Scholar
  7. 7.
    Prins MJ, Ptasinski KJ, Janssen FJJG (2006) Torrefaction of wood: part 1—weight loss kinetics. J Anal Appl Pyrol 77(1):28–34Google Scholar
  8. 8.
    Chew JJ, Doshi V (2011) Recent advances in biomass pretreatment: torrefaction fundamentals and technology. Renew Sustain Energy Rev 15(8):4212–4222Google Scholar
  9. 9.
    Bates RB, Ghoniem AF (2012) Biomass torrefaction: modeling of volatile and solid product evolution kinetics. Biores Technol 124:460–469Google Scholar
  10. 10.
    Basu P (2013) Biomass gasification, pyrolysis and torrefaction: practical design and theory. Academic Press, New YorkGoogle Scholar
  11. 11.
    Nhuchhen DR, Basu P, Acharya B (2014) A comprehensive review on biomass torrefaction. Int J Renew Energy Biofuels 2014:1–56Google Scholar
  12. 12.
    Chen WH, Peng J, Bi XT (2015) A state-of-the-art review of biomass torrefaction, densification and applications. Renew Sustain Energy Rev 44:847–866Google Scholar
  13. 13.
    Matali S, Rahman NA, Idris SS, Yaacob N, Alias AB (2016) Lignocellulosic biomass solid fuel properties enhancement via torrefaction. Procedia Eng 148:671–678Google Scholar
  14. 14.
    Motghare KA, Rathod AP, Wasewar KL, Labhsetwar NK (2016) Comparative study of different waste biomass for energy application. Waste Manag 47:40–45Google Scholar
  15. 15.
    Liu X, Wang W, Gao X, Zhou Y, Shen R (2012) Effect of thermal pretreatment on the physical and chemical properties of municipal biomass waste. Waste Manag 32(2):249–255Google Scholar
  16. 16.
    Vapnik V (1998) Statistical learning theory. Wiley, New YorkzbMATHGoogle Scholar
  17. 17.
    Haykin S (1999) Neural networks: a comprehensive foundation. Pearson Education Inc., SingapurezbMATHGoogle Scholar
  18. 18.
    Cristianini N, Shawe-Taylor J (2000) An introduction to support vector machines and other kernel-based learning methods. Cambridge University Press, New YorkzbMATHGoogle Scholar
  19. 19.
    Schölkopf B, Smola AJ, Williamson R, Bartlett P (2000) New support vector algorithms. Neural Comput 12(5):1207–1245Google Scholar
  20. 20.
    Hastie T, Tibshirani R, Friedman J (2003) The elements of statistical learning. Springer, New YorkzbMATHGoogle Scholar
  21. 21.
    Hansen T, Wang CJ (2005) Support vector based battery state of charge estimator. J Power Sources 141:351–358Google Scholar
  22. 22.
    Li X, Lord D, Zhang Y, Xie Y (2008) Predicting motor vehicle crashes using support vector machine models. Accid Anal Prev 40:1611–1618Google Scholar
  23. 23.
    Steinwart I, Christmann A (2008) Support vector machines. Springer, New YorkzbMATHGoogle Scholar
  24. 24.
    Kulkarni S, Harman G (2011) An elementary introduction to statistical learning theory. Wiley, New YorkzbMATHGoogle Scholar
  25. 25.
    Kennedy J, Eberhart R (1995) Particle swarm optimization. In: Proceedings of the fourth IEEE international conference on neural networks, vol 4. IEEE Publisher, Perth, pp 1942–1948Google Scholar
  26. 26.
    Eberhart RC, Shi Y, Kennedy J (2001) Swarm intelligence. Morgan Kaufmann, San FranciscoGoogle Scholar
  27. 27.
    Clerc M (2006) Particle swarm optimization. Wiley-ISTE, LondonzbMATHGoogle Scholar
  28. 28.
    Olsson AE (2011) Particle swarm optimization: theory, techniques and applications. Nova Science Publishers, New YorkGoogle Scholar
  29. 29.
    Dorigo M, Stützle T (2004) Ant colony optimization. Bradford Publisher, CambridgezbMATHGoogle Scholar
  30. 30.
    Panigrahi BK, Shi Y, Lim M-H (2011) Handbook of swarm intelligence: concepts, principles and applications. Springer, BerlinzbMATHGoogle Scholar
  31. 31.
    Karaboga D, Basturk B (2007) A powerful and efficient algorithm for numerical function optimization: artificial bee colony (ABC) algorithm. J Glob Optim 39(3):459–471MathSciNetzbMATHGoogle Scholar
  32. 32.
    Karaboga D, Akay B (2009) A survey: algorithms simulating bee swarm intelligence. Artif Intell Rev 31(1):68–85Google Scholar
  33. 33.
    Karaboga D, Gorkemli B (2014) A quick artificial bee colony (qABC) algorithm and its performance on optimization problems. Appl Soft Comput 23:227–238Google Scholar
  34. 34.
    Fister I, Stranad D, Yang X-S, Fister I Jr (2015) Adaptation and hybridization in nature-inspired algorithms. In: Fister I, Fister I Jr (eds) Adaptation and hybridization in computational intelligence, vol 18. Springer, New York, pp 3–50Google Scholar
  35. 35.
    Shrestla NK, Shukla S (2015) Support vector machine based modeling of evapotranspiration using hydro-climatic variables in a sub-tropical environment. Agric For Meteorol 200:172–184Google Scholar
  36. 36.
    Chen J-L, Li G-S, Wu S-J (2013) Assessing the potential of support vector machine for estimating daily solar radiation using sunshine duration. Energy Convers Manag 75:311–318Google Scholar
  37. 37.
    Zeng J, Qiao W (2013) Short-term solar power prediction using a support vector machine. Renew Energy 52:118–127Google Scholar
  38. 38.
    Ortiz-García EG, Salcedo-Sanz S, Pérez-Bellido AM, Portilla-Figueras JA, Prieto L (2010) Prediction of hourly O3 concentrations using support vector regression algorithms. Atmos Environ 44(35):4481–4488Google Scholar
  39. 39.
    Pal M, Goel A (2007) Estimation of discharge and end depth in trapezoidal channel by support vector machines. Water Resour Manag 21(10):1763–1780Google Scholar
  40. 40.
    Nikoo MR, Mahjouri N (2013) Water quality zoning using probabilistic support vector machines and self-organizing maps. Water Resour Manag 27(7):2577–2594Google Scholar
  41. 41.
    Fine TL (1999) Feedforward neural networks methodology. Springer, New YorkzbMATHGoogle Scholar
  42. 42.
    Breiman L (2001) Random forests. Mach Learn 45(1):5–32zbMATHGoogle Scholar
  43. 43.
    Mitchell TM (1997) Machine learning. McGraw-Hill Company Inc, New YorkzbMATHGoogle Scholar
  44. 44.
    Nocquet T, Dupont C, Commandre J, Grateau M, Thiery S, Salvador S (2014) Volatile species release during torrefaction of wood and its macromolecular constituents: part 1—experimental study. Energy 72:180–187Google Scholar
  45. 45.
    Nocquet T, Dupont C, Commandre J, Grateau M, Thiery S, Salvador S (2014) Volatile species release during torrefaction of biomass and its macromolecular constituents: part 2—modeling study. Energy 72:188–194Google Scholar
  46. 46.
    Bychkov AL, Denkin AI, Tikhova VD, Lomovsky OI (2017) Prediction of higher heating values of plant biomass from ultimate analysis data. J Therm Anal Calorim 130(3):1399–1405Google Scholar
  47. 47.
    Galhano dos Santos R, Bordado JC, Mateus MM (2018) Estimation of HHV of lignocellulosic biomass towards hierarchical cluster analysis by Euclidean’s distance method. Fuel 221:72–77Google Scholar
  48. 48.
    Peduzzi E, Boissonnet G, Maréchal F (2016) Biomass modelling: estimating thermodynamic properties from the elemental composition. Fuel 181:207–217Google Scholar
  49. 49.
    Ghugare SB, Tiwary S, Elangovan V, Tambe SS (2014) Prediction of higher heating value of solid biomass fuels using artificial intelligence formalisms. Bioenergy Res 7(2):681–692Google Scholar
  50. 50.
    Estiati I, Freire FB, Freire JT, Aguado R, Olazar M (2016) Fitting performance of artificial neural networks and empirical correlations to estimate higher heating values of biomass. Fuel 180:377–383Google Scholar
  51. 51.
    Ozveren U (2017) An artificial intelligence approach to predict gross heating value of lignocellulosic fuels. J Energy Inst 90(3):397–407Google Scholar
  52. 52.
    Erol M, Haykiri-Acma H, Küçükbayrak S (2010) Calorific value estimation of biomass from their proximate analyses data. Renew Energy 35(1):170–173Google Scholar
  53. 53.
    Vargas-Moreno JM, Callejón-Ferre AJ, Pérez-Alonso J, Velázquez-Martí B (2012) A review of the mathematical models for predicting the heating value of biomass materials. Renew Sustain Energy Rev 16(5):3065–3083Google Scholar
  54. 54.
    Demirbas A (2004) Linear equations on thermal degradation products of wood chips in alkaline glycerol. Energy Convers Manag 45:983–994Google Scholar
  55. 55.
    Energy Research Centre of the Netherlands (ECN) (2018) Research database for biomass and waste. https://www.ecn.nl/phyllis2/. Accessed 5 July 2018
  56. 56.
    Chen Q, Zhou J, Liu B, Mei Q, Luo Z (2011) Influence of torrefaction pretreatment on biomass gasification technology. Chin Sci Bull 56(14):1449–1456Google Scholar
  57. 57.
    Phanphanich M, Mani S (2011) Impact of torrefaction on the grindability and fuel characteristics of forest biomass. Biores Technol 102(2):1246–1253Google Scholar
  58. 58.
    Rousset P, Aguiar C, Labbé N, Commandré JM (2011) Enhancing the combustible properties of bamboo by torrefaction. Biores Technol 102(17):8225–8231Google Scholar
  59. 59.
    Lu KM, Lee WJ, Chen WH, Liu SH, Lin TC (2012) Torrefaction and low temperature carbonization of oil palm fiber and eucalyptus in nitrogen and air atmospheres. Biores Technol 123:98–105Google Scholar
  60. 60.
    Peng JH, Bi HT, Lim CJ, Sokhansanj S (2013) Study on density, hardness, and moisture uptake of torrefied wood pellets. Energy Fuels 27(2):967–974Google Scholar
  61. 61.
    Callejón-Ferre AJ, Velázquez-Martí B, López-Martínez JA, Manzano-Agügliaro F (2011) Greenhouse crop residues: energy potential and models for the prediction of their higher heating value. Renew Sustain Energy Rev 15:948–955Google Scholar
  62. 62.
    Saidur R, Abdelaziz EA, Demirbas A, Hossain MS, Mekhilef S (2011) A review on biomass as a fuel for boilers. Renew Sustain Energy Rev 15(5):2262–2289Google Scholar
  63. 63.
    Yin C-Y (2011) Prediction of higher heating values of biomass from proximate and ultimate analyses. Fuel 90:1128–1132Google Scholar
  64. 64.
    Ziani R, Felkaoui A, Zegadi R (2017) Bearing fault diagnosis using multiclass support vector machines with binary particle swarm optimization and regularized Fisher’s criterion. J Intell Manuf 28:405–417Google Scholar
  65. 65.
    De Leone R, Pietrini M, Giovannelli A (2015) Photovoltaic energy production forecast using support vector regression. Neural Comput Appl 26:1955–1962Google Scholar
  66. 66.
    de Cos Juez FJ, García Nieto PJ, Martínez Torres J, Taboada Castro J (2010) Analysis of lead times of metallic components in the aerospace industry through a supported vector machine model. Math Comput Model 52:1177–1184Google Scholar
  67. 67.
    Shawe-Taylor J, Cristianini N (2004) Kernel methods for pattern analysis. Cambridge University Press, New YorkzbMATHGoogle Scholar
  68. 68.
    Simon D (2013) Evolutionary optimization algorithms. Wiley, New YorkGoogle Scholar
  69. 69.
    Yang X-S, Cui Z, Xiao R, Gandomi AH, Karamanoglu M (2013) Swarm intelligence and bio-inspired computation: theory and applications. Elsevier, LondonGoogle Scholar
  70. 70.
    Clerc M (2012) Standard particle swarm optimisation: from 2006 to 2011. Technical report. http://clerc.maurice.free.fr/pso/SPSO_descriptions.pdf. Accessed 23 Sept 2012
  71. 71.
    Breiman L, Friedman J, Olshen RA, Stone CJ (1984) Classification and regression trees. The Wadsworth statistics/probability series. Wadsworth, BelmontGoogle Scholar
  72. 72.
    Quinlan JR (1993) C4.5 programs for machine learning. Morgan Kaurmann, San MateoGoogle Scholar
  73. 73.
    Rodriguez-Galiano V, Mendes MP, Garcia-Soldado MJ, Chica-Olmo M, Ribeiro L (2014) Predictive modeling of groundwater nitrate pollution using random forest and multisource variables related to intrinsic and specific vulnerability: a case study in an agricultural setting (southern Spain). Sci Total Environ 476–477:189–206Google Scholar
  74. 74.
    Wang L, Zhou X, Zhu X, Dong Z, Guo W (2016) Estimation of biomass in wheat using random forest regression algorithm and remote sensing data. Crop J 4:212–219Google Scholar
  75. 75.
    Genuer R, Poggi J-M, Tuleau-Malot C, Villa-Vialaneix N (2017) Random forests for big data. Big Data Res 9:28–46Google Scholar
  76. 76.
    Wasserman L (2003) All of statistics: a concise course in statistical inference. Springer, New YorkzbMATHGoogle Scholar
  77. 77.
    Freedman D, Pisani R, Purves R (2007) Statistics. W.W. Norton & Company, New YorkzbMATHGoogle Scholar
  78. 78.
    Picard R, Cook D (1984) Cross-validation of regression models. J Am Stat Assoc 79(387):575–583MathSciNetzbMATHGoogle Scholar
  79. 79.
    Efron B, Tibshirani R (1997) Improvements on cross-validation: the.632 + bootstrap method. J Am Stat Assoc 92(438):548–560MathSciNetzbMATHGoogle Scholar
  80. 80.
    Chang C-C, Lin C-J (2011) LIBSVM: a library for support vector machines. ACM Trans Intell Syst and Technol 2:1–27Google Scholar
  81. 81.
    Hall M, Frank E, Holmes G, Pfahringer B, Reutemann P, Witten IH (2009) The WEKA data mining software: an update. ACM SIGKDD Explor Newsl 11(1):10–18Google Scholar
  82. 82.
    Witten IH, Frank E, Hall MA, Pal CJ (2016) Data mining: practical machine learning tools and techniques. Morgan Kaufmann, AmsterdamGoogle Scholar
  83. 83.
    Dahlquist E (2013) Biomass as energy source: resources, systems and applications. CRC Press, Boca RatónGoogle Scholar
  84. 84.
    Wang S, Luo Z (2016) Pyrolisis of biomass. De Gruyter Ltd, WarsawGoogle Scholar

Copyright information

© Springer-Verlag London Ltd., part of Springer Nature 2018

Authors and Affiliations

  1. 1.Department of Mathematics, Faculty of SciencesUniversity of OviedoOviedoSpain
  2. 2.Department of Energy, College of Mining, Energy and Materials EngineeringUniversity of OviedoOviedoSpain
  3. 3.Department of Mining Technology, Topography and StructuresUniversity of LeónLeónSpain

Personalised recommendations