Eventos Anais de eventos
COBEM 2017
24th ABCM International Congress of Mechanical Engineering
Predictive Maintenance based on mechanical unbalance severity analysis of rotating machines
Submission Author:
Dionísio Henrique Carvalho de Sá Só Martins , RJ
Co-Authors:
Dionísio Henrique Carvalho de Sá Só Martins, Thiago de Moura Prego, Amaro Lima, Douglas Hemerly, Fabrício Lopes e Silva
Presenter: Douglas Hemerly
doi://10.26678/ABCM.COBEM2017.COB17-2082
Abstract
This paper presents a classification method for mechanical unbalance fault severity in rotating machines based on the force created by the unbalancing mass. The unbalance severity was broken down into 3 discrete levels, which are H (High), M (Medium) and L (Low). Test results verification led to the use of Random Forest algorithm as a classifier for the unbalance severity fault, reaching a global accuracy of 93.73%, with average standard deviation of 2.15% and total computational cost of 12.5 hours.
Keywords
Random Forest, mechanical unbalance, Predictive maintenance
