| 摘要 |
<p><P>PROBLEM TO BE SOLVED: To provide a method for developing a unified quality assessment and providing an automated fault diagnostic tool for turbine machine systems and the like. <P>SOLUTION: A computer implemented process shown in the drawing develops and tracks machine unit signatures, machine site signatures and machine fleet signatures (110, 120) to evaluate various operational events (140, 150) and provide fault detection (130, 160). Sensor data acquired from the machine system during an operational event are transformed to correct or reduce variabilities in the data caused by ambient conditions and fuel quality. The transformed data is then analyzed using statistical methods to determine whether the operational event conforms to an expected normal behavior. This information is used to develop a single comprehensive quality assessment of the event. By saving, tracking and further updating operational event assessments over time, machine/component degradation may be recognized at any early stage. <P>COPYRIGHT: (C)2006,JPO&NCIPI</p> |
