Obtaining the fullest possible representation of solutions to a multi-objective optimization problem has been a major concern in MultiObjective Genetic Algorithms (MOGAs). This is because a MOGA, due to its nature, usually produces several clusters of solutions that does not cover the whole range of Pareto frontier. This poster paper indroduces an overview of a new approach, one that aims at ob...

This paper presents the use of neural networks and genetic algorithms in time-optimal control of a closed-loop robotic system. Radial-basis function networks are used in conjunction with PID controllers in an independent joint position control to reduce tracking errors. The results indicate that using neural network controllers is more effective than using trajectory preshaping scheme, reported...

Title of Dissertation: ROBUST OPTIMIZATION AND SENSITIVITY ANALYSIS WITH MULTI-OBJECTIVE GENETIC ALGORITHMS: SINGLEAND MULTIDISCIPLINARY APPLICATIONS Mian Li, Doctor of Philosophy, 2007 Dissertation directed by: Shapour Azarm, Professor Department of Mechanical Engineering Uncertainty is inevitable in engineering design optimization and can significantly degrade the performance of an optimized ...

This paper presents an automatic optimization method for compliant constant force mechanisms, which eliminates the need time-consuming parameter tuning and complex model design in conventional process. The proposed framework is based on finite-element analysis (FEA) multi-objective genetic algorithm (MOGA) methods designed two steps: First, preliminary mechanism carried out to roughly encompass...

* Department of Mechanical Engineering, Ubonratchathani University. ** Research and Development Center for Intelligent Systems, King Mongkut’s Institute of Technology North Bangkok. Abstract This paper presents the use of a multi-objective diversity control oriented genetic algorithm (MODCGA) for solving a closed-loop time-optimal path planning problem. The MODCGA is a result of the integration...

investment casting is a versatile manufacturing process to produce high quality parts with high dimensional accuracy. the process begins with the manufacture of wax patterns. the dimensional accuracy of the model affects the quality of the finished part. the present study investigated the control and optimization of dimensional deviations in wax patterns. a mold for an h-shaped wax pattern was ...

in order to reduce both the weight of vehicles and the damage of occupants in a crash event simultaneously, it is necessary to perform a multi-objective optimization of the automotive energy absorbing components. in this paper, axial impact crushing behavior of the aluminum foam-filled thin-walled tubes are studied by the finite element method using commercial software abaqus. comparison of the...

In this paper, Metallic Catalytic Converter (MCC) is installed in motorcycle exhausts to produce the minimum CO as well optimum engine power. The results from previous research were collected and then used predict best MCC design using Artificial Neural Network Multi-Objective Genetic Algorithm (ANN-MOGA). addition, ANN parameter tuning process was also carried out Taguchi method find initial w...

The multiobjective genetic algorithm (MOGA) has been applied to various real-world problems in a variety of fields, most prominently in control systems engineering, with considerable success. However, a recent empirical analysis of multiobjective evolutionary algorithms (MOEAs) has suggested that a MOGA-based algorithm performed poorly across a diverse set of two-objective test problems. In thi...