Intelligent diagnosis method for plant machinery using wavelet transform, rough sets and neural network

This paper proposes an intelligent diagnosis method for plant machinery using wavelet transform (WT), rough sets (RS) and partially-linearized neural network (PNN) to detect faults and distinguish fault type at an early stage. The WT is used to extract feature signal of each machine state from measured vibration signal for high-accurate diagnosis of states. The decision method of optimum frequency area for the extraction of feature signal is discussed using real plant data. We also propose the diagnosis method by using "Partially-linearized Neural Network (PNN)" by which the type of faults can be automatically distinguished on the basis of the probability distributions of symptom parameters. The symptom parameters are non-dimensional parameters which reflect the characteristics of time signal measured for condition diagnosis of plant machinery. The knowledge for the PNN learning can be acquired by using the Rough Sets (RS) of the symptom parameters. The practical examples of diagnosis for rotating machinery are shown to verify the efficiency of the method.