Medical, Pharma, Engineering, Science, Technology and Business

MSc Engineering, Graphic Era University, Dehradun, Uttarakhand, India

- *Corresponding Author:
- Punit Gupta

MSc Engineering

Graphic Era University

Dehradun, Uttarakhand, India

**Tel:**+918449385221

**E-mail:**punit.gupta71@gmail.com

**Received Date**: April 29, 2017; **Accepted Date:** May 08, 2017; **Published Date**: May 18, 2017

**Citation: **Gupta P, Varshney RG (2017) Simulation of Two Dimensional Raceway
Using Back Propagation Neural Networks. J Material Sci Eng 6: 342. doi: 10.4172/2169-0022.1000342

**Copyright:** © 2017 Gupta P, et al. This is an open-access article distributed under
the terms of the Creative Commons Attribution License, which permits unrestricted
use, distribution, and reproduction in any medium, provided the original author and
source are credited.

**Visit for more related articles at** Journal of Material Sciences & Engineering

The raceway phenomenon of the iron-making blast furnace has been studied in two dimensional cold models. The effect of tuyere diameter, blast velocity, and particle diameter and particle density has been physically modeled and a semi-empirical correlation has been developed. The data collected from the experimental study was simulated using a three layer back propagation neural network, for the first time. The effects of the network design parameters on the performance of the network have been studied and the optimum values of these parameters have been found. . Sensitivity analysis has been done to establish the effect of the tuyere diameter, blast velocity, particle density and particle diameter on the raceway diameter. The performance of the ANN has been compared with the semi empirical correlation developed from experimental data and it has been found that ANN is superior.

Raceway; Cold model; Artificial neural networks; Back propagation; Preprocessing; Regression; Sensitivity analysis

When a high velocity blast of gas is introduced into a packed bed through a hollow tube, a cavity with moving particles in the periphery is generally formed in front of the tube nose. The cavity that is formed in the iron making blast furnace in front of the hot blast tuyeres is known as the raceway [1]. The air velocity through the tuyeres is high (around 200 m/s) and this causes the coke particles to circulate in a rotating flow field around 0.75 m deep. Due to the extreme conditions (temperature in excess of 2000°C, high pressure etc.) involved, direct experimentation is very limited [2-7] and a number of cold model studies [8-13] have been performed in the past and their results have been presented in the form of empirical correlations. Experimental studies to determine the shape of the raceway have also been performed [14,15]. There have also been extensive mathematical models developed for quantifying this phenomenon [11,16,17]. The effect of liquid flow in the raceway zone has also been studied and simulated [18]. There are considerable differences in the dependence of raceway diameter on fundamental quantities like blast momentum, particle size and bed height between all correlations. In the present study, experiments have been performed in two dimensional models to simulate the gas-solid interactions. The effect of the blast and bed parameters on the raceway dimension has been studied and the Back propagation ANN (BPNN) technique has been used to simulate the results. The main advantage with the neural network modeling technique as compared with statistical techniques is that no functional form of the correlation is assumed a priori. Sensitivity analysis has also been performed to establish the effects of the inputs on the raceway size. The performance of the ANN model and the semi empirical correlation developed from experimental data has been compared.

Experiments were performed in transparent two dimensional
models of 15 mm depth, 700 mm height and 280 mm width, with
sidewalls made of glass. A schematic of the experimental setup is
as shown in the **Figure 1**. The tuyere (hollow tube) in the form of a
rectangular slot was placed horizontally 85 mm above the base of the
model. The effect of the following blast and bed parameters was studied:

(1) Blast velocity (2) Tuyere diameter (3) Bed height (4) Particle size (5) Particle density.

The blast velocities varied from 15 to 75 m/s f, the solid materials used were quartz and ragi (a food grain). In the present report, the data has been considered for those bed heights where the raceway dimensions become independent of the height as this is the case close to actual operating conditions

An artificial neural network (ANN) is a computational model that
is inspired by the structure and functional aspects of the biological
neuron, like those found in the human brain. In general, the network
model consists of a weighted interconnection of input nodes, hidden
nodes and output nodes, biases and activation functions [19]. The most widely used neural network for function approximation and regression
analysis is the Back Propagation (BP) algorithm whose details are
described explicitly by Rumelhart and Demuth [20,21]. The design
considerations are to find the number of hidden layers, the number
of nodes in each layer, the interconnection weights and biases and
activation functions that best fit the problem at hand **(Figure 2)**.

Consider a BP network with d nodes in the input, M nodes in the
first hidden layer, S nodes in the second hidden layer and one node in
the output layer, as shown in **Figure 3**. During the forward propagation
phase, the processing from input layer to the j^{th} neuron in the

First hidden layer is:

(1)

Similarly, the processing from the first hidden layer to the kth neuron in the second hidden layer is:

(2)

The final output for the pth pattern of data is:

(3)

During training of the network, this output is compared with the target to give the error:

(4)

for the pth data. For one complete cycle of inputs, this error is summed up to give the error function

(5)

During the weight update phase (the back propagation phase) the objective is to update the weights so as to minimize the above error function, also known as the mean square error (MSE). The commonly used optimization techniques for this like the Gauss -Newton, gradient descent, Levenberg-Marquardt can be found in refs. [22,23]. All of these techniques attempt to calculate the gradients ∂E/∂wij in a unique and optimized manner. The update rule using the momentum backpropagation technique with η, the learning rate, and μ, the momentum parameter is:

(6)

Similarly the bias terms are also updated after each training cycle till the performance criteria (number of training epochs/MSE/mean absolute error), is met.

**Preprocessing data**

The raw data is preprocessed to avoid any duplicate sets and also condition the data for processing by the network. Multilayer networks can be trained to generalize well within the range of inputs for which they have been trained. However, they do not have the ability to accurately extrapolate beyond this range, so it is important that the training data span the full range of the input space.

The main considerations for scaling the inputs/outputs are the transfer functions.

The commonly used transfer functions like logsig and tansig are sensitive to inputs only within certain ranges. For example the tansig transfer function is sensitive to inputs between (-1,1) and becomes saturated in adjacent intervals. If the saturation occurs at the beginning of the training process, the gradients will be very small, and the network training will be very slow. Two preprocessing techniques were used and their performance studied for the BP networks. In the first technique, the inputs and targets were normalized to have zero mean and unity standard deviation. In the second, inputs and targets were scaled to fall in the range (-1,1) . Due to the nonlinearity of the first mapping, the performance was also poorer than the second technique and so the latter was adopted for the simulations.

Simulations on different architectures were done with the help of
the Neural Networks tool in Matlab software [24]. The models used
had one input layer with four inputs, two hidden layers, with variable
number of nodes and one Neuron in the output to characterize the
raceway size. The effect of the learning rate, momentum term, training
algorithm, number of neurons in each layer and transfer functions on
the number of epochs to meet the performance goal (MSE was kept
constant at 1 e-08) was studied. The dataset had 107 data points in all of
which 64 data points were kept for training, 22 for validation and 21 for
testing. It was observed during the trials that the convergence criteria
is not met in exactly the same number of epochs and, the network
weights and biases always do not converge to the same values even when initialized to exactly the same constants (zeros/+1/-1). For each
architecture, after conducting a number of trials, and considering the
average and standard deviation of each set of trials, it was found that
the statistics for twenty runs can be considered as the representative.
The fastest convergence was observed with the Levenberg-Marquardt
algorithm which is in accordance with other findings [25]. The
activation function chosen were tansig for both the layers and the
purelin function performed the best for the output node. In order to
arrive at the optimum architecture, trials were made only with the
training data by keeping a constant number of nodes in one layer and
varying the number of nodes in the other layer and the results are being
shown here graphically, in **Figures 3 and 4**.

Based on these results, network architecture of 16 by 16 by 1 was
chosen for validation. The data set was partitioned into 60%training,
20% validation and 20% test. A typical performance graph is as shown
in **Figure 5**. It can be seen from this figure that when the training goal
of 10-8 (Mean Square Error, MSE) is satisfied in the epoch number 10,
the test and validation MSE's are also the minimum.

The regression statistics of this trial are as shown in **Figure 6**. It can
be seen that the regression coefficient is very close to 1 for all datasets.

(7)

Where D_{r}: Raceway diameter in mm; d_{t}: Tuyere diameter in mm.

ρ_{g}: Density of gas kg/m^3; ρ_{s}: Density of solid kg/m^3, v_{b}: Blast
velocity m/s; d_{p}: Particle diameter m; g: 9.81 m/s2 and Heff: Effective bed
height in mm (=400 mm).

A Regression coefficient value of 0.79 was obtained and the MSE
was also higher (1.49 × 10^{-2}). It can thus be concluded that the BPNN
model is superior. Sensitivity analysis was performed by perturbing
each variable over its entire range while holding other variables
constant. The average rate of change of the raceway diameter with each
of the four variables is presented in **Table 1**.

Variable | Slope |
---|---|

Tuyerediameter | 1.40 |

Blast velocity | 1.00 |

Particle diameter | -0.4 |

Particle density | -0.82 |

**Table 1:** Slope of the variables after sensitivity analysis.

The negative value of the slope for particle diameter and density signifies an inverse propotionality with the raceway diameter.

The raceway has been simulated in a cold model and from the data collected; the raceway diameter has been completely simulated by a three layer (16 × 16 × 1) back propagation artificial neural network, for the first time. The network performance is optimum when the inputs are scaled to the range (-1,1), the Levenenberg-Marquardt algorithm is used for training with tansig transfer functions in both the intermediate layers and purelin for the output layer. The BPNN model was found to be superior to the semi empirical correlation developed. Sensitivity analysis has been done to establish the effect of the tuyere diameter, blast velocity, particle density, particle diameter on the raceway diameter. In a forthcoming study, pseudo 2D modeling data will be used and Radial basis networks will also be used for simulation.

The authors would like to thank Dr. A.K. Lahiri, Retired Professor, Department of Materials Engineering, I.I.Sc., Bangalore for his guidance and support.

- Mustoe LH (1983) Principles of blast furnace ironmaking. In: BiswasAK(ed.)Cootha Publishing House, Brisbane, 1981; xi+ 528; price, Australian $75 (hard cover), Australian $37.50 (soft cover).
- Elliott JF, Buchanan RA, Wagstaff JB (1952) Physical conditions in the combustion and smelting zones of a blast furnace. Trans. AIME 194: 709-717.
- Wagstaff JB, Holman WH (1957) Comparison of blast furnace penetration with model studies. Trans AIME,pp: 210-370.
- Nakamura M, Sugiyama T, Takeo UNO, Yukiaki HARA, Kondo S (1977) Configuration of the Raceway in the Experimental Furnace. Tetsu-to-Hagané 63: 28-36.
- Hatano M, Hiraoka B, Fukuda M, Masuike T (1976) Analysis of the combustion zone in the experimental blast furnace. Tetsu-to-Hagané 62: 505-513.
- McCarthy MJ, Taggart IJ, Rogers H, Goldsworthy PC, Burgess JM (1983) Effect of blast parameters and coke properties on raceway geometry in a hot model. Iron making Proc., Metall. Soc. AIME; United States, 42.
- Burgess JM (1985) Fuel combustion in the blast furnace raceway zone. Progress in Energy and Combustion Science 11: 61-82.
- Szekely J, Poveromo JJ (1975) A mathematical and physical representation of the raceway region in the iron blast furnace. Metallurgical and Materials Transactions B 6: 119-130.
- Hatano M, Fukuda M, Takeuchi M (1976) An experimental study of the formation of raceway using a cold model. Tetsu-to-Hagané 62: 25-32.
- Omori Y (1987) Blast furnace phenomena and modelling. The Iron and Steel Institute of Japan, Elsevier, London, 255.
- Flint PJ, Burgess JM (1992) A fundamental study of raceway size in two dimensions. Metallurgical Transactions B 23: 267-283.
- Litster JD, Gupta GS, Rudolph VR, White ET (1991) Size hysteresis in a two dimensional model raceway. In CHEMECA.
- Apte VB, Wall TF, Truelove JS (1990) Stress distribution in a packed bed above raceway cavities formed by an air jet. AIChE Journal 36: 461-468.
- Nogami H, Miura T, Furukawa T (1992) Simulation of transport phenomena around raceway zone in the lower part of blast furnace. Tetsu-to-Hagané 78: 1222-1229.
- Matsui Y, Yamaguchi Y, Sawayama M, Kitano S, Nagai N, et al. (2005) Analyses on blast furnace raceway formation by micro wave reflection gunned through tuyere. ISIJ international 45: 1432-1438.
- Umekage T, Shinichi Y, Kadowaki M (2005) Numerical simulation of blast furnace raceway depth and height, and effect of wall cohesive matter on gas and coke particle flows. ISIJ international 45: 1416-1425.
- Singh V, Gupta GS,Sarkar S (2007)Modeling of liquid flow in a packed bed in the presence of gas flow. Metallurgical and Materials Transactions B 38: 401-411.
- Simon Haykin (1991) Neural Networks: A Comprehensive Foundation (2ndedn), Upper Saddle River, NJ: Prentice Hall.
- Holyoak KJ (1987) Parallel distributed processing: Explorations in the microstructure of cognition. Science 236: 992-997.
- Rumelhart DE, Hinton GE, Williams RJ (1988) Learning representations by back-propagating errors. Cognitive Modeling 5: 1.
- Demuth HB, Beale MH, De Jess O, Hagan MT (2014) Neural network design. Martin Hagan.
- Fletcher R, Reeves CM (1964) Function minimization by conjugate gradients. The Computer Journal 7: 149-154.
- Demuth H, Beale M (1992) Neural Network Toolbox. For Use with MATLAB. The MathWorksInc, 2000.
- Dwarapudi S, Gupta PK, Rao SM (2007) Prediction of iron ore pellet strength using artificial neural network model. ISIJ International 47: 67-72.
- Yang B, Li N, Lei L, Wang X (2011) BP Neural Network Fitting for Spectra of Blast Furnace Raceway. In: Applied Mechanics and Materials. Trans Tech Publications 55: 197-202.

Select your language of interest to view the total content in your interested language

- Analytical Biochemistry Techniques
- Analytical Chemistry
- Analytical Techniques
- Antibodies Drug Conjugates
- Applied Engineering
- Bio Ceramics
- Bio inert Materials
- Bioanalysis
- Bioanalytical Techniques
- Biological Engineering
- Bionanoscience
- Biopolymers
- Brittle Materials
- Calcium Phosphate
- Capillary Electrophoresis
- Ceramic Engineering
- Ceramic Metal Oxides
- Ceramics
- Ceramics Engineering
- Clinical Biotherapeutics
- Coal Mining
- Colloid Chemistry
- Composite Materials
- Composite Materials Fabrication
- Compressive Strength
- Electronic Material Development
- Experts Opinion on Nanomedicine
- Extractive Metallurgy
- Fracture Toughness
- Geological Materials
- Human osteoblasts
- Hydrometallurgy
- Hydroxyapatite
- Implants Biology
- Implementation and Implications of Nanomedicine
- Industrial Engineering
- Injectable bone substitute material
- LC-MS principles
- Lipid based Nanoparticles
- Material Science
- Materials Chemistry
- Materials Engineering
- Materials Processing and Manufacturing
- Medicine
- Metal Casting Technology
- Metallic Materials
- Metallic Materials (Ferrous & Nonferrous)
- Metallurgical Engineering
- Metallurgy
- Mineral Processing
- Molecular Electronics
- Nano Composites
- Nano Materials
- Nano Particles
- Nano Structures
- Nanobiopharmaceuticals
- Nanobiopharmaceutics
- Nanobiotechnology
- Nanocars
- Nanocomposites
- Nanoelectronics
- Nanoemulsions
- Nanoengineering
- Nanofabrications
- Nanofluidics
- Nanohedron
- Nanoionics
- Nanolithography
- Nanomaterial
- Nanomedical Tools in Gene Therapy
- Nanomedicine
- Nanomedicine Applications
- Nanomedicine and Nanobiotechnology
- Nanomedicine in Cancer
- Nanomedicine in Drug Discovery
- Nanoparticles
- Nanoparticles and Biocompatibility
- Nanotechnology
- Nanothermite
- Nanotoxicology
- Nanotubes
- Pharmaceutical Analytical Techniques
- Polymeric Materials
- Polymeric Nanoparticle Delivery
- Porous Materials
- Prosthetic Devices
- Qualitative Analysis
- Rock Mechanics
- Semiconductors
- Solid Lipid Nanoparticles
- Spectroscopy
- Supramolecule
- Surface Mining
- TM-Joint disorders
- Therapeutic Agents
- Tissue Scaffold
- Toxicity of Nanomaterials

**3rd International Conference and Expo on Ceramics and Composite Materials**

June 26-27, 2017 Madrid, Spain**2nd International Conference and Exhibition on Materials Chemistry**

July 13-14, 2017 Berlin, Germany**10th International Conference on Emerging Materials and Nanotechnology**

July 27-29, 2017 Vancouver, Canada**10th International Conference on Advanced Materials and Processing**

August 16-17 Edinburgh, Scotland**3rd International Conference on Polymer Science and Engineering**

October 2-4, 2017 Chicago, USA**International Conference on Advanced Materials and Nanotechnology**

October 26-28, 2017 Osaka, Japan**13th International Conference and Exhibition on Materials Science and Engineering**

November 13-15, 2017 Las Vegas, Nevada, USA**14th International Conference on Functional****Energy Materials**

December 06-07, 2017 Atlanta, USA

- Total views:
**60** - [From(publication date):

June-2017 - Jun 24, 2017] - Breakdown by view type
- HTML page views :
**42** - PDF downloads :
**18**

Peer Reviewed Journals

International Conferences 2017-18