Fault diagnosis in a rotor supported by active magnetic bearings / Detecção de falhas em rotores sustentados por mancais magneticos ativos

AUTOR(ES)
DATA DE PUBLICAÇÃO

2006

RESUMO

This work applies the methodology of fault diagnosis in rotating machinery supported by active magnetic bearings and active con1rol systems, excited by unbalance and white noise. This diagnostic applies the correlation matrices based on the Ljapunov matrix formulation and artificial neural network for linear stationary systems. The procedure uses only measured state variables, computing the correlation between the output variables. It is possible to derive specific relations involving the physical parameter of the system and the correlation matrices of the measured variables. Faults in the system can be detected by monitoring the variation of the physical parameter through a comparison of theoretical and estimated correlation functions. Artificial neural networks are used to map the correlations involving the variables, which are difficult to be measured. There is a large number of resultant compatibility equations and it is proposed a methodology to select the equations that establish relationships with the faults. The proposed fault diagnosis method can detect the fault present in the system and it is also possible to distinguish between mechanical and electrical fault as well as their location in the system

ASSUNTO(S)

fault diagnosis neural networks localização de falhas (engenharia) mancais redes neurais (computação) magnetic bearings rotor dynamics rotores - dinamica

ACESSO AO ARTIGO

Documentos Relacionados