Search

This paper compares two different implementations of the Self-Organizing Migrating Algorithm (SOMA), which is a highly effective tool of an evolutionary optimization that is aimed at the same set of problems as Genetic Algorithms. One implementation of algorithm was created in the C# framework and the second implementation in Java framework. Both implementations are the asynchronous parallel 'All-to-One' strategy of SOMA, which is used to equally distribute computation loads between several available processors/cores. The aim of our effort is to statistically evaluate the computation time efficiency of these two concurrent frameworks including dependence on the number of threads. The obtained results are discussed in the conclusion. [ABSTRACT FROM AUTHOR]

The paper present a method for optimal design of non-standard spur gears, with the aim of minimising multi-objectives optimisation functions, obtained by weighted sum of different evaluation function, represented of the significant values of some functional parameters. Those parameters can be carrying out with designing and analysing computer applications. The paper is focused on using original MATLAB application, based on genetic algorithms, developed for optimal design, with the aim of simultaneous minimising the contact stress and bending stress on the pinion and on the gear, of asymmetric gears. Having asymmetrical involutes teeth profiles, asymmetric gears are non-standard gears obtained with the "direct gear design method", used for improving the performances of the involutes toothed gears. [ABSTRACT FROM AUTHOR]

The already introduced generic Data Mining system SHOCID (System applying High Order Computational Intelligence in Data Mining) (Neukart et al., 2011) applies Computational Intelligence (CI) paradigms for solving any numeric Data Mining problem statement. Within this paper, we introduce the evolutionary approach by which the system is able to decide on its own, which of the possible evolutionary approaches suits best for solving a presented problem statement. Moreover, the system is, by the application of genetic algorithms, able to adapt the architecture and learning method of the Data Mining solution until coming to or at least close to the optimal solution. [ABSTRACT FROM AUTHOR]

The job-shop scheduling is concerned with arranging processes and resources. Proper schedules are very important for the manufacturers, but can cause serious problems because of the enormous solution space. Pressure from the competitive enterprises is the main reason why time is becoming one of the most important success factors. The goal of the paper is the development of an algorithm for the job-shop scheduling, which is based on genetic algorithms. Our intention is to prove, that even a relatively simple genetic algorithm is capable for job-shop scheduling. [ABSTRACT FROM AUTHOR]

Process planning is one of the key activities for product design and manufacturing, impact of process plans on all phases of product design and manufacture requires high level of interaction of different activities and tight integration of them into coherent system. This paper describes a model for manufacturing activities that allows integration and process of product development with manufacturing approach based on intelligent process planning techniques with focus on optimal selection of manufacturing parameters. The selection of cutting parameters is an important step in process planning; therefore a new evolutionary computation technique has been developed to optimize the machining process through optimization of cutting parameters (sped, feed, dept of cut and cutting time). Genetic Algorithm (GA) based optimization method and deterministic optimization method (DO) are developed and then implementations into real manufacturing process planning for new product developed are analyzed. The results showed that the both developed optimization methods (GA and DO) are effective methods for solving multi-objective optimization problems during the manufacturing process planning and cutting parameters selection. [ABSTRACT FROM AUTHOR]

The paper proposes an iterative method for designing aerodynamic profiles using genetic algorithms and CFD modeling. The study shows the construction of aerodynamic profiles using two parabolas, one for the skeleton and one for the thickness of the profile, as part of parametrization for genetic algorithms. CAD software is used for defining the geometry of the fluid domain which is further used in numerical simulations. With respect to a p redefined selection criterion, the current aerodynamic profile is compared to the ones obtained before and a decision is made whether the new one is retained or not. The conclusions are related to the robustness of the method and to the necessary computational efforts for obtaining a so-called convergence. [ABSTRACT FROM AUTHOR]