Estimation of Calorific Values of Some of the Turkish Lignites by Artificial Neural Network and Multiple Regressions

Author(s): Engin Özdemir*, Didem Eren Sarici

Journal Name: Current Physical Chemistry

Volume 10 , Issue 2 , 2020

Become EABM
Become Reviewer

Graphical Abstract:


Abstract:

Background: The calorific value is the most important and effective factors of lignites in terms of energy resources. Humidity, ash content, volatile matter and sulfur content are the main factors affecting lignite's calorific values.

Objective: Determination of calorific value is a process that takes time and cost for businesses. Therefore, estimating the calorific value from the developed models by using other parameters will benefit enterprises in term of time, cost and labor.

Method: In this study calorific values were estimated by using artificial neural network and multiple regression models by using lignite data of 30 different regions. As input parameters, humidity, ash content and volatile matter values are used. In addition, the mean absolute percentage error and the significance coefficient values were determined.

Results: Mean absolute percentage error values were found to be below 10%. There is a strong relationship between calorific values and other properties (R2> 90).

Conclusion: As a result, artificial neural network and multiple regression models proposed in this study was shown to successfully estimate the calorific value of lignites without performing laboratory analyses.

Keywords: Calorific value regression, energy, multiple artificial neural networks, Turkish lignite, regression models, ash content, mean absolute percentage error.

[1]
Yılmaz, M. Türkiye’nin enerji potansiyeli ve yenilenebilir enerji kaynaklarının elektrik üretimi açısından önemi. Ankara Üniversitesi Çevre Bilimleri Dergisi, 2012, 4(2), 33-54.[in Turkish].
[2]
Channiwala, S.A.; Parikh, P.P. A unified correlation for estimating HHV of solid, liquid and gaseous fuels. Fuel, 2002, 81, 1051-1063.
[http://dx.doi.org/10.1016/S0016-2361(01)00131-4]
[3]
De Souza, K.F.; Sampaio, C.H.; Kussler, J.A.T. Washability curves for the lower coal seams in Candiota Mine - Brazil. Fuel Process. Technol., 2012, 96, 140-149.
[http://dx.doi.org/10.1016/j.fuproc.2011.12.026]
[4]
Sivrikaya, O. Cleaning study of a low-rank lignite with DMS, Reichert spiral and flotation. Fuel, 2014, 119, 252-258.
[http://dx.doi.org/10.1016/j.fuel.2013.11.061]
[5]
Majumder, A.K.; Jain, R.; Banerjee, J.P.; Barnwal, J.P. Development of a new proximate analysis based correlation to predict calorific value of coal. Fuel, 2008, 87, 3077-3081.
[http://dx.doi.org/10.1016/j.fuel.2008.04.008]
[6]
Hower, J.C.; Eble, C.F. Coal quality and coal utilization. Energy Miner Divis. Hourglass, 1996, 30(7), 1-8.
[7]
Toprak, S. Petrographic properties of major coal seams in Turkey and their formation. Int. J. Coal Geol., 2009, 78, 263-275.
[http://dx.doi.org/10.1016/j.coal.2009.03.006]
[8]
Devlet Planlama TeşkilatıNinth Development Plan, Energy Raw Materials (Lignite, Coal, Geothermal) Group Report,; Ankara, Turkey, 2009.
[9]
Demirbaş, A. Demineralization and desulfurization of coals via column froth flotation and different methods. Energy Convers. Manage., 2002, 43, 885-895.
[http://dx.doi.org/10.1016/S0196-8904(01)00088-7]
[10]
Abakay, T.H.; Majumder, A.K.; Bakır, Y. An assessment of Malatya-Arguvan lignite and Southeastern Anatolia region lignites (Turkey). Energy Sources A Recovery Util. Environ. Effects, 2015, 37(11), 1202-1209.
[http://dx.doi.org/10.1080/15567036.2013.830163]
[11]
Mesroghli, S.; Jorjani, E.; Chelgani, S.C. Estimation of gross calorific value based on coal analysis using regression and artificial neural networks. Int. J. Coal Geol., 2009, 79, 49-54.
[http://dx.doi.org/10.1016/j.coal.2009.04.002]
[12]
Akkaya, A.V. Proximate analysis based multiple regression models for higher heating value estimation of low rankcoals. Fuel Process. Technol., 2009, 90, 165-170.
[http://dx.doi.org/10.1016/j.fuproc.2008.08.016]
[13]
Türkiye Kömür İşletmeleri. Available from: http://www.tki.gov.tr/kurumsal/kurulus-ve-tarihce/81
[14]
Ediger, V.Ş. Komurun tarihcesi ve Turkiye komur stratejileri, Ankara, Turkiye Komur Isletmeleri Kurumu yayınları., 2014.
[15]
Kaastra, I.; Boyd, M. Designing a neural network for forecasting financial and economic time series. Neurocomputing, 1996, 10, 215-236.
[http://dx.doi.org/10.1016/0925-2312(95)00039-9]
[16]
Jensen, E. Teaching with the Brain in Mind; Association for Supervision and Curriculum Development: Alexandra, Virginia, 1998.
[17]
Law, R.; Au, N. A neural network model to forecast Japanese demand for travel to Hong Kong. Tour. Manage., 1999, 20, 89-97.
[http://dx.doi.org/10.1016/S0261-5177(98)00094-6]
[18]
Johnson, R.A.; Wichern, D.W. Applied multivariate statistical analysis,; Prentice Hall: : Upper Saddle River New Jersey,, 2002, 5, . (8)
[19]
Durmuş, B.; Yurtkoru, E.S.; Çinko, M. Sosyal bilimlerde SPSS’le veri analizi, Beta yayıncılık. Baskı, 2011, 4, 215.
[20]
Lewis, C.D. Industrial and business forecasting methods; Butterworths- Heinemann: London, 1982.
[21]
Dahal, H.; Routray, J.K. Identıfyıng assocıatıons between soil and production variables using linear multiple regression models. J. Agricul. Environ., 2011, 12, 27-37.
[http://dx.doi.org/10.3126/aej.v12i0.7560]


open access plus

Rights & PermissionsPrintExport Cite as

Article Details

VOLUME: 10
ISSUE: 2
Year: 2020
Page: [154 - 162]
Pages: 9
DOI: 10.2174/1877946809666191120125450

Article Metrics

PDF: 20