论文部分内容阅读
A new method of fault analysis and detection by signal classification in rotating machines is presented. The Local Wave time-frequency spectrum which is a new method for processing a non- stationary signal is used to produce the representation of the signal. This method allows the decomposition of one-dimensional signals into intrinsic mode functions(IMFs) using empirical mode decomposition and the calculation of a meaningful multi-component instantaneous frequency. Applied to fault signals, it provides new time-frequency attributes. Then the moments and margins of the time-frequency spectrum are calculated as the feature vectors. The probabilistic neural network is used to classify different fault modes. The accuracy and robustness of the proposed methods is investigated on signals obtained during the different fault modes(early rub, loose, misalignment of the rotor) .
A new method of fault analysis and detection by signal classification in rotating machines is presented. The Local Wave time-frequency spectrum which is a new method for processing a non-stationary signal is used to produce the representation of the signal. decomposition of one-dimensional signals into intrinsic mode functions (IMFs) using empirical mode decomposition and the calculation of a meaningful multi-component instantaneous frequency. Applied to fault signals, it provide new time-frequency attributes. Then the moments and margins of the time The accuracy and robustness of the proposed methods is investigated on signals obtained during the different fault modes (early rub, loose, misalignment of the rotor ).