A Classifier Development Process for Mechanical Health Diagnostics on US Army Rotorcraft
published: Nov. 7, 2016, recorded: August 2016, views: 984
Report a problem or upload filesIf you have found a problem with this lecture or would like to send us extra material, articles, exercises, etc., please use our ticket system to describe your request and upload the data.
Enter your e-mail into the 'Cc' field, and we will keep you updated with your request's status.
Due to various historical events, the Aviation Engineering Directorate (AED) of the United States Army has a unique, large data set describing the mechanical health of rotorcraft systems. This data set includes detailed information regarding non-critical failures and wear over a significant period and number of aircraft, each of which is instrumented to take measurements of mechanical vibrations and other parameters every flight. Attempts to utilize this data led AED to investigate the efficacy of machine learning and knowledge discovery from data (KDD) techniques. This paper outlines a tool–termed the Crawler–which AED developed to automate the process of creating diagnostic classifiers, and its application to two specific problems of interest: improving the usability and performance of a deployed gearbox health classifier, and rapidly developing a model to search sensor data for a newly identified fault mode.
Link this pageWould you like to put a link to this lecture on your homepage?
Go ahead! Copy the HTML snippet !