Rotating machinery is a common class of machinery in industry. The root cause of faults in rotating machinery is often faulty like rolling element bearing and cavitations phenomenon. One may to increase operational reliability is to monitor these faults in order to maintain the machine viability. Condition monitoring is a field of technical activity in which selected parameters associated with machinery operation are observed for determining integrity, it is based on a fault diagnosis component which must be viable and reactive in order to detect early faults that affects the normal operation phase of the machine. In this paper we develop some novel real time signal processing techniques applied in feature extraction for machinery faults diagnosis. The effectiveness of our techniques is verified by the application to the fault diagnosis on a spatial rocket engine turbo-pum.
Ahmed ali Sofiane, Houcine Chafouk