The influence of PVTf on machine learning estimation of IGBT junction temperature
Andrei Ribeiro, Rômullo Carvalho, Paulo da Silva, Geyciane Lima, Guilherme Prym, Tárcio Barros, Francisco Marques, Marcelo Villalva
CAPÍTULO DE LIVRO
Inglês
Este artigo foi apresentado no evento International Conference on Electrical Systems & Automation (ICESA), 2023
Agradecimentos: This study was financed in part by CAPES – Finance Code 001 and in part by Total Energies/CEPETRO under FUNCAMP/UNICAMP agreement 6002.4. The authors would like to thank the late Prof. Marcelo Gradella Villalva (1978-2023) for the knowledge he passed on about photovoltaic solar...
Ver mais
Agradecimentos: This study was financed in part by CAPES – Finance Code 001 and in part by Total Energies/CEPETRO under FUNCAMP/UNICAMP agreement 6002.4. The authors would like to thank the late Prof. Marcelo Gradella Villalva (1978-2023) for the knowledge he passed on about photovoltaic solar energy, electric machines and power electronics, for his hard work in designing the Laboratory of Energy and Photovoltaic Systems (LESF) at UNICAMP, and for all the funding he helped secure for research projects
Ver menos
Abstract: The literature indicates that the PV inverter is the element of a photovoltaic plant most prone to failure. For this reason, power electronics converters are generally responsible for most photovoltaic projects' operating and maintenance costs. This article describes the influence of PVTf...
Ver mais
Abstract: The literature indicates that the PV inverter is the element of a photovoltaic plant most prone to failure. For this reason, power electronics converters are generally responsible for most photovoltaic projects' operating and maintenance costs. This article describes the influence of PVTf (power, voltage, ambient temperature, and frequency) on the IGBT junction temperature. We use correlation coefficients and machine learning techniques on the dataset in (Tomislav et al. in IEEE Transactions on Power Electronics 34:7161-7171, 2019). We perform feature selection and the impacts of removing one or more inputs on model training. Data analysis indicates that input power is the most important attribute in the studied dataset and decision tree model presented the best results for the regression problem when compared with MLP and linear regressor. The tool took good advantage of the most important features at the beginning and only considered the less important ones for fine-tuning in the most distant nodes
Ver menos
COORDENAÇÃO DE APERFEIÇOAMENTO DE PESSOAL DE NÍVEL SUPERIOR - CAPES
001
Fechado
The influence of PVTf on machine learning estimation of IGBT junction temperature
Andrei Ribeiro, Rômullo Carvalho, Paulo da Silva, Geyciane Lima, Guilherme Prym, Tárcio Barros, Francisco Marques, Marcelo Villalva
The influence of PVTf on machine learning estimation of IGBT junction temperature
Andrei Ribeiro, Rômullo Carvalho, Paulo da Silva, Geyciane Lima, Guilherme Prym, Tárcio Barros, Francisco Marques, Marcelo Villalva
Fontes
|
ADVANCES in control power systems and emerging technologies (ICESA 2023) Cham : Springer, 2024. p. v. 2, p. 107-116 |