Diagnóstico de fallos en generadores tipo jaula de ardilla de turbinas eólicas mediante la señal de corriente
In relation to maintenance, the main strategy of the wind industry is predictive maintenance based on the constant monitoring of various types of signals obtained from the components of the wind turbines (WTs) through sensors. Since all dynamic equipment produces acoustic or ultrasound vibration, th...
| Autor: | |
|---|---|
| Formato: | tesis doctoral |
| Estado: | Versión publicada |
| Fecha de publicación: | 2022 |
| País: | España |
| Recursos: | Universidad de Valladolid |
| Repositorio: | UVaDOC. Repositorio Documental de la Universidad de Valladolid |
| OAI Identifier: | oai:uvadoc.uva.es:10324/60301 |
| Acesso em linha: | https://doi.org/10.35376/10324/60301 https://uvadoc.uva.es/handle/10324/60301 |
| Access Level: | acceso abierto |
| Palavra-chave: | Generadores eléctricos Mantenimiento (Ingeniería) Electric generador Generador eléctrico Current signal Señal de corriente Fault diagnosis Diagnóstico de fallo 3310.04 Ingeniería de Mantenimiento |
| Resumo: | In relation to maintenance, the main strategy of the wind industry is predictive maintenance based on the constant monitoring of various types of signals obtained from the components of the wind turbines (WTs) through sensors. Since all dynamic equipment produces acoustic or ultrasound vibration, this type of signal is generally used to monitor from the blades to the tower, and most of the existing references on fault detection and diagnosis use the vibration signal. However, there is a lack of publications on other types of signals, especially when it comes to field work. Therefore, this thesis is dedicated exclusively to the study of the current signal and its application to the maintenance of the squirrel-cage induction generator used in WTs. The research includes from the historical aspects of the use of the current signal, theoretical foundations on how the components associated with faults are manifested in the signal spectrum and the methodologies for detection and diagnosis, ranging from techniques for signal processing and traditional artificial intelligence (AI) models, to deep learning models, which represent the state of the art in AI models |
|---|