ÖZELLİK SEÇİMİ İLE BİRLEŞTİRİLMİŞ DESTEK VEKTÖR MAKİNELERİNİ KULLANARAK KÖMÜRÜN ÜST ISIL DEĞERİNİN KISA VE ELEMENTEL ANALİZ DEĞİŞKENLERİNDEN TAHMİNİ

Üst ısıl değer (GCV), kömürün belirli bir miktarı yakıldığında açığa çıkan ısı enerjisi miktarını gösteren temel bir termal özelliğidir. Sunulan çalışmanın ana amacı, özellik seçimi algoritması ile destek vektör makineleri (SVM'ler) kullanarak yeni GCV tahmin modelleri geliştirmektir. Bu amaçla, literatürde ilk kez, özellik seçici RRelief-F algortiması, GCV'nin her bir tahmin edici değişkeninin önemini belirlemek için kısa ve elementel analiz değişkenlerinden oluşan veri kümesine uygulanmıştır. Bu şekilde, yedi farklı karma giriş seti (veri modelleri) oluşturulmuştur. Sunulan modellerin tahmin performansı, çoklu korelasyon katsayısının karesi (R2), kök ortalama kare hatası (RMSE) ve ortalama mutlak yüzde hatası (MAPE) ile hesaplanmıştır. Bu çalışmadan elde edilen tüm sonuçlar değerlendirildiğinde, kısa analizden elde edilen nem (M) ve kül (A) ile elementel analizden elde edilen karbon (C), hidrojen (H) ve kükürt (S) değişkenleri kömürün GCV'sini tahmin etmede en uygun değişkenler olarak belirlenirken, kısa analizden elde edilen uçucu madde ile elementel analizden elde edilen nitrojenin tahmin etme doğruluğu üzerinde olumlu bir etkiye sahip olmadığı görülmüştür. M, A, C, H ve S tahmin edici değişkenlerini kullanan SVM-tabanlı model, en yüksek R2 ve en düşük RMSE ve MAPE değerlerini sırasıyla 0,998, 0,22 Mj/kg ve % 0,66 olarak vermiştir. Ayrıca, karşılaştırma amacıyla GCV’yi tahmin etmek için çok katmanlı algılayıcı ve radyal temelli fonksiyon ağı kullanılmıştır.

Anahtar Kelimeler:

kömürün üst ısıl değeri, özellik seçimi, destek vektör makinesi, yapay sinir ağları

PREDICTION OF GROSS CALORIFIC VALUE OF COAL FROM PROXIMATE AND ULTIMATE ANALYSIS VARIABLES USING SUPPORT VECTOR MACHINES WITH FEATURE SELECTION

The gross calorific value (GCV) is an essential thermal property of coal which indicates the amount of heat energy that could be released by burning a specific quantity. The primary objective of the presented study is to develop new GCV prediction models using support vector machines (SVMs) combined with feature selection algorithm. For this purpose, the feature selector RReliefF is applied to the dataset consisting of proximate and ultimate analysis variables to determine the importance of each predictor of GCV. In this way, seven different hybrid input sets (data models) were constructed. The prediction performance of models was computed by using the square of multiple correlation coefficient (R2), root mean square error (RMSE), and mean absolute percentage error (MAPE). Considering all the results obtained from this study, the predictor variables moisture (M) and ash (A) obtained from the proximate analysis and carbon (C), hydrogen (H) and sulfur (S) obtained from the ultimate analysis were found to be the most relevant variables in predicting GCV of coal, while the predictor variables volatile matter from the proximate analysis and nitrogen from the ultimate analysis did not have a positive effect on the prediction accuracy. The SVM-based model using the predictor variables M, A, C, H, and S yielded the highest R2 and the lowest RMSE and MAPE with 0.998, 0.22 MJ/kg, and 0.66%, respectively. For comparison purposes, multilayer perceptron and radial basis function network were also used to predict GCV.

Keywords:

Gross calorific value of coal, feature selection, support vector machines, artificial neural network,

PDF

___

Q. Feng, J. Zhang, X. Zhang, and S. Wen, “Proximate analysis based prediction of gross calorific value of coals: A comparison of support vector machine, alternating conditional expectation and artificial neural network,” Fuel Processing and Technology, vol. 129, pp. 120–129, Jan. 2015.
A. Garg and P. R. Shukla, “Coal and energy security for India: Role of carbon dioxide (CO2) capture and storage (CCS),” Energy, vol. 34, no. 8, pp. 1032–1041, 2009.
W. Chen and R. Xu, “Clean coal technology development in China,” Energy Policy, vol. 38, no. 5, pp. 2123–2130, 2010.
P. Tan, C. Zhang, J. Xia, Q. Y. Fang, and G. Chen, “Estimation of higher heating value of coal based on proximate analysis using support vector regression,” Fuel Processing and Technology, vol. 138, Oct., pp. 298–304, 2015.
S. U. Patel et al., “Estimation of gross calorific value of coals using artificial neural networks,” Fuel, vol. 86, no. 3, pp. 334–344, 2007.
A. V. Akkaya, “Proximate analysis based multiple regression models for higher heating value estimation of low rank coals,” Fuel Processing and Technology, vol. 90, no. 2, pp. 165–170, 2009.
A. K. Majumder, R. Jain, P. Banerjee, and J. P. Barnwal, “Development of a new proximate analysis based correlation to predict calorific value of coal,” Fuel, vol. 87, no. 13– 14, pp. 3077–3081, 2008.
S. Yerel and T. Ersen, “Prediction of the Calorific Value of Coal Deposit Using Linear Regression Analysis,” Energy Sources, Part A: Recovery, Utilization, and Environmental Effects, vol. 35, no. 10, pp. 976–980, May 2013.
S. S. Matin and S. C. Chelgani, “Estimation of coal gross calorific value based on various analyses by random forest method,” Fuel, vol. 177, pp. 274–278, 2016.
S. Mesroghli, E. Jorjani, and S. C. Chelgani, “Estimation of gross calorific value based on coal analysis using regression and artificial neural networks,” International Journal of Coal Geology, vol. 79, no. 1–2, pp. 49–54, 2009.
X. Wen, S. Jian, and J. Wang, “Prediction models of calorific value of coal based on wavelet neural networks,” Fuel, vol. 199, pp. 512–522, 2017.
I. Yilmaz, N. Y. Erik, and O. Kaynar, “Different types of learning algorithms of artificial neural network (ANN) models for prediction of gross calorific value (GCV) of coals,” Scientific Research and Essays, vol. 5, no. 16, pp. 2242–2249, 2010.
I. Boumanchar et al., “Multiple regression and genetic programming for coal higher heating value estimation,” International Journal of Green Energy, vol. 15, no. 14–15, pp. 958–964, 2018.
A. K. Verma, T. N. Singh, and M. Monjezi, “Intelligent prediction of heating value of coal,” Iranian Journal of Earth Sciences, vol. 2, pp. 32–38, 2010.
S. C. Chelgani, S. Mesroghli, and J. C. Hower, “Simultaneous prediction of coal rank parameters based on ultimate analysis using regression and artificial neural network,” International Journal of Coal Geology, vol. 83, no. 1, pp. 31–34, 2010.
M. Robnik-Šikonja and I. Kononenko, “Theoretical and Empirical Analysis of ReliefF and RReliefF,” Machine Learning, vol. 53, no. 1/2, pp. 23–69, 2003.
C. Palmer, C. Oman, A. Park, and J. Luppens, “The U.S. Geological Survey Coal Quality (COALQUAL) Database Version 3.0 Data Series 975,” p. 43, 2015.
M. Acikkar and O. Sivrikaya, “Prediction of gross calorific value of coal based on proximate analysis using multiple linear regression and artificial neural networks,” Turkish Journal of Electrical Engineering & Computer Sciences, vol. 26, no. 5, pp. 2541–2552, 2018.
V. H. Quej, J. Almorox, J. A. Arnaldo, and L. Saito, “ANFIS, SVM and ANN soft-computing techniques to estimate daily global solar radiation in a warm sub-humid environment,” Journal of Atmospheric and Solar-Terrestrial Physics, vol. 155, pp. 62–70, Mar. 2017.
K. O. Akande, T. O. Owolabi, S. Twaha, and S. O. Olatunji, “Performance Comparison of SVM and ANN in Predicting Compressive Strength of Concrete,” IOSR Journal of Computer Engineering, vol. 16, no. 5, pp. 88-94, 2014.
F. Abut, M. F. Akay, and J. George, “Developing new VO2max prediction models from maximal, submaximal and questionnaire variables using support vector machines combined with feature selection,” Computers in Biology and Medicine, vol. 79, no. October, pp. 182–192, 2016.
J. Fu, “Application of SVM in the estimation of GCV of coal and a comparison study of the accuracy and robustness of SVM,” in 2016 International Conference on Management Science and Engineering (ICMSE), 2016, pp. 553–560.
E. Hadavandi, J. C. Hower, and S. C. Chelgani, “Modeling of gross calorific value based on coal properties by support vector regression method,” Modeling Earth Systems and Environment, vol. 3, no. 1, p. 37, Apr. 2017.
M. Qi, H. Luo, P. Wei, and Z. Fu, “Estimation of low calorific value of blended coals based on support vector regression and sensitivity analysis in coal-fired power plants,” Fuel, vol. 236, pp. 1400–1407, 2019.
X. Huang, X. Liu, and Y. Ren, “Enterprise credit risk evaluation based on neural network algorithm,” Cognitive Systems Research, vol. 52, pp. 317–324, Dec. 2018.
S. Ren and L. Gao, “Combining artificial neural networks with data fusion to analyze overlapping spectra of nitroaniline isomers,” Chemometrics and Intelligent Laboratory Systems, vol. 107, no. 2, pp. 276–282, Jul. 2011
P. H. Sherrod, “DTREG Predictive Modeling Software,” 2003.
Ö. Baydaroğlu and K. Koçak, “SVR-based prediction of evaporation combined with chaotic approach,” Journal of Hydrology, vol. 508, pp. 356–363, Jan. 2014.
C. Campbell, “Kernel methods: a survey of current techniques”, 2002.
T. Kavzoglu and I. Colkesen, “A kernel functions analysis for support vector machines for land cover classification,” International Journal of Applied Earth Observation and Geoinformation, vol. 11, no. 5, pp. 352–359, Oct. 2009.
C. W. Hsu, C. C. Chang, and C.J. Lin, “A Practical Guide to Support Vector Classification”, 2003.
G. Ozbayoglu, A. M. Ozbayoglu, and M. E. Ozbayoglu, “Estimation of Hardgrove grindability index of Turkish coals by neural networks,” International Journal of Mineral Processing, vol. 85, pp. 93-100, 2003.
J. Arliansyah and Y. Hartono, “Trip Attraction Model Using Radial Basis Function Neural Networks,” Procedia Engineering, vol. 125, pp. 445–451, Jan. 2015.
S. Chen, X. Hong, and C.J. Harris, “Orthogonal Forward Selection for Constructing the Radial Basis Function Network with Tunable Nodes,” In International Conference on Intelligent Computing, Springer, Berlin, Heidelberg, August 23-26, 2005, pp. 777–786,.
M. J. L. Orr, “Introduction to Radial Basis Function Networks,” Centre for Cognitive Science, University of Edinburgh, Scotland, 1996.