Signal processing aapplication based on an improved CLIQUE algorithm for marine motors' bearing faults detection

A new signal processing application method of an improved CLIQUE algorithm based on Park's vector modulus spectrum for bearing fault detection is presented. The major theoretical principles of the algorithm based on spectral analysis are described. The presented approach is suited for condition monitoring of machine system under varying operating and loading conditions. The performance of this technique is investigated through study of realistic current signals. Experimental results show that the proposed method has better performance and validity in realizing bearing faults of marine motors.