240
V. Rajashekar and Y. Shivraj Narayan
posteriori and interactive methods [1–4]. In order to have better prediction and efficiency, TLBO [5] and JAYA [6] are developed by R. Venkata Rao. There is not much
literature available on these MOO techniques as they are relatively new. TLBO is
further modified as Elite TLBO and Non-Sorted TLBO [7] whereas Jaya is further
modified as Self-adaptive Jaya [8], Quasi-Oppositional based Jaya (QO-Jaya) [9] and
Self-Adaptive Multi-Population Jaya [10]. This paper aims to provide an overview of
significant contributions of new optimization techniques especially TLBO and JAYA
in fields like machining, design, shop floor problems, medical and 3D printing.
1.1 Optimization
Optimization is defined as minimization or maximization of performance measurements by obtaining optimum condition (OC) to process parameters. Optimization is
done in two steps. They are [3]as follows:
1. Parameter Modelling: To construct the relationship between the input-output and
process variables [3].
2. Optimal/Near-Optimal Condition for process parameters was developed by using
various optimization techniques [3].
Optimization are classified based on objectives as Single objective optimization and
Multi-objective optimization [5, 6, 11].
2 TLBO [5]
TLBO consists of teachers phase and learners phase.
1. Teachers phase: Teacher improves average performance in a particular variable
[5]. At each iteration ‘i’, consider ‘m’ input variables (number of subjects j
= 1,…m), ‘n’ population (number of learners k = 1,…n), M i, j be the average
outcome particular variable ‘j’. The best overall result X total,Kbest,i taking all the
variables together obtained in total population can be taken as the outcome of
best learner K best . Variation between the existing mean results of each subject
and the respective result of the teacher for each variable is given by
Differencemean j,k,i = r i (X total,Kbest,i − T F M i, j )
where r i is random number [0, 1], T F is teaching factor (T F = round (1 + r i {2−1}))
Then update input variables by using below equation.
X
j,k,i = X j,k,i + Difference mean j,k,i
V. Rajashekar and Y. Shivraj Narayan
posteriori and interactive methods [1–4]. In order to have better prediction and efficiency, TLBO [5] and JAYA [6] are developed by R. Venkata Rao. There is not much
literature available on these MOO techniques as they are relatively new. TLBO is
further modified as Elite TLBO and Non-Sorted TLBO [7] whereas Jaya is further
modified as Self-adaptive Jaya [8], Quasi-Oppositional based Jaya (QO-Jaya) [9] and
Self-Adaptive Multi-Population Jaya [10]. This paper aims to provide an overview of
significant contributions of new optimization techniques especially TLBO and JAYA
in fields like machining, design, shop floor problems, medical and 3D printing.
1.1 Optimization
Optimization is defined as minimization or maximization of performance measurements by obtaining optimum condition (OC) to process parameters. Optimization is
done in two steps. They are [3]as follows:
1. Parameter Modelling: To construct the relationship between the input-output and
process variables [3].
2. Optimal/Near-Optimal Condition for process parameters was developed by using
various optimization techniques [3].
Optimization are classified based on objectives as Single objective optimization and
Multi-objective optimization [5, 6, 11].
2 TLBO [5]
TLBO consists of teachers phase and learners phase.
1. Teachers phase: Teacher improves average performance in a particular variable
[5]. At each iteration ‘i’, consider ‘m’ input variables (number of subjects j
= 1,…m), ‘n’ population (number of learners k = 1,…n), M i, j be the average
outcome particular variable ‘j’. The best overall result X total,Kbest,i taking all the
variables together obtained in total population can be taken as the outcome of
best learner K best . Variation between the existing mean results of each subject
and the respective result of the teacher for each variable is given by
Differencemean j,k,i = r i (X total,Kbest,i − T F M i, j )
where r i is random number [0, 1], T F is teaching factor (T F = round (1 + r i {2−1}))
Then update input variables by using below equation.
X
j,k,i = X j,k,i + Difference mean j,k,i