Locomotive wheelset bearing quantitative diagnosis method based on adaptive filtering demodulation

摘要: The disclosure discloses a locomotive wheelset bearing quantitative diagnosis method based on adaptive filtering demodulation. demodulation comprises two stages of parameter training and real-time diagnosis, wherein in the stage, three filter parameters length, step length frequency band are traversed, optimal extraction fault impact features is implemented by iterative loop, optical an envelope spectrum adaptively determinedso as to calculate degree index FSI, corresponding relationship between symptom FSI established threshold determined; which obtained stage adopted, signal acquired real time filtered, solved, size current compared, so implement alarm for bearing.