Estimation of free-swelling index based on coal analysis using multivariable regression and artificial neural network S. Chehreh Chelgani a, ⁎, James C. Hower b , B. Hart a a Surface Science Western, University of Western Ontario, London, Ont., Canada N6G 0J3 b Center for Applied Energy Research, University of Kentucky, 2540 Research Park Drive, Lexington, KY 40511, USA abstract article info Article history: Received 13 November 2009 Received in revised form 22 August 2010 Accepted 26 September 2010 Available online 20 October 2010 Keywords: Free-swelling index (FSI) Proximate and ultimate analysis Regression Artificial neural network The effects of proximate, ultimate and elemental analysis for a wide range of American coal samples on Free-swelling Index (FSI) have been investigated by multivariable regression and artificial neural network methods (ANN). The stepwise least square mathematical method shows that variables of ultimate analysis are better predictors than those from proximate analysis. The non linear multivariable regression, correlation coefficients (R 2 ) from ultimate analysis inputs was 0.71, and for proximate analysis input variables was 0.49. With the same input sets, feed-forward artificial neural network (FANN) procedures improved accuracy of predicted FSI with R 2 = 0.89, and 0.94 for proximate and ultimate analyses, respectively. The ANN based prediction method, as a first report, shows FSI is a predictable variable, and ANN can be further employed as a reliable and accurate method in the free-swelling index prediction. © 2010 Elsevier B.V. All rights reserved. 1. Introduction Coke is an expensive component in the steel-making process [1] where about 90% of the coke produced from blends of coking coals is used to maintain the process of iron production in the blast furnace [2]. The plasticity of coal during heating, measured by rheological tests of coals in their softened state [3], is the major factor responsible for coke formation [4]. The fluid and swelling properties of coals relate to the ability of the reactive components in a coal to fuse with the inert material in the coal, thereby making a strong coke. Impurities present in coke affect its performance in the blast furnace by decreasing its role as a fuel in terms of carbon available for direct and indirect reduction roles and its role as a permeable support. These impurities include moisture, volatile matter, ash, sulfur, phosphorous, and alkali contents [2]. In spite of the relative smallness in the amount of inorganic mineral content, the rank and chemistry of the parent coal strongly influences the optical textures of cokes [5–8]. Some mineral matters (for example, calcium-containing substances) deteriorate the thermoplastic proper- ties of coals, decrease their swelling and simultaneously favor the yield of solid residue (coke) [9,10]. Because the inorganic components of the coal remain in the coke, the ash content of the coal can have an adverse affect on the coke quality. Coke properties decrease in proportion to increasing ash content of the coal [11,12]. Diez et al. investigated how coke reactivity is affected by ash components, especially Fe 2 O 3 and K 2 O [2]. The alkali content of coal, which is measured by ash composition, will accelerate coke reactivity [3]. Goscinski and Patalsky emphasized the importance of Fe 2 O 3 and CaO contents [13]. When these oxides are present in eutectic proportions the catalytic effect of the ash on coke reactivity is enhanced [11]. In addition, approximately 75% of the sulfur in coal remains in the coke [3] and as it increases, coke productivity in the blast furnace decreases [2]. Fluidity, dilatation, and free-swelling index (FSI) are all useful indicators to predict the strength of coke that can be made from a parent coal [1]. FSI (determined according to ASTM D 720) is a test that rates a coal's ability to swell during heating [3], and denotes the caking capacity of coal [14,15]. FSI is determined by comparing the size and shape of the resulting solid “button” with a series of standards and assigning a value from 1 to 9 at intervals of 0.5 [14]. According to the test, standard FSIs are classified into weakly (0–2), medium (2–4), and strongly (4–9) caking ranges [16]. Fuel Processing Technology 92 (2011) 349–355 ⁎ Corresponding author. Tel.: + 1 519 702 9356. E-mail address: Sos4552@gmail.com (S.C. Chelgani). Table 1 The number of samples for different states. State Number of samples State Number of samples Alabama 733 Colorado 96 Illinois 16 Indiana 97 Kansas 21 Kentucky 798 Iowa 53 Missouri 65 New Mexico 29 Ohio 581 Oklahoma 29 Pennsylvania 354 Tennessee 51 Utah 66 Virginia 320 West Virginia 366 Wyoming 16 0378-3820/$ – see front matter © 2010 Elsevier B.V. All rights reserved. doi:10.1016/j.fuproc.2010.09.027 Contents lists available at ScienceDirect Fuel Processing Technology journal homepage: www.elsevier.com/locate/fuproc