PUBLICACIÓN

ARTÍCULO

FPGA-based entropyneuralprocessorforonlinedetectionof multiple combinedfaultsoninductionmotors

E. Cabal-Yepez, M.Valtierra-Rodriguez, R.J.Romero-Troncoso, A.Garcia-Perez,R.A. Osornio-Rios, H.Miranda-Vidales, R.Alvarez-Salas
Mechanical SystemsandSignalProcessing, Elsevier, 2012., 2012.

ABSTRACT:

For industry,afaultyinductionmotorsignifiesproductionreductionandcostincrease. Real-worldinductionmotorscanhaveoneormorefaultspresentatthesametimethat can misleadtoawrongdecisionaboutitsoperationalcondition.Thedetectionof multiplecombinedfaultsisademandingtask,difficulttoaccomplishevenwith computingintensivetechniques.Thisworkintroducesinformationentropyand artificialneuralnetworksfordetectingmultiplecombinedfaultsbyanalyzingthe 3-axis startupvibrationsignalsoftherotatingmachine.Afieldprogrammablegate arrayimplementationisdevelopedforautomaticonlinedetectionofsingleand combinedfaultsinrealtime.