An Intelligent Tutor for Diagnosing Faults in an Aircraft Power Distribution System

Abstract

A domain-general authoring system, DIAG, was employed to develop an intelligent tutor for diagnosing faults in a dual generator AC/DC power distribution system. The application provides an operable simulation of the front panel used to control power distribution in a dual engine aircraft, 148 replaceable units that comprise the functional elements of tile target system, and a number of test points for performing fault isolation tests. In all, 105 faults are simulated for presentation to the learner. Based entirely upon the model of tile power distribution system, DIAG was able to generate context-specific advisement concerning 1) the effectiveness of the diagnostic strategy employed by an individual learner, 2) the rationality of the learner's suspicions considering the symptoms seen, and 3) recommended next steps to further isolate tile simulated fault. The three most significant findings resulting from this development effort were that 1) no changes were required in tile DIAG authoring system or intelligent advisement functions to implement this new and complex domain, 2) the instructional intelligence, in the form of generated dialogues, was produced automatically and required no acquisition or representation of human expertise, and 3) the application was produced in a very short time, approximately 22 man days.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Dec 01, 1997
Accession Number
ADA334921

Entities

People

  • Douglas M. Towne

Organizations

  • University of Southern California

Tags

Communities of Interest

  • Air Platforms
  • Energy and Power Technologies

DTIC Thesaurus Topics

  • Abstracts
  • Acquisition
  • Aircrafts
  • Checkout Procedures
  • Connectors
  • Generators
  • Indicator Lights
  • Indicators
  • Instructors
  • Military Aircraft
  • Power Distribution
  • Simulations
  • Standards
  • Students
  • Switches
  • Test Equipment
  • Training

Readers

  • Artificial Intelligence
  • Electrical Engineering
  • Fault Tolerant Diagnosis of Black and White Balloon Isolation Tests Using ¥.