Determination of synchronous machine parameters through the SSFRT test and artificial neural networks

摘要

The frequency response test on synchronous generators has been increasing in the last decades, but the high cost of equipment used for conducting the test is still a stumbling block for both manufacturers and end consumers. This study aims to propose a methodology for obtaining parameters, through the use of neural networks. This study treats the results designed through frequency tests, in which the proposal was the use of low-cost equipment to perform them. In addition, a process of optimisation of the neural network was developed during the development of this study.