A generalized model of SO 2 emissions from large- and small-scale CFB boilers by artificial neural network approach Part 1. The mathematical model of SO 2 emissions in air-firing, oxygen-enriched and oxycombustion CFB conditions J. Krzywanski a, ⁎, T. Czakiert b , A. Blaszczuk b , R. Rajczyk b , W. Muskala b , W. Nowak c a Jan Dlugosz University in Czestochowa, 13/15 Armii Krajowej Av., Czestochowa, Poland b Czestochowa University of Technology, 73 Dabrowskiego, Czestochowa, Poland c AGH University of Science and Technology, 30 Mickiewicza Av., Krakow, Poland abstract article info Article history: Received 16 December 2014 Received in revised form 30 March 2015 Accepted 2 April 2015 Available online xxxx Keywords: Modeling Circulating fluidized bed Oxycombustion SO 2 emissions Artificial neural networks Since the complexity of sulfur capture and release during solid fuel combustion in circulating fluidized bed (CFB) boilers, especially in the oxycombustion conditions is still not sufficiently recognized, the development of a simple SO 2 emission model for wide range of operating conditions is of practical significance. The paper introduces the artificial neural network (ANN) approach for the prediction of SO 2 emissions from CFB boilers. The model considers a wide range of parameters influencing SO 2 emissions. The [16-1-6-1] ANN model was successfully applied to predict SO 2 emissions from coal combustion in several large- and small-scale CFB boilers, over a wide range of operating conditions, both in air-firing as well as oxygen-enriched and oxycombustion conditions. Since the method constitutes a quick and easy to run technique this approach makes a complementary tool in relation to the experimental procedures and the programmed computing approach. Therefore, the model can be easily applied by scientists and engineers for simulations and optimizations of CFB units. © 2015 Elsevier B.V. All rights reserved. 1. Introduction Sulfur dioxide is the main S-based flue gas compound. Although other sulfur species, such as SO 3 H 2 S, CS, CS 2 , COS, SH, can be also detected in flue gas, their amount is much lower than SO 2 [1–7]. The source of SO 2 in air-fired conditions constitutes the fuel-bound sulfur. In combustion recycled flue gas, particularly in oxycombustion conditions, SO 2 from the recycled gas makes an additional sulfur source [6]. The emission of SO 2 is affected by complex factors and when its con- centration is too high the need for desulfurization of flue gas appears. An extensive review of sorbent systems for removal of sulfur oxides from flue gases is given in [8]. The authors distinguished four categories of the oxide materials intended for SO 2 removal: single oxides, mixed oxides, oxides supported on carbonaceous materials and oxides sup- ported on porous silica-based materials. A widely used method for SO 2 capture during solid fuel combustion in CFBC is a dry flue gas desulfurization (FGD) technology, based on thermal decomposition of limestone, followed by the sulfation reaction. This method belongs to the first of all four groups which are discussed in the paper [8]. The possibility of the in situ SO 2 emissions control by the addition of a sorbent, usually limestone or dolomite, directly into the combustion chamber, due to the low combustion temperature, is considered to be one of the main advantages of fluidized bed boilers [5,9–12]. The process of dry flue gas desulfurization can proceed via indirect or direct sulfation [9,13–17]. The investigations presented in the paper are limited to the cases when if used, limestone is applied as a sorbent to retain SO 2 from flue gas. During conventional air-fired conditions indirect sulfation of lime- stone occurs, including calcination (1) and CaO–SO 2 sulfation (2) reac- tions [17]: CaCO 3 →CaO þ CO 2 ð1Þ CaO þ SO 2 þ 0:5O 2 →CaSO 4 : ð2Þ Fuel Processing Technology 137 (2015) 66–74 ⁎ Corresponding author at: Jan Dlugosz University in Czestochowa, Faculty of Mathematics and Natural Science, Institute of Technical Education and Safety, 13/15 Armii Krajowej Av., Czestochowa, Poland. Tel./fax: + 48 343615970. E-mail address: jkrzywanski@tlen.pl (J. Krzywanski). http://dx.doi.org/10.1016/j.fuproc.2015.04.012 0378-3820/© 2015 Elsevier B.V. All rights reserved. Contents lists available at ScienceDirect Fuel Processing Technology journal homepage: www.elsevier.com/locate/fuproc