genetic algorithm

This research introduces the optimal design for underwater sound-absorbing linings. To address the time and computational cost of the optimization process, a combined approach of the genetic algorithm and a surrogate model using artificial neural networks was implemented. The results conclusively demonstrate that the best cavity shape for the low-frequency domain is conical with an apex near the surface of the entering wave. In contrast, a conical shape in the opposite direction of the low-frequency case is optimal for the entire frequency range. Selecting the best frequency range is crucial for the design and optimization process. The optimal response significantly outperformed other randomly established linings, validating the chosen approach. Additionally, increasing the number of optimization variables will undoubtedly alter the optimal solution, albeit with a considerable increase in problem complexity.

In recent decades, different methods of wave prediction model have been used. Experimental methods, numerical methods, soft computing algorithms are among such methods. In this study, the height of the waves in the Gulf of Mexico is predicted in two different sections. In the first part, the ALM algorithm and GIDS model and in the second part, the experimental methods of SPM and CEM are investigated. For this purpose, first, the collected data and wind stress factor in SPM model were pre-processed using ALM and GIDS models. After investigations, it was determined that the wind stress factor should be corrected with a dimensionless correction factor p⁄((1⁄2 ρ〖〖 u〗_10〗^2 ) ). In the next step, the most suitable input of the GIDS model was selected and in order to reduce the time of this modeling, different combinations of modified wind stress factor Ua with wavelength were considered, which resulted in the parameter U_a (gX)^(-0.02) The most appropriate input for the GIDS model is in predicting the height of the waves. In the second part of the paper, each of the SPM and CEM models was implemented and compared with the optimized GIDS model. The results showed that the GIDS model was more accurate in predicting the wave height of the Gulf of Mexico. Then the wind speed correction coefficient was modified using a genetic algorithm and with this operation the SPM model was modified and presented as the most appropriate prediction model.

Today, marine transportation has a significant role in global trade. The characteristics of the containerized shipping have made the number of container ships grow every day and made significant improvements in the construction and operation of these ships.
In this research, the main dimensions of a container ship are optimized according to different objectives. This optimization aims to reduce both hydrodynamic resistance and the steel weight of the ship. Initially, the information needed for optimization is specified, and the problem's constraints are determined. Then, the optimization is done using the optimization tool of the genetic algorithm toolbox in Matlab software. Also, a software code is developed, and the optimization case is done using this code. The results show that the genetic algorithm can be used as a practical tool for optimizing the dimensions of the ships.

Radar absorbing materials are one of the key technologies in reducing the radar cross-section and thus RCS reduction of air and sea systems. In this paper, by examining the properties of the Brewster angle in various electromagnetic structures, it was shown how the ultra-broadband absorbers can be achieved by using this concept and engineering the Brewster angle. It was also shown how to design multi-band absorbers with high angular stability using anisotropic materials. Finally, using the genetic algorithm optimization method, two types of applied absorbers with minimum thickness and in the desired frequency bands and angular range are designed and their absorption characteristics are evaluated.

In the present paper, an attempt has been made to improve the mechanical properties of 5083 aluminum alloy welded by metal inert gas method followed by frictional stir process using an experimental method. For this purpose, the FSP process was performed in three rotation velocities of 500, 750, and 1000 rpm and with a forward velocity of 100 cm/min. In order to achieve the effect of FSP process on the microstructure of the tested alloy, welding samples, as well as frictional stir process samples, were studied. Thus, the microhardness and tensile strength of each sample were investigated. Then, using the genetic algorithm method, the optimal value of the rotation velocity was calculated. The results showed that the FSP process makes the heat affected area finer in terms of granulation and in addition, defects such as porosity and non-wettability due to the molten weld area are reduced or eliminated by the frictional stir process. On the other hand, the results of optimization indicate that the most suitable strength is obtained at a rotational velocity of 820 rpm. At this speed, the grain size is reduced by 96% compared to the heat affected area in the initial base state. Also, the cross-sectional images of the optimal sample fracture, unlike other samples, show that the fracture did not occur in the weld area, which can be attributed to the removal of cavities in the welded area by the frictional stir process.