Chapter

Genetic Algorithms for Chemical

Engineering Optimization
Problems
Thi Anh-Nga Nguyen and Tuan-Anh Nguyen

Abstract

Chemical engineering processes are frequently composed of multiple complex

phenomena. These systems can be represented by a set of several equations, which are
referred to as mathematical model of the process. Optimization in chemical engineer-
ing utilizes specialized techniques to determine the values of the decision variables at
which the performance of the process, measured as the objective function(s), is
minimum or maximum. The profitability of the process improves remarkably as a
result of this selection. This benefit has encouraged the broad application of optimi-
zation for important industrial challenges. However, many problems in chemical
engineering processes are hard to find the optimum using gradient-based algorithms.
For example, the cases when the objective functions of the processes are multimodal,
discontinuous, or implicit. Genetic algorithms (GAs) are a kind of metaheuristic
searching optimization methods, which are inspired by nature, the mechanics of
natural evolution and genetics. Genetic algorithms have received significant attention
due to their remarkable advantages over classical algorithms. Compared with tradi-
tional optimization approaches, GAs are straightforward, robust, capable of handling
the non-differentiable, discontinuous, or multimodal problems. The purpose of this
paper is to give several case studies using genetic algorithms in chemical engineering
optimization problems.

Keywords: optimization, genetic algorithm, chemical engineering, modeling

1. Introduction

Chemical engineering processes are frequently composed of multiple complex

phenomena. These systems can be represented by a set of several equations, such as
z = f(d; x; p), where z is the vector state of the system. The system of equations is
referred to as the mathematical model of the process. The performance of the process
is predicted by the model from the assigned data of several “input” variables, d and x,
and a group of parameters, p. Among the input variables, some, referred as x, can be
changed and are known as design variables, while others, referred as d, are
predetermined. The performance of the process can be evaluated through a set of
output variables, y = g (z), referred as the function of state of the system. Optimiza-
tion in chemical engineering utilizes specialized techniques to determine the values of
1
Genetic Algorithms

the decision variables, x, at which the performance of the process, measured as the
objective function(s), I(x), is minimum or maximum. The profitability of the process
improves remarkably as a result of this selection of input/operating/decision variables.
This benefit has encouraged the broad application of optimization for important
industrial challenges. However, many problems in chemical engineering processes are
hard to find the optimum using gradient-based algorithms. For example, the cases
when the objective functions of the processes are multimodal, discontinuous, or
implicit. Genetic algorithms (GAs) are a kind of metaheuristic searching optimization
methods, which are inspired by nature, the mechanics of natural evolution, and
genetics [1]. Genetic algorithms have received significant attention due to their
remarkable advantages over classical algorithms. Compared with traditional optimi-
zation approaches, GAs are straightforward, robust, capable of handling the non-
differentiable, discontinuous, or multimodal problems. GAs have been effectively
employed in a wide range of various engineering, manufacturing, and management
applications [2]. The purpose of this chapter is to give several case studies using
genetic algorithms in chemical engineering optimization problems. The case studies
include the optimization of an autothermal ammonia synthesis reactor, a separation
module using membrane technology, and data-driven modeling optimizations of solid
oxide fuel cells.

2. Optimization of an autothermal ammonia synthesis reactor

In the chemical process industries, ammonia is one of the most widely manufactured
inorganic compounds [3]. The majority of ammonia produced commercially is con-
sumed in fertilizers, with the rest going into plastics, synthetic fibers and resins, phar-
maceuticals, explosives, papers, and refrigeration [4]. As a result, modeling and
optimization of ammonia synthesis process have received a significant attention from
both the academia and industry. Ammonia is produced predominantly from the com-
bination of elements such as nitrogen and hydrogen in a catalytic process using a
promoted iron catalyst firstly established by Haber and Bosch as the reaction [4]:

N 2 þ 3H2 ⇌ 2NH3 (1)

The reaction is reversible and exothermic, releasing a significant amount of heat.

In order to achieve a high conversion, the heat of the reaction should be removed.
Therefore, the process is typically carried out in an autothermal synthesis reactor, in
which the heat of reaction is utilized to preheat the feed gas and ensure the suitable
temperature inside. The production of ammonia depends on several factors such as
the reactor length, the operating pressure, temperature of the feed and reacted gas,
the flow rate, and composition of the gas mixture. The optimization problem of the
process is to maximize the economic return. Many studies discussing the modeling,
simulation, and optimization of an autothermal ammonia synthesis reactor can be
found in literature. Some of them can be mentioned here as in Babu et al. [5], Babu
and Angira [6], Carvalho et al. [7], Edgar et al. [8], Ksasy et al. [9], Murase et al. [10],
Upreti and Deb [11], Yusup et al. [12]. However, the model discussed in the studies of
Edgar et al. [8], Murase et al. [10] has some minor errors and has been corrected in
Upreti and Deb [11]. Moreover, the studies primarily focus on optimizing reactor
length for a specific reactor top temperature, usually 694 K [6, 7, 12], or for a limited
set of temperatures [9, 11]. However, as reported in some studies [11, 12], the
2
Genetic Algorithms for Chemical Engineering Optimization Problems
DOI: http://dx.doi.org/10.5772/intechopen.104884

economic return is determined by the top temperature and also the reactor length (the
temperature of feed gas entering to the reaction zone). As a result, rather than a single
variable problem of reactor length, the optimization problem should be viewed as a
multivariable problem.
In the study [13], both the reactor length and the reactor top temperature are
considered in the design variables for maximizing the profit return of the process. In
order to solve the multivariate optimization problem, the cyclic coordinate search
technique was employed. This method alters the value of one decision variable at a
time, and for each coordinate direction, the golden section search was utilized to solve
the single variable optimum problem. However, this traditional searching approach is
prone to get caught in local optima. Therefore, the genetic algorithm has higher
chance to obtain the global optimum profit of the process.

2.1 Problem formulation of ammonia synthesis reactor

The system discussed here is an autothermal synthesis reactor, which is described

in [10] and contains the correction of the objective function reported in [6, 11]. The
feed gas contains 21.75 mole% nitrogen, 65.25 mole% hydrogen, 5.0 mole% ammonia,
4.0 mole% methane, and 4.0 mole% argon. In an autothermal reactor, the feed gas
mixture enters from the bottom of the reactor, flows upward, enters the catalyst zone
from the top, and moves downward. In the catalyst zone, the reaction takes place at
around 500°C and 200 atm of pressure. The heat generated by the reaction is utilized
to preheat the feed gas mixture in counter current flow. Figure 1 shows the schematic
diagram of an autothermal ammonia synthesis reactor. The considered factors affect-
ing the synthesis process are the temperature of feed gas at the entrance of the
reaction zone (top temperature) and the reactor length. The goal of the optimal design
is to determine the conditions that will give the highest economic return from the
reactor operation.

2.1.1 Objective function

The return of the process, which is calculated from the value of the product gas
(heating value and ammonia value), subtract the cost of feed gas (as a source of heat

Figure 1.
Schematic diagram of an autothermal ammonia reactor [10].

3
Genetic Algorithms

only) and minus the amortization of reactor capital expenses, is the objective function
for maximization (F). Other operating costs are not considered [11].



F ¼ 1:3356  107  1:708  104 N N 2 þ 704:09 T g  T 0  699:27 T f  T 0

1 (2)
 3:4566  107 þ 1:9837  109 L 2

in which,
Tf is the temperature of the feed gas.
Tg is the temperature of the reacting gas (the gas in the catalyst zone).
T0 is the top temperature or temperature at the inlet of the catalyst zone.
N N 2 is the flow rate of nitrogen.
L is the length of the reactor.

2.1.2 Equality constraints

The heat balance for the feed gas and the reacting gas and the mass balance for the
nitrogen flow along the catalyst zone, respectively, give the mathematical model for
the system:

dT f US1

¼ Tg  T f (3)
dx WCpf
 
dT g US1
 ðΔHÞS2 dN 2
¼ Tg  T f þ  (4)
dx WCpg WCpg dx
!
dN N 2 p p1:5 pNH
¼ f k1 N 2 H2  k2 1:53 (5)
dx pNH3 pH2

in which
 
20800
k1 ¼ 1:78954  10 exp4
(6)
RT g
 
47400
k2 ¼ 2:5714  10 exp
16
(7)
RT g
pH2 ¼ 3pN 2 (8)
286N N 2
pN 2 ¼ (9)
2:598N 0N 2 þ 2N N


286 2:23N 0N  2N N 2
pNH3 ¼ (10)
2:598N 0N þ 2N N

The differential equations are valid in the interval [0, L], in which L is the reactor
length (or the length of the catalyst zone).
The notations T 0f , T 0g , and N 0N 2 denote the initial value at x = 0 (at the inlet of the
catalyst zone) for Tf, Tg, and N N 2 , respectively, and are given by

T 0f ¼ T 0g ¼ T 0 , N 0N 2 ¼ 701:2 kmol=hm2 (11)

4
Genetic Algorithms for Chemical Engineering Optimization Problems
DOI: http://dx.doi.org/10.5772/intechopen.104884

Other notations of the system are summarized in Table 1.

2.1.3 Box constraints

The variables are subjected to the following physical constraints, as is typical in

industries [10]:

0 < L ≤ 10, 400 ≤ T f ≤ 800, 0 ≤ N N2 ≤ 3220 (12)

The length of the reactor and the top temperature are chosen as the design vari-
ables. The remaining variables (Tf, Tg, and N N 2 ) can be calculated from the model by
three differential Eqs. (3), (4), and (5). Then, the objective function is determined by
Eq. (2). Due to the constraints of temperatures, the variable T0 is also set to be within
400 and 800.
The optimal design problem is summarized as follows:

maximize F ¼ F ðx, T 0 Þ
8
>
>
dT f US1

>
> ¼ Tg  T f
>
> dx WCpf
>
>
>
>  
>
>
>
dT f US1
 ðΔHÞS2 dN 2
>
> ¼  T g  T f þ 
> dx
> WCpg WCpg dx
>
>
< !
pN 2 p1:5 pNH (13)
s:t: dN 2 H2
>
> ¼ f k 1  k2 1:53
> dx
> pNH3 pH2
>
>
>
>
>
> T 0f ¼ T 0g ¼ T 0 , N 0N 2 ¼ 701:2
>
>
>
>
>
> 400 ≤ T f ≤ 800, 0 ≤ N N 2 ≤ 3220
>
>
>
:
0 < L ≤ 10, 400 ≤ T 0 ≤ 800

Notation

Cpf Heat capacity of the feed gas

Cpg Heat capacity of the reacting gas

f Catalyst activity

ΔH Heat of reaction

N Mass flow of component designed by subscript

k Reaction rate constant

p Partial pressure of component designated by subscript

R Universal gas constant

S1 Surface area of catalyst tubes per unit length of reactor

S2 Cross-sectional area of catalyst zone

U Overall heat transfer coefficient

W Total mass transfer flow rate

Table 1.
Notation of the synthesis system.

5
Genetic Algorithms

2.2 Optimization strategy

The system of ordinary differential Eqs. (3), (4), and (5) with initial conditions
(11) was solved by Runge–Kutta fourth-order method. The system is well defined
when the top temperature (T0) and the interval of integration (the reactor length L)
are assigned. After that, the economic return is clearly evaluated, and it can be
considered as two-variable function of the top temperature and reactor length. The
genetic algorithm is employed to find the optimal solution. In order to handle the
constraints, a penalty or barrier is defined to the objective function whenever any of
variable limits is violated. The proposed strategy is detailed as follows.

2.2.1 Genetic algorithm for optimization problem

The range of the design variables is 0 < x ≤ 10, 400 ≤ T 0 ≤ 800. The parameters of
GA such as population size, crossover probability, mutation probability values were
set to be 50, 1.0, and 0.30, respectively. The selection was chosen as roulette wheel
selection with elitism. The number of generations was set to be 500.

2.2.2 Barrier method for constrained optimization

In barrier or penalty methods, the objective function will receive an undesired

value when one of the constraints is violated. Therefore, the solution will be kept in
the feasible region. The objective function has been modified as

F if 400 ≤ T f ≤ 800, 0 ≤ N N 2 ≤ 3220
F¼ (14)
0 otherwise

2.2.3 Parameters

The parameters were obtained from the literature [7, 10] and summarized in
Table 2.

Parameter Value Unit

Cpf 0.707 kcal/kg K

Cpg 0.719 kcal/kg K

f 1.0

ΔH 26,000 kcal/kmol

R 1.987 kcal/kmol K

S1 10 M

S2 0.78 m2

U 500 kcal/h m2 K

W 26,400 kg/h

Table 2.
Model parameters [7].

6
Genetic Algorithms for Chemical Engineering Optimization Problems
DOI: http://dx.doi.org/10.5772/intechopen.104884

Figure 2.
Fitness value versus generations.

Variables Interval Cyclic coordinate [13] Genetic algorithm

x (m) [0,10] 6.724 6.772

T0 (K) [600,800] 700.27 707.09

Tf (K) [400,800] 400.00 401.09

Tg (K) 629.94 631.12

NN2 [0,3220] 490.68 490.68

6
F (10 $/year) 5.018 5.018

Table 3.
Maximization results.

2.3 Optimization results

Figure 2 shows the fitness values as a function of generation. As can be observed,

the fitness function value achieved the highest after roughly 20 generations and then
stayed unchanged. After 100 generations, it was obtained that the reactor length
should be 6.772 m, and the top temperature should be 707.09 K. The process produces
a profit of 5.018 106 $ per year. The other parameters of the process are summarized
in Table 3 and compared with the findings of a cyclic coordinate search [13]. The
profit value is slightly higher than those reported in the literature, which focused
solely on reactor length optimization. From the results, the temperature at the
entrance of the catalyst zone should be slightly higher, and that the reactor length
should also be slightly longer than previously reported.

3. Economic optimization of membrane module for ultrafiltration of

protein solution

The behavior of permeate flux has a significant impact on the performance of

cross-flow ultrafiltration. Many factors cause flux declination, such as solution

7
Genetic Algorithms

properties, membrane properties, and operation conditions. The majority of current

research has centered on increasing membrane performance in terms of permeability
and selectivity [14, 15]. Just a few studies have paid attention to the configuration and
operation of the membrane module [16].
Various factors determine the decision of membrane module geometry for a given
application, including fabrication method, power consumption, and fouling potential
[17]. Manufacturers frequently recommend the membrane module design from the
fabrication standpoint [17]. There is virtually no evidence that their approach priori-
tizes the energy efficiency. Currently, with a growing in energy concern and a falling
in membrane cost, the membrane module design should place a higher attention on
energy efficiency. As a result, it is necessary to propose a module design methodology
that takes into account the energy factor.
Furthermore, membrane operating conditions are usually decided by user
experience, a handbook, or a manual from the membrane supplier. However,
the permeate flux equation governing the performance of the membrane system
varies greatly between different situations. In this aspect, for any specific
application, a general methodology for the design and operation conditions should
be studied.
In cross-flow ultrafiltration of protein solution, Nguyen et al. [18] proposed a
simple combined model, which simultaneously considers pore blockage and cake
filtration, to describe the flux declination. Then, in the study [19], the correlation
between the steady-state permeate flux and operation parameters was reported. From
the steady-state operation equation, optimal design and operation conditions for each
particular application could be established.
However, just a few reports on the optimization of membrane processes and cost
estimation have been published, or the cost estimation is too general. For example,
Wiley et al. [17] optimized the membrane module configurations for brackish water
desalination. However, the operation mode is single-pass and only the membrane cost
and energy cost were taken into account. Sethi and Wiesner [20] developed the cost
model for the removal of natural organic matter, but the study has not conducted the
optimization. In membrane technology, the feed and bleed operation mode, which
combines the batch and the single-pass configurations, is commonly utilized for
continuous full-scale filtration [21, 22]. Therefore, the optimization of a membrane
module operated in feed and bleed mode for protein ultrafiltration is considered. The
membrane geometry dimensions and operating conditions are design variables in the
problem. The system is represented by a set of ordinary differential equations. The
objective function is the annual cost, which consists of various types of capital invest-
ments and an operating expense. The capital investments are classified into several
categories, which are individually correlated to plant scale, particularly the membrane
area. The operating expense is the power consumption.

3.1 Process configuration and model calculation

3.1.1 Membrane plant configuration

The configuration of filtration system is continuous feed and bleed, which is

shown schematically in Figure 3. The notations are summarized in Table 4. There are
two main pumps in this operation: the feed pump provides the necessary trans-
membrane pressure, while the recirculation pump maintains the cross-flow rate

8
Genetic Algorithms for Chemical Engineering Optimization Problems
DOI: http://dx.doi.org/10.5772/intechopen.104884

Figure 3.
Schematic configuration of feed-and-bleed mode membrane system.

Notation Name and units

F Feed flow rate [m3/hr]

R Retentate (concentrate) flow rate [m3/hr]

Q Recirculation flow rate [m3/hr]

Flow Flow rate in membrane module [m3/hr]

P Permeation flow rate [m3/hr]

PF Pressure at outlet of feed pump [kPa]

Pi Pressure at the inlet of membrane module [kPa]

Po Pressure at the inlet of membrane module [kPa]

EP Energy consumed by the feed pump [kW]

EQ Energy consumed by the recirculation pump [kW]

ϕ0 Initial concentration of protein solution [m3/m3]

ϕi Inlet concentration of protein solution [m3/m3]

ϕf Final concentration of protein solution [m3/m3]

ϕP Concentration of protein in permeate flux [m3/m3]

u Fluid flow velocity [m/s]

ρ Fluid density [kg/m3]

μ Fluid viscosity [kg/(ms)]

w, h, L, dh Width, height, length, hydraulic diameter of the membrane module

Table 4.
Summary of system configuration notations.

through the modules. The concentrate is continually withdrawn from the system at a
flow rate (R).

3.1.2 Modeling of membrane modules

The material balance for total mass and protein give:

9
Genetic Algorithms

F ¼RþP

Fϕ0 ¼ Rϕf þ Pϕp (15)

Fϕ0 þ Qϕf ¼ ðF þ Q Þϕi

The viscosity and density of protein solution correlate to its concentration [23]:

μm ¼ 8:94  104 exp ð13:5482ϕm Þ

(16)
ρm ¼ 1000ð1  ϕm Þ þ 1360ϕm

in which, μm, ϕm are the viscosity and concentration of the mixture (solution),
respectively. ρm is the density of protein solution, 1000 kg/m3 is the density of water,
and 1360 kg/m3 is the density of dry protein powder.
The permeate flux through the membrane is [19].

   
J P 0:27 ρm udh 0:52
¼ 3:66  107 (17)
u ρm u2 μm

in which P is the trans-membrane pressure, u is the cross-flow velocity, dh is the

hydraulic diameter of the flow channel.
The equation for permeate flux can be rewritten as:

 0:27    
9 P ρm udh 0:52 u
J ¼ 5:124  10 (18)
ρm u 2 μm dh

h ¼ dh , where h is the channel height:

or in terms of shear rate γ_ ¼ 6u 12u

 0:27  0:52
P ρm udh
J ¼ 4:27  1010 γ_ (19)
ρm u2 μm

The flow rate/velocity drop and channel length change are calculated from the
total mass balance and component balance within the control volume dz across the
channel. Protein is assumed to be fully rejected by the membrane:

dðFlow  ϕm Þ ¼ 0 (20)

dðFlowÞ ¼ J  dðwzÞ ¼ J w dz (21)

The pressure loss is estimated by the Darcy-Weisbach Equation [24, 25].

dz u2
dP ¼ 4f ρm (22)
dh 2

in which f is the friction factor.

The set of ordinary equations that describes the membrane module system was
established as follows [26].

10
Genetic Algorithms for Chemical Engineering Optimization Problems
DOI: http://dx.doi.org/10.5772/intechopen.104884

8
> dðFlowÞ Flow
>
> dϕ ¼
>
> ϕm
>
> m
>
>
>
> dz Flow
>
> ¼
>
> dϕ ϕ
>
> m m wJ
>
>
>
> dP 1 u2 Flow 1
>
> ¼ 4f ρ
>
> m
>
> dϕm dh 2 ϕm w J
>
>
>
>
> μm ¼ 8:94  104 exp ð13:5482ϕm Þ
>
>
<
ρm ¼ 1000ð1  ϕm Þ þ 1360ϕm (23)
>
>  0:27  0:52  u 
>
>
>
> ¼  9 P ρm udh
>
> J 5:124 10 ρm u2 μm
>
> dh
>
>
>
>
>
> Flow
>
> u¼
>
> hw
>
>
>
> 24
>
> f ¼ if Re < 2000
>
>
>
> Re
>
>
>
>
: f ¼ 0:079 if Re > 2000
Re 0:25

in the range of concentration [ϕi, ϕf] and the initial condition

8
< Flowðϕi Þ ¼ F þ Q
>
z ð ϕi Þ ¼ 0 (24)
>
:
Pðϕi Þ ¼ Pi

The system of the ordinary equations can be solved numerically by Runge–Kutta

fourth-order method [27] to obtain the flow rate, the length, and the pressure. From
that, the two important factors determining the total cost, membrane area, and total
energy were calculated:

Amembrane ¼ w  L (25)
Epumps ¼ EP þ EQ
(26)
¼ F  Pi þ Q  ΔPdrop

In this equation,
EP, EQ are the power supplied by the feed pump and recirculation pump,
respectively.
PF, Pi, Po are the pressure at the outlet of the feed pump, at the inlet and outlet of
the membrane module, respectively.
ΔPdrop is the pressure drop in the membrane module.

3.1.3 Cost estimation

3.1.3.1 Operating cost

The operating cost consists of power consumption of the pumps and membrane
replacement. The annual energy expense of the pumps is calculated as
11
Genetic Algorithms

Epumps 3600
Cenergy ¼  8000   electricity price $=year (27)
η 1000

Epumps is from Eq. (26). The system is assumed to work 8000 hr./year (24 hr./day
and 333 days/year). η is the efficiency of the pumps, which is set to be 0.7. The
electricity price is supposed to be 0.08 $/kWh, which is the price for the industrial
sector in the United States [28].
The membrane replacement cost is calculated as
 
A
Cmembrane ¼ Amembrane  cmembrane  $=year (28)
P

where Cmembrane [$/m2/year] is the membrane replacement cost calculated per

year.
c
membrane
 [$] is the membrane price per unit area,
A
P is the amortization factor, which presents the time value of money [29] and is
calculated as a function of interest rate i and the membrane life.
The membrane price is usually about 200 $/m2 [9], and membrane life is
12–18 months. Therefore, the membrane replacement cost per year is roughly
estimated as 200 $/m2/year for the interest of i = 8%.

3.1.3.2 Capital cost

It is widely observed that capital costs are correlated to the size in the power-law
form [30]:

cost ¼ kðsizeÞn (29)

In order to achieve higher accuracy, rather than simply predicting the whole
capital cost of the membrane plant to capacity, Sethi and Wiesner [20] divided the
capital investment into several major categories, which was correlated to the size
independently. The major categories include pumps and other manufactured
equipment.

a. Pump capital cost

The pumps capital cost can be estimated as (Perry et al. [31]):

C ∗ pump ¼ I  f 1  f 2  CL  81:27  ðQ  PÞ0:4 (30)

in which.
I: a cost index ratio for updating the cost to the recent year.
f1: an adjust factor for pump construction material.
f2: an adjust factor for suction pressure range.
CL: a factor used to incorporate labor costs.
Q: flow capacity of the pump [m3/h].
P: pressure outlet of the pump [kPa].
12
Genetic Algorithms for Chemical Engineering Optimization Problems
DOI: http://dx.doi.org/10.5772/intechopen.104884

The cost index, I in Eq. (30), can be referred to as the chemical engineering (CE)
index to update the cost. It can be obtained from [32], and the value of 2.4 is used.
CL = 1.4 with the assumption that 40% of the cost is required to install the
equipment [33]. The factors f1 and f2 can be found in [31]. f1 = 1.5 when the
material is stainless steel. f2 = 1.0 when the pump pressure is below 10 bar
(1 MPa).
The pump size (Q  P in Eq. (30)) of the two pumps (feed and recirculation
pump) is

pump size ¼ ðF þ Q Þ  Pi (31)

b. Capital cost of other equipment

In membrane application, the membrane area is the key parameter, which
determines the plant capacity [34]. Thus, the membrane area is chosen as the
basic for the estimation of various components in the capital costs.
Non-membrane equipment and facilities, excluding the pumps, were grouped
into four main categories: (1) pipes and valves; (2) instruments and controls; (3)
tanks and frames; and (4) miscellaneous. The capital cost of each is correlated to
the membrane area as follows (Sethi and Wiesner [20])

1. Pipes and valves

C ∗ PV ¼ 6000ðAmembrane Þ0:42 ½$ (32)

2.Instruments and controls

C ∗ IC ¼ 1500ðAmembrane Þ0:66 ½$ (33)

3.Tanks and frames

C ∗ TF ¼ 3100ðAmembrane Þ0:53 ½$ (34)

4.Miscellaneous

C ∗ MI ¼ 8000ðAmembrane Þ0:57 ½$ (35)

c. Annual capital cost

The capital cost can be annualized using the amortization factor as
 
∗ A
Ccapital cost ¼ C capital  $=year (36)
P

For the plant design year of 20 years and the interest rate 8%, the amortization
factor will be about 0.1.

13
Genetic Algorithms

3.2 Formulizations of the problem

3.2.1 Fix parameters and design variables

In the problem, some variables, called input variables, are fixed due to the
requirement of the design. In membrane design, these are feed flow F, inlet concen-
tration ϕ0, and outlet concentration ϕf. The protein is assumed to be entirely rejected
by the membrane (ϕp = 0).
The design variables were: channel geometry (width  length  height), the inlet
pressure (Pi), and recirculation flow rate (Q).

3.2.2 Objective function

The objective function is the sum of capital cost and operating cost, which were
annualized:

minimum f ðxÞ ¼ annual total cost ¼ annual capital cost þ annual operating cost
¼ Cenergy þ Cmembrane þ Ccapital ðpumpsþotherÞ
(37)

3.2.3 Constraints

The pressure at the outlet point should be positive. This constraint is satisfied by
assigning a high value to the objective function if the outlet pressure is negative.
The decision variables are frequently limited on a finite range

xl ≤ x ≤ xu (38)

in which x is the vector of decision variables x = (Pi,Q ,w,h), subscripts l and u

indicate the lower and upper bound.

Parameters Value
3
Feed flow rate (m /hr) 0.02–200

Inlet pressure (kPa) 200–1000

Recirculation flow rate (m3/hr) 0–50

3 3
Initial solid fraction (m /m ) 0.1
3 3
Final solid fraction (m /m ) 0.4

Plant design year (year) 20

Interest rate (%) 8

Energy price ($/kWh) 0.08

Efficiency of pumps (%) 70

Operating temperature (°C) 25

Module height (mm) 0–100

Module width (m) 0–30

Table 5.
System parameters and variables.

14
Genetic Algorithms for Chemical Engineering Optimization Problems
DOI: http://dx.doi.org/10.5772/intechopen.104884

The system parameters and variables are summarized in Table 5.

3.2.4 Optimization by genetic algorithm

The parameters of GA such as population size, crossover probability, mutation

probability values were set to be, 100, 1.0, and 0.30, respectively. The selection was
based on roulette wheel with elitism, which means the most fit individual is guaranteed
a place in the next generation. The number of generations was assigned to be 500.
Because the problem is to minimize the cost, the fitness function was defined as:
(
0 if f ðxÞ > 5  105
fitness ¼ (39)
5  105  f ðxÞ otherwise

3.3 Optimum design

For the demonstration of this method, optimum designs of several feed flow rates
have been carried out. The lower limit of the membrane width is 0.1 m, the lower limit
for the module height is 0.5 mm. The designs are shown in Table 6.

Feed [m3/ ϕ0 ϕf Pressure Recirculation width height total cost

hr] [] [] [kPa] [m3/hr] [m] [mm] [$/yr]

0.02 0.1 0.4 523 2.8 0.1 5.0 1.29  103

0.2 0.1 0.4 1000 4.9 0.1 8.9 4.30  103

2 0.1 0.4 1000 0.2 0.1 6.9 1.18  104

20 0.1 0.4 987 0.2 1.3 5.0 5.60  104

200 0.1 0.4 1000 0.8 11.1 5.0 3.65  105

Table 6.
Optimum designs of membrane module.

Figure 4.
The behavior of cost per unit flow rate design in optimum condition with plant capacity.

15
Genetic Algorithms

Figure 4 presents the optimum total cost per unit of feed flow. The cost per unit of
feed flow decreases with an increase in plant capacity. It reflects the economies of
scale.
The results also suggest that the membrane module dimensions and operation
condition will change greatly depending on the process requirements, such as the
required feed capacity. It is challenging to predict the direction. It might be concluded
that the permeate flux also greatly affects the geometric design and operation strategy
in membrane separation processes. It is difficult to find a general rule for the design,
for each specific system, the correlation between the permeate flux and operating
conditions and membrane geometry should be investigated.

4. Modeling and optimization of the BSCF-based single-chamber solid

oxide fuel cell by artificial neural network and genetic algorithm

Fuel cells that are highly effective and green technology for converting chemical
energy stored in fuel to useable power are currently regarded as one of the most
promising approaches for future energy requirements [35]. The solid oxide fuel cell
(SOFC) has demonstrated an exceptional integration of advantages, such as high
efficiency, fuel flexibility, wide contamination acceptance, and low pollution [36, 37].
Modeling and simulation are valuable tools for determining the impact of various
design factors and operating conditions on cell performance, as well as for improving
fuel cells [38–40]. Plenty of models have been reported to add to the understanding of
fuel cells. Modeling approaches can be categorized into two types: theoretical and
empirical one [39, 41, 42]. In the theoretical approach, the spatial dimensions of the
models range from simple 0 (0-D) [43, 44] and 1 (1-D) [42, 45–47], to more compli-
cated 2 (2-D) [48–51] and 3 (3-D) [52–54], all with various characteristics and
directed at different objectives. The mathematical models, which are based on con-
servation principles, require a lot of data on parameters and properties of fuel cell, as
well as complicated equations and time-consuming calculation.
Empirical or data-driven approach may be more feasible for fuel cell users since
the behavior can be quickly and simply deduced without a comprehensive under-
standing of the internal components, just based on the experimental data [39, 41].
Least squares support vector machine (LS-SVM) [55], Hammerstein model [56, 57]
are examples of these approaches. In this approach, artificial neural network (ANN)
shows several advantages, including high nonlinearity, rapid computation, a low
degree of error in matching experimental data. Using ANNs to model SOFCs appears
to be a very promising method.
In this section, an ANN was used to model the performance of the BSCF/GDC-
based cathode SOFC. The cell voltage was predicted from cathode sintering tempera-
ture, cell operating temperature, and cell current. Several network architectures were
examined to find the best structure, and the network was trained using back-
propagation methods. The data for training, validation, and testing were taken from
our study [58]. The genetic algorithm and the developed ANN were then used to find
the best conditions for achieving maximum power.

4.1 Artificial neural network models

Artificial neural networks (ANNs), which were analogous to biological nervous

systems, consist of interconnected nodes known as neurons to receive and transfer
16
Genetic Algorithms for Chemical Engineering Optimization Problems
DOI: http://dx.doi.org/10.5772/intechopen.104884

data [59]. The most basic form, feed-forward architecture, is made up of an input
layer, one hidden layers, and an output layer. The input and output layers have the
same number of neurons as the number of inputs and outputs in the system to be
modeled. Weighted connections connect each neuron to every other neuron in the
next layer. In any layer except the input, the weighted sum of data from the previous
layer is the input of a neuron. The neuron then activates the data using a function and
transfers the response to all neurons in the next layer. The size of the hidden layers is a
significant factor that affects the estimation precision because it can make the net-
work become insufficient or overfitting [60]. The number of neurons in hidden layer
is generally determined through trials. Figure 5 illustrates a 3–5-1 feed forward artifi-
cial neural network with operating temperature, sintering temperature, and current as
inputs.
The activation function employed in this model is the logistic
sigmoidf ðxÞ ¼ 1=ð1 þ ex Þ.
The input data (xi) are scaled to normalized value (xnorm) to enhance the perfor-
mance of the network:

ðx  xmin Þ
xnorm ¼ 0:8 þ 0:1 (40)
xmax  xmin

in which xmax and xmin are the bounded interval of the experimental data.
To assess the performance of ANN, the mean squared error (MSE) and coefficient
of determination (R2) are usually used [61].
Various factors affect the performance of fuel cells such as cathode and anode
structure, electrolyte material and thickness, cell temperature, inlet and outlet gas
compositions. Two important factors, cathode sintered temperature and cell operating
temperature, were considered in this model. The sintered temperature is from 1000–
1050°C, whereas the operating temperature ranges from 625–700°C. The sintered
temperature affects the structure of the obtained cathode as reported in [58]. The
explanation of the range for the investigated parameters can be found in [62].
An ANN with one input layer, one hidden layer, and one single output layer was
proposed. Current density, sintered temperature of the cathode, and cell operating
temperature are the inputs. Back-propagation algorithm [63] was used to train the
network. The maximum number of iteration and minimum performance gradient
were set to 400 and 105, respectively, to stop the training. The proper network
structure is determined through a series of trial tests. The data were split into three
subsets at random: training, validation, and test, each containing 70, 20, 10% of the

Figure 5.
Artificial neural network (3–5-1) structure.

17
Genetic Algorithms

total samples, respectively. The validation and test sets are necessary for evaluating
the validation and power of the networks.
The parameters of the neural network were saved and utilized in the next stage to
optimize the power density using genetic algorithms.

4.2 Optimization by genetic algorithm

The objective function is the power density of the fuel cell

P¼IV (41)

where P is the power density (mW.cm2), I is the current density (mA.cm2) and
is the input to the ANN model, and V is the cell voltage (V), which is calculated from
the model.
The design variables and their corresponding ranges are summarized as follows:

• sintered temperature of the cathode, [1000–1050] (°C).

• operating temperature of the cell, [625–700] (°C).

• electric current of the cell, [0–1500] (mA.cm2)

The parameters of GA as population size, mutation probability values were set to

be 100 and 0.10, respectively. The survival of the individuals was decided by roulette
wheel with elitism. The number of generations was 500.

4.3 Optimization results

Figure 6 depicts the fitness values (maximum and mean) of the population versus
generation. As indicated in the figure, after about 20 generations, the value of fitness
function attained to a maximum value and then remained unchanged. After 100

Figure 6.
The fitness values versus generation.

18
Genetic Algorithms for Chemical Engineering Optimization Problems
DOI: http://dx.doi.org/10.5772/intechopen.104884

generations, the maximum fuel cell power density of 451.64 mW/cm2 could be
achieved at the sintered temperature of 1005°C, operating temperature of 668°C, and
current density of 777 mA/cm2.

5. Conclusions

The application of genetic algorithm in chemical engineering processes has been

illustrated by three case studies. The results suggest that the optimum conditions of
complex chemical problems can be easily obtained using genetic algorithm. The suc-
cesses of genetic algorithm for the challenging problems reported herein, the devel-
opment of many faster and flexible versions of GA, the improvement of computing
ability all suggest the continually increasing impact of metaheuristic methods in
chemical engineering systems.

Author details

Thi Anh-Nga Nguyen1 and Tuan-Anh Nguyen2*

1 Faculty of Applied Sciences, Ton Duc Thang University, Ho Chi Minh City, Vietnam

2 Faculty of Chemical Engineering, Ho Chi Minh City University of Technology,

VNU-HCM, Vietnam

*Address all correspondence to: [email protected]

© 2022 The Author(s). Licensee IntechOpen. This chapter is distributed under the terms of
the Creative Commons Attribution License (http://creativecommons.org/licenses/by/3.0),
which permits unrestricted use, distribution, and reproduction in any medium, provided
the original work is properly cited.
19
Genetic Algorithms

References

[1] Goldberg DE. Genetic Algorithms in [8] Edgar TF, Himmelblau DM,
Search, Optimization, and Machine Lasdon LS. Optimization of Chemical
Learning. Boston, MA, United States: Processes. New York, NY, USA:
Addison-Wesley; 1989 McGraw-Hill; 2001

[2] Deb K. Introduction to genetic [9] Ksasy M, Areed F, Saraya S,

algorithms for engineering optimization. Khalik MA. Optimal reactor length of
In: Onwubolu GC, Babu BV, editors. an auto-thermal ammonia synthesis
New Optimization Techniques in reactor. IJECS: International Journal of
Engineering. Berlin, Heidelberg: Electrical and Computer Sciences.
Springer Berlin Heidelberg; 2004. 2010;10(3):6-11
pp. 13-51
[10] Murase A, Roberts HL,
[3] Nielsen A, Aika K, Christiansen LJ, Converse AO. Optimal thermal Design of
Dybkjaer I, Hansen JB, Nielsen PEH, an Autothermal Ammonia Synthesis
et al. Ammonia: Catalysis and Reactor. Industrial & Engineering
Manufacture. Berlin Heidelberg: Chemistry Process Design and
Springer; 1995 Development. 1970;9(4):503-513. DOI:
10.1021/i260036a003
[4] Ammonia AM. Priciples & Industrial
Practice. Weinheim, Germany: Wiley; [11] Upreti SR, Deb K. Optimal design of
1999 an ammonia synthesis reactor using
genetic algorithms. Computers &
[5] Babu B, Angira R, Nilekar A. Chemical Engineering. 1997;21(1):87-92.
Optimal design of an auto-thermal DOI: 10.1016/0098-1354(95)00251-0
ammonia synthesis reactor using
differential evolution. In: Proceedings [12] Yusup S, Zabiri H, Yusoff N,
of the Eighth World Multi-Conference Yew YC. Modeling and Optimization of
on Systemics, Cybernetics and Ammonia Reactor Using Shooting
Informatics (SCI-2004). Methods. Bucharest, Romania:
Orlando, Florida, USA: International Proceedings of the 5th WSEAS
Institute of Informatics and Systemics; international conference on Data
2004 networks, communications and
computers, World Scientific and
[6] Babu BV, Angira R. Optimal design of Engineering Academy and Society
an auto-thermal ammonia synthesis (WSEAS); 2006. pp. 258-268
reactor. Computers & Chemical
Engineering. 2005;29(5):1041-1045. [13] Nguyen TAN, Nguyen TA, Vu TD,
DOI: 10.1016/j.compchemeng. Nguyen KT, Dao TKT, Huynh KPH.
2004.11.010 Optimization of an auto-thermal
ammonia synthesis reactor using cyclic
[7] Carvalho EP, Borges C, Andrade D, coordinate method. IOP Conference
Yuan JY, Ravagnani MASS. Modeling Series: Materials Science and
and optimization of an ammonia reactor Engineering. 2017;206:012059.
using a penalty-like method. Applied DOI: 10.1088/1757-899x/206/1/012059
Mathematics and Computation. 2014;
237:330-339. DOI: 10.1016/j. [14] Mores PL, Arias AM, Scenna NJ,
amc.2014.03.099 Caballero JA, Mussati SF, Mussati MC.
20
Genetic Algorithms for Chemical Engineering Optimization Problems
DOI: http://dx.doi.org/10.5772/intechopen.104884

Membrane-based processes: [21] Cheryan M. Ultrafiltration and

Optimization of hydrogen separation by Microfiltration Handbook. Boca Raton,
minimization of power, membrane area, FL, USA: Taylor & Francis; 1998
and cost. Processes. 2018;6(11):221. DOI:
10.3390/pr6110221 [22] Zeman LJ, Zydney AL.
Microfiltration and Ultrafiltration:
[15] Ramírez-Santos ÁA, Bozorg M, Principles and Applications. New York,
Addis B, Piccialli V, Castel C, Favre E. NY, USA: CRC Press; 1996
Optimization of multistage membrane
gas separation processes. Example of [23] Karasu K. A Study on Permeation
application to CO2 capture from blast Phenomena in Cross-Flow Ultrafiltration
furnace gas. Journal of Membrane Producing a Compressible Cake Layer.
Science. 2018;566:346-366. Tokyo, Japan: Tokyo Institute of
DOI: 10.1016/j.memsci.2018.08.024 Technology; 2010

[16] Ohs B, Lohaus J, Wessling M. [24] White FM. Fluid Mechanics. 8th ed.
Optimization of membrane based New York, NY, USA: McGraw-Hill
nitrogen removal from natural gas. Education; 2016
Journal of Membrane Science. 2016;498:
291-301. DOI: 10.1016/j.memsci. [25] Fox RW, McDonald AT,
2015.10.007 Mitchell JW. Fox and McDonald's
Introduction to Fluid Mechanics.
[17] Wiley DE, Fell CJD, Fane AG. Hoboken, NJ, USA: Wiley; 2020
Optimisation of membrane module
design for brackish water desalination. [26] Nguyen T-A, Yoshikawa S. Modeling
Desalination. 1985;52(3):249-265. and economic optimization of the
DOI: 10.1016/0011-9164(85)80036-9 membrane module for ultrafiltration of
protein solution using a genetic
algorithm. Processes. 2020;8(1):4. DOI:
[18] Nguyen T-A, Yoshikawa S,
Karasu K, Ookawara S. A simple 10.3390/pr8010004
combination model for filtrate flux in
[27] Dorfman KD, Daoutidis P.
cross-flow ultrafiltration of protein
Numerical Methods with Chemical
suspension. Journal of Membrane
Engineering Applications. Cambridge,
Science. 2012;403-404:84-93.
United Kingdom: Cambridge University
DOI: 10.1016/j.memsci.2012.02.026
Press; 2017
[19] Nguyen T-A, Yoshikawa S, [28] U.S. Energy Information
Ookawara S. Steady state permeate Administration. Average Retail Price of
flux estimation in cross-flow Electricity to Ultimate Customers Total
ultrafiltration of protein solution. End-Use Sector. U.S., USA: Department
Separation Science and Technology. of Energy; 2019
2014;49(10):1469-1478. DOI: 10.1080/
01496395.2014.893533 [29] Park CS. Fundamentals of
Engineering Economics. London, United
[20] Sethi S, Wiesner MR. Performance Kingdom: Pearson Education; 2013
and cost modeling of ultrafiltration.
Journal of Environmental Engineering. [30] Turton R, Bailie RC, Whiting WB,
1995;121(12):874-883. DOI: 10.1061/ Shaeiwitz JA. Analysis, Synthesis and
(ASCE)0733-9372(1995)121:12(874) Design of Chemical Processes. London,
21
Genetic Algorithms

United Kingdom: Pearson Education; Energy. 2007;32(7):761-786. DOI:

2008 10.1016/j.ijhydene.2006.11.028

[31] Perry RH, Perry RH, Chilton CH, [39] Hajimolana SA, Hussain MA,
Perry JH. Chemical Engineers' Daud WMAW, Soroush M, Shamiri A.
Handbook. 5th ed. New York, NY, USA: Mathematical modeling of solid oxide
McGraw-Hill; 1973 fuel cells: A review. Renewable and
Sustainable Energy Reviews. 2011;15(4):
[32] Green DW, Perry RH. Perry's 1893-1917. DOI: 10.1016/j.
Chemical Engineers' Handbook. Eighth rser.2010.12.011
ed. New York, NY, USA: McGraw-Hill
Education; 2007 [40] Ma L, Ingham DB,
Pourkashanian M, Carcadea E. Review of
[33] Holland FA, Wilkinson JK. Process the computational fluid dynamics
economics. In: Perry RH, Green DW, modeling of fuel cells. Journal of Fuel
editors. Perry’s Chemical Engineers’ Cell Science and Technology. 2005;2(4):
Handbook. 7th ed. New York, NY, USA: 246-257. DOI: 10.1115/1.2039958
McGraw-Hill; 1997
[41] Wang K, Hissel D, Péra MC,
[34] Mir L, Michaels SL, Goel V, Kaiser R. Steiner N, Marra D, Sorrentino M, et al.
Crossflow Microfiltration: Applications, A review on solid oxide fuel cell models.
Design, and Cost. In: Ho WSW, International Journal of Hydrogen
Sirkar KK, editors. Membrane handbook: Energy. 2011;36(12):7212-7228.
Newyork, NY, USA: Springer; 1992. DOI: 10.1016/j.ijhydene.2011.03.051
pp. 571-594
[42] Karcz M. From 0D to 1D modeling
[35] Wachsman ED, Marlowe CA, of tubular solid oxide fuel cell. Energy
Lee KT. Role of solid oxide fuel cells in a Conversion and Management. 2009;
balanced energy strategy. Energy & 50(9):2307-2315. DOI: 10.1016/j.
Environmental Science. 2012;5(2): enconman.2009.05.007
5498-5509. DOI: 10.1039/C1EE02445K
[43] Costamagna P, Magistri L,
[36] Ghezel-Ayagh H, Borglum BP. Massardo AF. Design and part-load
(invited) review of Progress in solid performance of a hybrid system based on
oxide fuel cell at FuelCell energy. ECS a solid oxide fuel cell reactor and a micro
Transactions. 2017;80(9):47-56. gas turbine. Journal of Power Sources.
DOI: 10.1149/08009.0047ecst 2001;96(2):352-368. DOI: 10.1016/
S0378-7753(00)00668-6
[37] Minh N, Mizusaki J, Singhal SC.
Advances in solid oxide fuel cells: [44] Zabihian F, Fung AS. Macro-level
Review of Progress through three modeling of solid oxide fuel cells,
decades of the international symposia on approaches, and assumptions revisited.
solid oxide fuel cells. ECS Transactions. Journal of Renewable and Sustainable
2017;78(1):63-73. DOI: 10.1149/ Energy. 2017;9(5):054301. DOI: 10.1063/
07801.0063ecst 1.5006909

[38] Kakaç S, Pramuanjaroenkij A, [45] Ota T, Koyama M, Wen C-j,

Zhou XY. A review of numerical Yamada K, Takahashi H. Object-based
modeling of solid oxide fuel cells. modeling of SOFC system: Dynamic
International Journal of Hydrogen behavior of micro-tube SOFC. Journal of
22
Genetic Algorithms for Chemical Engineering Optimization Problems
DOI: http://dx.doi.org/10.5772/intechopen.104884

Power Sources. 2003;118(1):430-439. 2007;171(2):601-609. DOI: 10.1016/j.

DOI: 10.1016/S0378-7753(03)00109-5 jpowsour.2007.07.003

[46] Li P-W, Suzuki K. Numerical [53] Andersson M, Paradis H, Yuan J,

modeling and performance study of a Sundén B. Three dimensional modeling
tubular SOFC. Journal of The of an solid oxide fuel cell coupling charge
Electrochemical Society. 2004;151(4): transfer phenomena with transport
A548. DOI: 10.1149/1.1647569 processes and heat generation.
Electrochimica Acta. 2013;109:881-893.
[47] Bove R, Lunghi P, M. Sammes N. DOI: 10.1016/j.electacta.2013.08.018
SOFC mathematic model for systems
simulations—Part 2: Definition of an [54] Yang C, Yang G, Yue D, Yuan J,
analytical model. International Journal Sunden B. Computational fluid dynamics
of Hydrogen Energy. 2005;30(2): model development on transport
189-200. DOI: 10.1016/j.ijhydene. phenomena coupling with reactions in
2004.04.018 intermediate temperature solid oxide
fuel cells. Journal of Renewable and
[48] Ma R, Gao F, Breaz E, Huangfu Y, Sustainable Energy. 2013;5(2):021420.
Briois P. Multidimensional reversible DOI: 10.1063/1.4798789
solid oxide fuel cell modeling for
embedded applications. IEEE [55] Huo H-B, Zhu X-J, Cao G-Y.
Transactions on Energy Conversion. Nonlinear modeling of a SOFC stack
2018;33(2):692-701. DOI: 10.1109/ based on a least squares support vector
TEC.2017.2762962 machine. Journal of Power Sources.
2006;162(2):1220-1225. DOI: 10.1016/j.
[49] Ni M. 2D thermal-fluid modeling jpowsour.2006.07.031
and parametric analysis of a planar
solid oxide fuel cell. Energy [56] Huo H-B, Zhong Z-D, Zhu X-J,
Conversion and Management. 2010; Tu H-Y. Nonlinear dynamic modeling
51(4):714-721. DOI: 10.1016/j. for a SOFC stack by using a
enconman.2009.10.028 Hammerstein model. Journal of Power
Sources. 2008;175(1):441-446.
[50] Geisler H, Dierickx S, Weber A, DOI: 10.1016/j.jpowsour.2007.09.059
Ivers-Tiffee E. A 2D stationary FEM
model for hydrocarbon Fuelled SOFC [57] Jurado F. A method for the
stack layers. ECS Transactions. 2015; identification of solid oxide fuel cells
68(1):2151-2158. DOI: 10.1149/ using a Hammerstein model. Journal of
06801.2151ecst Power Sources. 2006;154(1):145-152.
DOI: 10.1016/j.jpowsour.2005.04.005
[51] Luo XJ, Fong KF. Development of 2D
dynamic model for hydrogen-fed and [58] Le M-V, Tsai D-S, Nguyen T-A.
methane-fed solid oxide fuel cells. BSCF/GDC as a refined cathode to the
Journal of Power Sources. 2016;328: single-chamber solid oxide fuel cell
91-104. DOI: 10.1016/j.jpowsour. based on a LAMOX electrolyte.
2016.08.005 Ceramics International. 2018;44(2):
1726-1730. DOI: 10.1016/j.ceramint.
[52] Nikooyeh K, Jeje AA, Hill JM. 3D 2017.10.103
modeling of anode-supported planar
SOFC with internal reforming of [59] Baughman DR, Liu YA. Neural
methane. Journal of Power Sources. Networks in Bioprocessing and Chemical
23
Genetic Algorithms

Engineering. Amsterdam, Netherlands:

Elsevier Science; 1995

[60] Sheela KG, Deepa SN. Review on

methods to fix number of hidden
neurons in neural networks.
Mathematical Problems in Engineering.
2013;2013:425740. DOI: 10.1155/2013/
425740

[61] Himmelblau DM. Accounts of

experiences in the application of
artificial neural networks in chemical
engineering. Industrial & Engineering
Chemistry Research. 2008;47(16):
5782-5796. DOI: 10.1021/ie800076s

[62] Le M-V, Nguyen T-A, Nguyen

TA-N. Modeling and optimization of the
BSCF-based single-chamber solid oxide
fuel cell by artificial neural network and
genetic algorithm. Journal of Chemistry.
2019;2019:7828019. DOI: 10.1155/2019/
7828019

[63] Wythoff BJ. Backpropagation neural

networks: A tutorial. Chemometrics and
Intelligent Laboratory Systems. 1993;
18(2):115-155. DOI: 10.1016/0169-7439
(93)80052-J

24