Abstract: A diagnostic system and method for rotating machinery having mechanical problems combine AI-based interpretive reasoning with rotordynamic-based modeling and numerical optimization. A vibration response in the machinery to be diagnosed is first measured by machine sensors, and this measured response is used in a rule-based expert system to determine a probable cause of the machinery's mechanical problem. An appropriate finite element analytical model of the machinery is generated based on the probable cause. An optimizer computes the predicted response from the analytical model and compares it with the measured response. The model is automatically refined, guided by the expert system and numerical optimization, to match the predicted response with the measured response. The modifications to the model necessary to duplicate the measured response of the defective machinery are then indicative of the defects.

Abstract: System and method for detecting the occurrence, location and depth of a crack in the rotor of a turbine-generator. The location and depth of a crack are determined by monitoring the fundamental and histogram harmonic components of vibrations at certain predetermined points along the length of the rotor. The histogram harmonic components are normalized relative to the fundamental component, and the normalized histogram harmonic components are monitored to determine the location of the crack. The unnormalized histogram harmonic components are analyzed to determine the depth of the crack. The occurrence of a crack is detected by monitoring the amplitude and phase of rotor vibrations during an accel or decel operation to detect harmonic resonances which are characteristic of a crack in the rotor. The amplitude and phase data is filtered to eliminate spurious data, and it is interpolated to provide baseline and current data at matching speed points.