Implementación de un sistema de diagnóstico por monitoreo de vibraciones en la caja multiplicadora y el generador para un procedimiento de toma de decisiones por redes neuronales para el aerogenerador g52/850 número 5 del Parque Eólico Los Santos.
MetadatosMostrar el registro completo del ítem
This project is about the implementation of a prototype of a vibration monitoring system for the gear box and the generator in the wind turbine number 5, model G52 / 850, GAMESA brand, located in Los Santos Wind Farm, which is also intended to work as a complement in the methodology based on artificial neuronal networks to predict the accumulated useful life, currently being developed in this wind farm. Since November 2016, the management department of the Los Santos Wind Farm started with the ambitious idea of performing a transition from a corrective maintenance to a maintenance based on condition, so the commitment was made to develop the artificial neuronal networks to predict the accumulated useful life with the help of advanced students of engineering from the Instituto Tecnológico de Costa Rica (Technological Institute of Costa Rica). The need to elaborate a system that allows the gathering of vibration data was found thanks to the development of this investigation. To begin with, the equipment which is intended to be installed will be analyzed in order to know its characteristics and the scope we can obtain from it. Once we define the condition of the equipment, a study of the previous works and an analysis of the plant will be carried out to determine their present conditions to perform a proper installation. Finally, the study of the parameters according to the norm ISO 10816 is made with the objective of starting the installed monitoring system. To conclude, we will obtain a vibrations monitoring system which starts a follow up process with the objective to refine the results
Proyecto de Graduación (Licenciatura en Ingeniería en Mantenimiento Industrial) Insituto Tecnológico de Costa Rica, Escuela de Ingeniería en Mantenimiento Industrial, 2017.