EFFICIENCY INCREASE OF MULTI-OBJECTIVE GENETIC ALGORITHMS USING THE CLUSTERIZATION OF A POPULATION IN THE VARIABLE SPACE

2019 ◽  
pp. 13-20
Author(s):  
P. V. Kazakov
Keyword(s):  
Genetic Algorithm ◽  
Benchmark Problems ◽  
Additional Parameter ◽  
Nsga Ii ◽  
Multi Objective ◽  
Multi Objective Genetic Algorithm ◽  
Fitness Value ◽  
Efficiency Increase ◽  
Variable Space ◽  
Special Rule

The paper introduces a new manner for improving of obtained by MOGA (Multi-Objective Genetic Algorithm) solutions. It is based on the concept of dividing the population into set of clusters according to solutions similarity. In different of most MOGA the clusterization of population is implemented in the variable space, enables to enhance diversity of population and to increase the number of non-dominated solutions. The special procedures for the clustering of current population and copying the clusters in the next population were developed. The dominance principal by fitness-value is used for clustering. The number of clusters depends on additional parameter the radius of cluster’s hypersphere that is determined experimentally. By the special rule the individuals corresponded to centroids of clusters are copied in the new population. The clusters are recalculated for every population. The influence of the radius cluster to the number of non-dominated solutions variation was studied. The cluster modification should be integrated into any multi-objective genetic algorithm. By the analytical evaluation has been studied, this MOGA modification has additional computationally complexity from linear to quadratic. In experiments it was tested with the evolutionary algorithms SPEA2, NSGA-II on the special benchmark problems (DTLZ) with a various number of criteria using the set of performance indices. The used clustering in the variable space algorithms were achieved a better distribution and convergence to the true Paretofront in some cases.

Optimisation of Assembly Line Balancing Type-E with Resource Constraints Using NSGA-II

2016 ◽  
Vol 701 ◽  
pp. 195-199 ◽  
Author(s):  
Masitah Jusop ◽  
Mohd Fadzil Faisae Ab Rashid
Keyword(s):  
Genetic Algorithm ◽  
Assembly Line ◽  
Resource Constraints ◽  
Hybrid Genetic Algorithm ◽  
Assembly Line Balancing ◽  
Search Space ◽  
Line Balancing ◽  
Benchmark Problems ◽  
Nsga Ii ◽  
Multi Objective Genetic Algorithm

Assembly line balancing of Type-E problem (ALB-E) is an attempt to assign the tasks to the various workstations along the line so that the precedence relations are satisfied and some performance measures are optimised. A majority of the recent studies in ALB-E assume that any assembly task can be assigned to any workstation. This assumption lead to higher usage of resource required in assembly line. This research studies assembly line balancing of Type-E problem with resource constraint (ALBE-RC) for a single-model. In this work, three objective functions are considered, i.e. minimise number of workstation, cycle time and number of resources. In this paper, an Elitist Non-dominated Sorting Genetic Algorithm (NSGA-II) has been proposed to optimise the problem. Six benchmark problems have been used to test the optimisation algorithm and the results are compared to multi-objective genetic algorithm (MOGA) and hybrid genetic algorithm (HGA). From the computational test, it was found NSGA-II has the ability to explore search space, has better accuracy of solution and also has a uniformly spaced solution. In future, a research to improve the solution accuracy is proposed to enhance the performance of the algorithm.

Applications of Multi-Objective Genetic Algorithm in Optimizing Steering Performances for Submersible

2013 ◽  
Vol 756-759 ◽  
pp. 3136-3140
Author(s):  
Zhuo Yi Yang ◽  
Yong Jie Pang ◽  
Shao Lian Ma
Keyword(s):  
Genetic Algorithm ◽  
Optimal Design ◽  
Approximation Model ◽  
Horizontal Movement ◽  
Nsga Ii ◽  
Hydrodynamic Coefficient ◽  
Pareto Solution ◽  
Multi Objective ◽  
Minimum Drag ◽  
Multi Objective Genetic Algorithm

Multi-objective arithmetic NSGA-II based on Pareto solution is investigated to deal with integrated optimal design of speedability and manoeuvre performances for submersible. Approximation model of resistance for serial revolving shape is constructed by hydrodynamic numerical calculations. The appraisement criterions of stability and mobility are calculated from linear equation of horizontal movement by estimating hydrodynamic coefficient of submersible. After optimization, the scattered Pareto solution of drag and turning diameter are gained, and from the solutions designer can select the reasonable one based on the actual requirement. The Pareto solution can ensure the minimum drag in this manoeuvre performance or the best manoeuvre performance in this drag value.

Optimization of Force and Moment Balance of a Four-Bar Linkage Using Multi-Objective Genetic Algorithm

2009 ◽  
Author(s):  
Mohammad Reza Farmani ◽  
A. Jaamiolahmadi
Keyword(s):  
Genetic Algorithm ◽  
Objective Functions ◽  
Fuzzy Decision ◽  
Nsga Ii ◽  
Multi Objective ◽  
Multi Objective Genetic Algorithm ◽  
Feasible Solutions ◽  
Four Bar Linkage ◽  
External Loads ◽  
Vibration Noise

In this study, force and moment balance of a four-bar linkage is implemented by using a Multi-Objective Genetic Algorithm (MOGA). During the time that an unbalanced linkage moves, it transmits shaking forces and moments to its surroundings. These transmitted forces and moments may cause some serious and undesirable problems such as vibration, noise, wear, and fatigue. In the current problem, the concepts of inertia counterweights and physical pendulum are utilized to complete balance of all mass effects (both linear and rotary, but excluding external loads), independent of input angular velocity. In this paper, Non-Dominated Genetic Algorithm (NSGA-II) is applied to minimize two objective functions subject to some different design constraints. The applied algorithm produced a set of feasible solutions called Pareto optimal solutions for the design problem. Finally, a fuzzy decision maker is applied to select the best solution among the obtained Pareto solutions based on design criteria. The results show that obtained solutions minimize the weights of applied counterweights and eliminate both shaking forces and moments transmitted to the ground, simultaneously.

scholarly journals MULTI-OBJECTIVE CALIBRATION OF IBIS MODEL BY GENETIC ALGORITHM WITH PARAMETRIC SENSITIVITY ANALYSIS

2016 ◽  
Vol 38 ◽  
pp. 90
Author(s):  
Amarísio Da Silva Araújo ◽  
Haroldo De Campos Velho ◽  
Lu Minjiao
Keyword(s):  
Genetic Algorithm ◽  
Good Description ◽  
Synthetic Data ◽  
Search Space ◽  
Adjustment Process ◽  
Nsga Ii ◽  
Multi Objective ◽  
Multi Objective Genetic Algorithm ◽  
Integrated Biosphere Simulator ◽  
Ibis Model

Atmospheric circulation models combine different modules for a good description of the atmospheric dynamics. One of these modules is the representation of surface coverage, since the dynamics depends on the interaction between the atmosphere and the surface of the planet. However, these modules depend on a number of parameters that need to be adjusted. The parameter adjustment process is called model calibration. In this study, the IBIS (Integrated Biosphere Simulator) model is calibrated following a multi-objective strategy. The Pareto set, which embraces the non-dominated solutions in the search space of objective functions, is determined by a version of multi-objective genetic algorithm (NSGA-II). The model sensitivity to the parameters is evaluated by the Morris’ method. Synthetic data for calibration were obtained from the Tapajós National Forest (FloNa Tapajós), located near to the 67 km from Santarém-Cuiabá highway (2,51S, 54,58W).

Conceptual design of UAV using Kriging based multi-objective genetic algorithm

2008 ◽  
Vol 112 (1137) ◽  
pp. 653-662 ◽  
Author(s):  
S. Rajagopal ◽  
R. Ganguli
Keyword(s):  
Genetic Algorithm ◽  
Conceptual Design ◽  
Empirical Relation ◽  
Aircraft Design ◽  
Function Evaluation ◽  
Maximum Speed ◽  
Nsga Ii ◽  
Multi Objective ◽  
Multi Objective Genetic Algorithm ◽  
Multidisciplinary Design Optimisation

Abstract This paper highlights unmanned aerial vehicle (UAV) conceptual design using the multi-objective genetic algorithm (MOGA). The design problem is formulated as a multidisciplinary design optimisation (MDO) problem by coupling aerodynamic and structural analysis. The UAV considered in this paper is a low speed, long endurance aircraft. The optimisation problem uses endurance maximization and wing weight minimisation as dual objective functions. In this multi-objective optimisation, aspect ratio, wing loading, taper ratio, thickness-to-chord ratio, loiter velocity and loiter altitude are considered as design variables with stall speed, maximum speed and rate of climb as constraints. The MDO system integrates the aircraft design code, RDS and an empirical relation for objective function evaluation. In this study, the optimisation problem is solved in two approaches. In the first approach, the RDS code is directly integrated in the optimisation loop. In the second approach, Kriging model is employed. The second approach is fast and efficient as the meta-model reduces the time of computation. A relatively new multi-objective evolutionary algorithm named NSGA-II (non-dominated sorting genetic algorithm) is used to capture the full Pareto front for the dual objective problem. As a result of optimisation using multi-objective genetic algorithm, several non-dominated solutions indicating number of useful Pareto optimal designs is identified.

Automatic calibration of urban drainage model using a novel multi-objective genetic algorithm

2005 ◽  
Vol 52 (5) ◽  
pp. 43-52 ◽  
Author(s):  
F. di Pierro ◽  
S. Djordjević ◽  
Z. Kapelan ◽  
S.-T. Khu ◽  
D. Savić ◽  
...  
Keyword(s):  
Genetic Algorithm ◽  
Optimization Techniques ◽  
Urban Drainage ◽  
Network Modelling ◽  
Nsga Ii ◽  
Multi Objective ◽  
Sewer Network ◽  
Multi Objective Genetic Algorithm ◽  
Physically Based ◽  
Feasible Solutions

In order to successfully calibrate an urban drainage model, multiple calibration criteria should be considered. This raises the issue of adopting a method for comparing different solutions (parameter sets) according to a set of objectives. Amongst the global optimization techniques that have blossomed in recent years, Multi Objective Genetic Algorithms (MOGA) have proved effective in numerous engineering applications, including sewer network modelling. Most of the techniques rely on the condition of Pareto efficiency to compare different solutions. However, as the number of criteria increases, the ratio of Pareto optimal to feasible solutions increases as well. The pitfalls are twofold: the efficiency of the genetic algorithm search worsens and decision makers are presented with an overwhelming number of equally optimal solutions. This paper proposes a new MOGA, the Preference Ordering Genetic Algorithm, which alleviates the drawbacks of conventional Pareto-based methods. The efficacy of the algorithm is demonstrated on the calibration of a physically-based, distributed sewer network model and the results are compared with those obtained by NSGA-II, a widely used MOGA.

Sign in / Sign up

Export Citation Format

Share Document