Study of optimization of electromechanical systems by intelligent design methods
Students Name: Muliak Nazarii Volodymyr
Qualification Level: magister
Speciality: Information Technology Design
Institute: Institute of Computer Science and Information Technologies
Mode of Study: full
Academic Year: 2022-2023 н.р.
Language of Defence: англійська
Abstract: Muliak Nazarii, Zdobytskyi A.Y (supervisor). Study of optimization of electromechanical systems by intelligent design methods. Master`s thesis. – Lviv Polytechnic National University, Lviv 2020. Extended abstract In this paper, we compare the, the work of group algorithms for the optimization. The purpose of the research is to find an optimal algorithm for optimizing technological design in the direction of microelectromechanical systems (MEMS). Each of these methods is used in practical calculations when solving optimization problems in the design of complex systems. But the use of data algorithms to solve generative design tasks requires additional knowledge. As a result of the study, a set of analytical data was obtained, on the basis of which the analysis and comparison of optimization algorithms was performed. Analysis of the effectiveness of the application of individual methods in practice will help to choose the optimal algorithm and increase the effectiveness of generative design in practice. In addition, with the help of modification of the above methods, it is possible to obtain additional parameters and results of optimization of applied problems. The study of modifications of optimization algorithms makes it possible to change the accuracy and speed of optimization in specialized areas of generative design at the expense of given changes. Since microelectronic systems differ in principle of operation and interaction from macrosystems, their design requires a new approach and modification of standard design methods. Optimization methods of applied problems are widely used at the moment in applied design problems. But some areas of their application require additional analysis and research. The research results can be used to modify optimal methods and apply modifications in specialized tasks, in particular in the direction of designing MEMS and creating application programs. In addition, the practical implementation of individual methods in the form of real software has been carried out, allowing to obtain researched tools for the analysis of individual applied problems. For this purpose, the optimal environment was chosen and tools were developed to ensure the openness of the code and access of individual groups of developers for finalizing and expanding software protection. The object of research is optimization algorithms of generative design with machine learning The purpose of the work is the analysis and modification of optimization algorithms for the study of lattice structures based on automatically generated structural cells. Possibility of implementing the modifications of methods in practice for the study of metamaterials based on generative lattice structures. Research methods – study of basic optimization methods and cells that used to generate lattice structures. The application of optimization methods for the analysis of lattice structures and the use of a neural network to filter individual cell models according to the given constraints.