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

Abstract

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.

Keywords

• neural nets
• frequency response
• synchronous generators
• electric machine analysis computing
• machine testing
• SSFRT test
• artificial neural networks
• frequency response test
• synchronous generators
• frequency tests
• low-cost equipment
• neural network optimisation process
• synchronous machine parameter determination