Design and Optimization of Transformer by Combining Finite Element Approach and Improved Genetic Algorithm

The electrical transformer is a crucial component for altering voltage levels in the electricity system. Electrical transformers are normally constructed by trial and error, but some obstacles, such as expensive prices or unexpected performance, may occur from time to time. Often, transformer optimization design aims to reduce manufacturing costs or boost transformer efficiency. Several literatures have lately highlighted the finite element approach and artificial intelligence (AI) methodologies for enhancing transformer performance. For example, artificial neural networks(ANNs) may be used to forecast the function of core design parameters when employing AI to analyse transformer loss. Georgilakis and colleagues likewise employed artificial neural networks to minimize core loss in constructed transformers, and the Taguchi technique was used to improve individual core manufacturing process losses. A multiple technique is an effective solution even if the objective functions of transformer design are relatively complicated. For transformer optimization, one of the versatile approaches, which combines the finite element method (FEM) with the genetic algorithm (GA), is advantageous. The objective of the study is to provide the results of a multi-method investigation into transformer design optimization. The genetic algorithm (GA) and the finite element approach(FEM) are combined in this multiple methodology