A New Automatic Diagnosis Method Based on the Multivariable Analysis for Structural Faults of Rotary Machinery

摘要

To effectively detect and identify the structural faults of the rotating machinery, a new kind of symptom parameters of the vibration signal measured inrnmultiple directions is proposed (hereinafter referred to as the structural feature symptom parameter SFSP), the method to extract anomaly signals basedrnon the multi-band filter, the method to enhance the sensitivity of the symptom parameters using the least square mapping, and the automatic fault diagnosisrnsystem established for the structural faults of the rotating machinery in combination with multivariate analysis (principal component analysis) method. Inrnaddition, the validity of the diagnostic method was also verified with reference to the experimental data measured on the rotating machine in differentrnstates of structural faults.