multi objective genetic algorithm

Banking, a vital economic pillar worldwide, thrives with effective management, aiding economic growth. Mitigating risks and addressing cost control are key challenges. Prioritizing strategies to enhance performance in both risk management and cost efficiency is crucial for the banking sector's success and economic stability. One approach is to select partners in such a way that the risk of bank insolvency and total costs are reduced, and the capital adequacy of the bank is increased. So, in this work, we first created a mathematical model to achieve the above goals in the field of banking using the approach of selecting partners. In this model, three objective functions are considered for the optimal selection of partners, two of which aim to minimize risk and cost, and the last objective is to maximize capital adequacy. To solve this multi-objective model, we implemented an integrated intelligent system. A combination of a multi-objective genetic algorithm and a neural network was used in this system. A multilayer perceptron neural network is used to calculate the nondeterministic parameters based on the data from different periods. The proposed method was evaluated using a numerical example in MATLAB software. The obtained results and their comparison with one of the classic algorithms show the superiority and reliability of this intelligent system. Using this system, the optimal partners can be selected to achieve the set goals. The most important factors in the field of risk have been identified. Then, a meta-heuristic multi-objective algorithm (NSGA-II) along with an intelligent neural network system has been used to optimally select partners. According to this intelligent system, a suitable methodology is presented along with the optimization algorithm.

The use of lasers is being considered as a modern method for forming process in recent years. This method has been used in various industries, such as aerospace, marine and oil industry. Extensive research has been done in the field of modeling and optimization of direct paths parameters with process of laser forming. Although forming in circular paths can be used for producing complex parts, due to some technical reasons, it is considered less. The main purpose of this paper is to detect the proper estimation model and obtain optimal variables conditions for complete circular paths in perforated circular parts by means of genetic algorithms. In this process the outer edges are fixed and the inner edges are being formed by laser. At first, the finite element simulation model is studied then the estimation model has been discussed, after that multi-objective functions have been examined with the least error and energy. Furthermore, the optimization results of the internal hole diameters are reported and analyzed in terms of Pareto charts. In conclusion, optimum forming conditions have been reported in terms of accuracy and energy for different diameters of holes. This study shows with acceptable increasing in the error rate, the required energy could be reduced. Also, increasing in the diameter of inside hole cause to increase energy and decrease of accuracy.