Application of a supervised learning machine for accurate prognostication of higher heating values of solid wastes

ABSTRACT One of the efficient and reasonable choices for solid waste disposal is waste combustion leading to the generation of a renewable source of energy. In present work, a statistical machine learning technique, namely, least-square support vector machine was created to compute the higher heating value in relation to elemental compositions. The used data sets which include 100 data points, was divided into the two parts of training and testing, respectively, for creating a model and examining the model reliability. In conclusion, it is perceived that the proposed approach is the most accurate numerical scheme as compared with commonly used literature correlations.

[1]  Francis P. Miknis,et al.  Calculating heating values from elemental compositions of fossil fuels , 1979 .

[2]  Fernando Rojas,et al.  A thermochemical concept-based equation to estimate waste combustion enthalpy from elemental composition☆ , 2003 .

[3]  Alireza Rostami,et al.  Fast Estimation of Supercritical CO2 Thermal Conductivity by a Supervised Learning Machine - Implications for EOR , 2017 .

[4]  A. Mohammadi,et al.  Prediction of CO2 loading capacities of aqueous solutions ofabsorbents using different computational schemes , 2017 .

[5]  Mahmood Amani,et al.  Effective Thermal Conductivity Modeling of Sandstones: SVM Framework Analysis , 2016 .

[6]  A. Mohammadi,et al.  Rigorous modeling of CO2 equilibrium absorption in ionic liquids , 2017 .

[7]  S. D. Patle,et al.  Effective Thermal Conductivity , 2018 .

[8]  Alireza Baghban,et al.  Prediction carbon dioxide solubility in presence of various ionic liquids using computational intelligence approaches , 2015 .

[9]  Amir H. Mohammadi,et al.  Characterizing the CO2-brine interfacial tension (IFT) using robust modeling approaches: A comparative study , 2017 .

[10]  Alireza Samadi Lemraski,et al.  Prediction of solubility of ammonia in liquid electrolytes using Least Square Support Vector Machines , 2016, Ain Shams Engineering Journal.

[11]  Martin T. Hagan,et al.  Neural network design , 1995 .

[12]  Ahmet Demir,et al.  Predicting the Heating Value of Municipal Solid Waste-based Materials: An Artificial Neural Network Model , 2010 .

[13]  Alireza Bahadori,et al.  Prediction of Air Specific Heat Ratios at Elevated Pressures Using a Novel Modeling Approach , 2014 .

[14]  Changqing Dong,et al.  Predicting the heating value of MSW with a feed forward neural network. , 2003, Waste management.

[15]  R. Shah,et al.  Least Squares Support Vector Machines , 2022 .

[16]  Ali Selamat,et al.  Predicting correlations properties of crude oil systems using type-2 fuzzy logic systems , 2011, Expert Syst. Appl..

[17]  D. A. Davenport,et al.  Applying thermodynamics to fossil fuels: Heats of combustion from elemental compositions , 1980 .

[18]  Hung-Yee Shu,et al.  Prediction for Energy Content of Taiwan Municipal Solid Waste Using Multilayer Perceptron Neural Networks , 2006, Journal of the Air & Waste Management Association.

[19]  Donald L. Wilson.  Prediction of heat of combustion of solid wastes from ultimate analysis , 1972 .

[20]  Johan A. K. Suykens,et al.  Least Squares Support Vector Machine Classifiers , 1999, Neural Processing Letters.