Detection Method and Experimental Research on Generator Bolt Loosening Fault Characteristics

Abstract This paper proposes a method for diagnosing bolt looseness faults using the principle of PCA to extract time-domain features monitoring data. First all, five dimensionless factors IMF are calculated after empirical mode decomposition (EMD) is performed on original Then, principal component analysis (PCA) applied data vectors, which processed by dimensionality reduction and residual space projection, calculate prediction error sample. At last, fault judgment test loosening was carried out bench intelligent water supply system. The results show that model can effectively judge fault.