Modeling of gross calorific value based on coal properties by support vector regression method

  • E. Hadavandi
  • James C. Hower
  • S. Chehreh Chelgani
Original Article


Gross calorific value (GCV) is one the most important coal combustion parameters for power plants. Modeling of GCV based on coal properties could be a key for estimating the amount of coal consumption in the combustion system of various plants. In this study, support vector regression (SVR) as a powerful prediction method has been used to investigate relationships among coal sample properties with their GCVs for a wide range of records. Variable importance measurement by the SVR method throughout various coal analyses (proximate, ultimate, different sulfur types, and petrography) indicated that carbon, ash, moisture, and hydrogen contents are the most effective variables for the GCV prediction. Two models based on all variables and four the most effective ones are conducted. Outputs in the testing stage of both models verified that SVR can predict GCV quite satisfactorily where the correlations of determination (R2) for models was 0.99. Based on these results, development of a variable selection system among wide range of parameters, and also application of an accurate predictive model such as SVR, can potentially be further employed as a reliable tool for evaluation of complex relationships in earth and energy problems.


Combustion Support vector regression Variable importance measurement Proximate Ultimate Petrography 


  1. ASTM D3176 (2015) Standard Practice for Ultimate Analysis of Coal and Coke, ASTM International, United States, 1–2Google Scholar
  2. ASTM D3172 (2013) Standard Practice for Proximate Analysis of Coal and Coke, ASTM International. West Conshohocken, PA 19428-2959 United States, 1–2.Google Scholar
  3. ASTM D5865, Standard Test Method for Gross Calorific Value of Coal and CokeGoogle Scholar
  4. ASTM D3286, Standard Test Method for Gross Calorific Value of Coal and Coke by the Isoperibol Bomb CalorimeterGoogle Scholar
  5. ASTM D2015, Standard Test Method for Gross Calorific Value of Coal and Coke by the Adiabatic Bomb CalorimeterGoogle Scholar
  6. Burnham AK, Sweeney JJ (1989) A chemical kinetic model of vitrinite maturation and reflectance. Geochim Cosmochim Acta 53:2649–2657CrossRefGoogle Scholar
  7. Chang CC, Chih-Jen L (2011) LIBSVM: a library for support vector machines. ACM Trans Intell Syst Technol (TIST) 2(3):27.CrossRefGoogle Scholar
  8. Channiwala SA, Parikh PP (2002) A unified correlation for estimating HHV of solid liquid and gaseous fuels. Fuel 81:1051–1063CrossRefGoogle Scholar
  9. Chehreh Chelgani S, Makaremi S (2013) Explaining the relationship between common coal analyses and Afghan coal parameters using statistical modeling methods. Fuel Process Technol 110:79–85.CrossRefGoogle Scholar
  10. Chehreh Chelgani S, Mesroghli SH, Hower JC (2010) Simultaneous prediction of coal rank parameters based on ultimate analysis using regression and artificial neural network. Int J Coal Geol 83:31–34CrossRefGoogle Scholar
  11. Chehreh Chelgani S, Hart B, Grady WC, Hower JC (2011a) Study relationship between inorganic and organic coal analysis with gross calorific value by multiple regression and ANFIS. Int J Coal Preparation Util 31(1):9–19Google Scholar
  12. Chehreh Chelgani S, Dehghan F, Hower JC (2011b) Estimation of some coal parameters depending on petrographic and inorganic analyses by using Genetic algorithm and Adaptive neuro-fuzzy inference systems. Energy Explor Exploit 29(4):479–494.Google Scholar
  13. Chehreh Chelgani S, Hower JC, Hart B (2011c) Estimation of free-swelling index based on coal analysis using multivariable regression and artificial neural network. Fuel Process Technol 92:349–355.Google Scholar
  14. Chehreh Chelgani S, Matin SS, Hower JC (2016a) Explaining relationships between coke quality index and coal properties by Random Forest method. Fuel 182:754–760Google Scholar
  15. Chehreh Chelgani S, Matin SS, Makaremi S (2016b) Modeling of free swelling index based on variable importance measurements of parent coal properties by random forest method. Measurement 94:416–422Google Scholar
  16. George SC, Smith JW, Jardine DR (1994) Vitrinite suppression in coal due to marine transgression: case study of the organic geochemistry of the Greta seam. Sydney Basin APEA J 34:241–255.Google Scholar
  17. Golshani T, Jorjani E, Chelgani SC, Shafaei SZ, Nafechi YH (2013) Modeling and process optimization for microbial desulfurization of coal by using a two-level full factorial design. Int J Min Sci Technol 23(2):261–265CrossRefGoogle Scholar
  18. Hadavandi E, Shahrabi J, Shamshirband Sh. (2015) A novel Boosted-neural network ensemble for modeling multi-target regression problems. Eng Appl Artif Intell 45:204–219CrossRefGoogle Scholar
  19. Hadavandi E, Shahrabi J, Hayashi Y, SPMoE (2016) a novel subspace-projected mixture of expert models for multi-target regression problems. Soft Comput 20:2047–2065CrossRefGoogle Scholar
  20. Hower JC (2006) Letter to the editor, discussion: prediction of grindability with multivariable regression and neural network in Chinese coal. Fuel 85:1307–1308CrossRefGoogle Scholar
  21. Energy Information Administration (US), Independent statistics and analysis, Short-Term Energy Outlook (STEO) (2016)Google Scholar
  22. Johnson JW (2000) A heuristic method for estimating the relative weight of predictor variables in multiple regression. Multivariate behavioral research 35(1):1–19CrossRefGoogle Scholar
  23. Jorjani E, Bagherieh AH, Mesroghli S, Chelgani SC (2008a) Prediction of yttrium, lanthanum, cerium, and neodymium leaching recovery from apatite concentrate using artificial neural networks. J Univ Sci Technol Beijing Miner Metall Mater 15(4):367–374Google Scholar
  24. Jorjani E, Hower JC, Chelgani SC, Shirazi MA, Mesroghli SH (2008b) Studies of relationship between petrography and elemental analysis with grindability for Kentucky coals. Fuel 87(6):707–713CrossRefGoogle Scholar
  25. Kazemi S.M.R., Hadavandi E, Shamshirband SH, Asadi SH (2016) A novel evolutionary-negative correlated mixture of expert models in tourism demand estimation. Comput Hum Behav 64:641–655CrossRefGoogle Scholar
  26. Matin SS, Chehreh Chelgani S (2016a) Estimation of coal gross calorific value based on variousanalyses by random forest. Fuel 177:274–278Google Scholar
  27. Matin SS, Hower JC, Chehreh Chelgani S (2016b) Explaining relationships among various coal analyses with coal grindability index by random forest. Int J Miner Process 140–146Google Scholar
  28. Mesroghli SH, Jorjani E, Chehreh Chelgani S (2009) Estimation of gross calorific value based on coal analysis using regression and artificial neural networks. Int J Coal Geol 79:49–54CrossRefGoogle Scholar
  29. Ozgur K, Parmar KS (2016) Application of least square support vector machine and multivariate adaptive regression spline models in long term prediction of river water pollution. J Hydrol 534:104–112CrossRefGoogle Scholar
  30. Platt J (1998) Sequential minimal optimization: a fast algorithm for training support vector machinesGoogle Scholar
  31. Shamshirband SH, Tavakkoli A, Roy CB, Motamedi Sh., Song KL, Hashim R, Islam SM (2015) Hybrid intelligent model for approximating unconfined compressive strength of cement-based bricks with odd-valued array of peat content (0–29%). Powder Technol 284:560–570CrossRefGoogle Scholar
  32. Shirazi AR, Bet-tin O, Eklund L, Lindqvist O (1995) The impact of mineral matter in coal on its combustion, and a new approach to the determination of the calorific value of coal. Fuel 74(2):247–251CrossRefGoogle Scholar
  33. Smith JR, Smith JW (2007) A relationship between the carbon and hydrogen content of coals and their vitrinite reflectance. Int J Coal Geol 70:79–86CrossRefGoogle Scholar
  34. Speight GJ (2005) Handbook of coal analysis. Wiley-Interscience, Chichester, pp 141–149Google Scholar
  35. Strobl C, Boulesteix AL, Zeileis A, Hothorn T (2007) Bias in random forest variable importance measures: illustrations, sources and a solution. BMC Bioinf 8(25):1–21Google Scholar
  36. Suarez-Ruiz I, Crelling JC (2010) Coal petrology: industrial applications, 2010, SciTopics, Available at Industrial_Applications.html
  37. Tavakkoli A, Rezaeenour J, Hadavandi E (2015) A novel forecasting model based on support vector regression and bat meta-heuristic (Bat–SVR): case study in printed circuit board industry. Int J Inf Technol Decis Making 14:195–215CrossRefGoogle Scholar
  38. Tayebi Khorami M, Chehreh Chelgani S, Hower JC, Jorjani E (2011) Studies of relationships between free swelling index (FSI) and coal quality by regression and adaptive neuro fuzzy inference system. Int J Coal Geol 85:65–71CrossRefGoogle Scholar
  39. Ting FTC, Bjorlie SC (1973) Effect of petrographic composition on heating value of lignite. AAPG Bull 57:963.Google Scholar
  40. Vapnik V, The nature of statistical learning theory (Springer Science & Business Media) (2013)Google Scholar
  41. Wu KP, Wang SD (2009) Choosing the kernel parameters for support vector machines by the inter-cluster distance in the feature space. Pattern Recognit 42:710–717CrossRefGoogle Scholar
  42. Yang H, Kaizhu H, Irwin K, Michael RL (2009) Localized support vector regression for time series prediction. Neurocomputing 72:2659–2669.CrossRefGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2017

Authors and Affiliations

  • E. Hadavandi
    • 1
  • James C. Hower
    • 2
  • S. Chehreh Chelgani
    • 3
  1. 1.Department of Industrial EngineeringBirjand University of TechnologyBirjandIran
  2. 2.Center for Applied Energy ResearchUniversity of KentuckyLexingtonUSA
  3. 3.Department of Electrical Engineering and Computer ScienceUniversity of MichiganAnn ArborUSA

Personalised recommendations