2023-03-072023-03-072023-01-25SOUZA, Klarissa Carvalho de. Identificação não-linear no espaço de estados por regressão esparsa de bancada motor-gerador. Orientador: Raphael Barros Teixeira. 2023. 53 f. Trabalho de Curso (Bacharelado em Engenharia Elétrica) – Faculdade de Engenharia Elétrica, Campus Universitário de Tucuruí, Universidade Federal do Pará, Tucuruí, 2023. Disponível em: https://bdm.ufpa.br:8443/jspui/handle/prefix/5375. Acesso em:.https://bdm.ufpa.br/handle/prefix/5375Over the years, there has been an interest in identifying dynamic systems using machine learning. These tools help, for example, in understanding and extracting information from experimental data and discovering model structures kill ´eaticos. Thus, this work aims to present the models obtained of the motor-generator bench using the sparse identification method of non-generator dynamics linear (SINDy), this method has been shown to be useful in the identification of non-linear dynamics, by assuming that the equations have only a few important terms that guide the dynamics. The SINDy approach solves a sparse regression problem, eliminating the terms whose coefficients are less than a limit. The components used in the Identification processes are based on the Threshold Least Square Optimizer (STLSq). Are The models obtained in the linear and non-linear experiment through the package are presented. PySINDy. The root squared error is calculated by the NRMSE metric for each of the models. At the end of the work it is seen that the SINDy method is able to identify the model of the motor-generator bench.Acesso AbertoOtimizadorSINDyIdentificação não-linearMotor-geradorOptimizerNon-linear identificationMotor-generatorCNPQ::ENGENHARIASTrabalho de Curso - Graduação - Monografia