A neural network mode inference engine for the advisory system for training and safety /

accomplish.

Bibliographic Details
Main Author: Nguyen, Thinh Xuan
Format: Thesis eBook
Language:English
Published: [Place of publication not identified] : [publisher not identified] ; 1996.
Subjects:
Online Access:Link to OAKTrust copy
Description
Summary:accomplish.
configuring the aircraft for different phases of the flight.
correct mode inferences which were slightly more accurate
Engineering Flight Simulator (EFS). The ANNSR returned
In order to perform this task, the ASTRAS system is endowed
infer the correct flight mode even when the aircraft was off
information to the pilot, assisting him in properly
membership functions. Although functional, the limitations
neural network based SR (ANNSR). The goal of the ANNSR was
nominal conditions, a task which the fuzzy logic SR failed to
of this method have prompted the development of an artificial
off nominal flight conditions. The ANNSR performed better
Recognizer (SR) which is able to discern the flight mode from
sector, the Advisory System for Training and Safety (ASTRAS)
sensor readings. The current SR is based on fuzzy logic
than the fuzzy logic based SR in flight tests on the
than the fuzzy logic SR during nominal flight conditions.
The most important result was that the AN-NSR was able to
To improve the safety record of the private general aviation
to provide more accurate mode inferences, particularly during
was conceived. The ASTRAS software provides timely
with an artificial intelligence engine or Situation
Item Description:"Major subject: Aerospace Engineering".
Vita.
Physical Description:xiii, 94 leaves : illustrations ; 28 cm.
Also available online.
Issued also on microfiche from Lange Micrographics.
Bibliography:Includes bibliographical references: pages 73-74.