Global Optimization Method Based on the Statistical Genetic Algorithm for Solving Nonlinear Bilevel Programming Problems

The calibration of the model is one of the most important steps in the development of models of engineering systems. A new approach is presented in this study to calibrate a complex multi-domain system. This approach respects the real characteristics of the circuit, the accuracy of the results, and minimizes the cost of the experimental phase. This paper proposes a complete method, the Global Optimization Method for Parameter Calibration (GOMPC). This method uses an optimization technique coupled with the simulated model on simulation software. In this paper, two optimization techniques, the Genetic Algorithm (GA) and the two-level Genetic Algorithm, are applied and then compared on two case studies: a theoretical and a real hydro-electromechanical circuit. In order to optimize the number of measured outputs, a sensitivity analysis is used to identify the objective function (OBJ) of the two studied optimization techniques. Finally, results concluded that applying GOMPC by combining the two-level GA with the simulated model was an efficient solution as it proves its accuracy and efficiency with less computation time. It is believed that this approach is able to converge to the expected results and to find the system's unknown parameters faster and with more accuracy than GA.

Download Full-text

A Hybrid Global Optimization Method Based on Genetic Algorithm and Shrinking Box

Modern Applied Science ◽

10.5539/mas.v10n2p67 ◽

2016 ◽

Vol 10 (2) ◽

pp. 67 ◽

Cited By ~ 1

Author(s):

Saleem Z. Ramadan

Keyword(s):

Genetic Algorithm ◽

Global Optimization ◽

Constrained Optimization ◽

Penalty Function ◽

Optimization Problems ◽

Fitness Function ◽

Hybrid Genetic Algorithm ◽

Optimization Method ◽

Efficient Global Optimization ◽

Global Optimization Method

<p class="zhengwen">This paper proposes a hybrid genetic algorithm method for optimizing constrained black box functions utilizing shrinking box and exterior penalty function methods (SBPGA). The constraints of the problem were incorporated in the fitness function of the genetic algorithm through the penalty function. The hybrid method used the proposed Variance-based crossover (VBC) and Arithmetic-based mutation (ABM) operators; moreover, immigration operator was also used. The box constraints constituted a hyperrectangle that kept shrinking adaptively in the light of the revealed information from the genetic algorithm about the optimal solution. The performance of the proposed algorithm was assessed using 11 problems which are used as benchmark problems in constrained optimization literatures. ANOVA along with a success rate performance index were used to analyze the model.</p>Based on the results, we believe that the proposed method is fairly robust and efficient global optimization method for Constrained Optimization Problems whether they are continuous or discrete.

Download Full-text

Development of Global Optimization Method for Design of Turbine Stages

Volume 6: Turbo Expo 2005, Parts A and B ◽

10.1115/gt2005-68290 ◽

2005 ◽

Cited By ~ 2

Author(s):

Hiroyuki Kawagishi ◽

Kazuhiko Kudo

Keyword(s):

Genetic Algorithm ◽

Global Optimization ◽

Simulated Annealing ◽

Optimum Design ◽

Optimization Method ◽

Global Optimum ◽

Global Optimization Method ◽

Optimum Solution ◽

Global Optimum Solution ◽

Number Of Iterations

A new optimization method which can search for the global optimum solution and decrease the number of iterations was developed. The performance of the new method was found to be effective in finding the optimum solution for single- and multi-peaked functions for which the global optimum solution was known in advance. According to the application of the method to the optimum design of turbine stages, it was shown that the method can search the global optimum solution at approximately one seventh of the iterations of GA (Genetic Algorithm) or SA (Simulated Annealing).

Download Full-text