eduzhai > Applied Sciences > Computer Science >

Contextual normalization applied to aircraft gas turbine engine diagnosis

  • paiqiu
  • (0) Download
  • 20210805
  • Save

... pages left unread,continue reading

Document pages: 45 pages

Abstract: Diagnosing faults in aircraft gas turbine engines is a complex problem. It involves several tasks,including rapid and accurate interpretation of patterns in engine sensor data. We have investigatedcontextual normalization for the development of a software tool to help engine repair technicianswith interpretation of sensor data. Contextual normalization is a new strategy for employingmachine learning. It handles variation in data that is due to contextual factors, rather than thehealth of the engine. It does this by normalizing the data in a context-sensitive manner. Thislearning strategy was developed and tested using 242 observations of an aircraft gas turbineengine in a test cell, where each observation consists of roughly 12,000 numbers, gathered over a12 second interval. There were eight classes of observations: seven deliberately implanted classesof faults and a healthy class. We compared two approaches to implementing our learning strategy:linear regression and instance-based learning. We have three main results. (1) For the givenproblem, instance-based learning works better than linear regression. (2) For this problem,contextual normalization works better than other common forms of normalization. (3) Thealgorithms described here can be the basis for a useful software tool for assisting technicians withthe interpretation of sensor data.

Please select stars to rate!

         

0 comments Sign in to leave a comment.

    Data loading, please wait...
×