Failure recognition alogrithm based on QDFD and GMM

2008 
Against the shortcomings of quartile deviation fractal dimension(QDFD),which is sensitive to signal amplitude and distribution,an improved algorithm that can be used in failure recognition was introduced.The QDFD and the intercept that was got when the QDFD was calculated were composed to the eigenvector.Then the Gaussian mixture model(GMM) was used to failure modelling and Bayes classifier was used to failure recognition(QDFD-GMM).To the same gear vibration signals with faults,the QDFD-GMM and the GMM of reconstructed phase space(RPS-GMM) were used to sort comparatively.The result shows that the better accuracy,faster operation speed and stronger robustness could be got by proposed method.
    • Correction
    • Source
    • Cite
    • Save
    • Machine Reading By IdeaReader
    0
    References
    0
    Citations
    NaN
    KQI
    []