Vehicle Health Inferencing Using Feature-Based Neural-Symbolic Networks-Reference-Cited by-同舟云学术

Vehicle Health Inferencing Using Feature-Based Neural-Symbolic Networks

Published:2013-10-21 Issue: Volume: Page:
ISSN:
Container-title:Volume 3: Nonlinear Estimation and Control; Optimization and Optimal Control; Piezoelectric Actuation and Nanoscale Control; Robotics and Manipulators; Sensing; System Identification (Estimation for Automotive Applications, Modeling, Therapeutic Control in Bio-Systems); Variable Structure/Sliding-Mode Control; Vehicles and Human Robotics; Vehicle Dynamics and Control; Vehicle Path Planning and Collision Avoidance; Vibrational and Mechanical Systems; Wind Energy Systems and Control
language:
Short-container-title:

Author:

Aasted Christopher M.¹,Lim Sunwook²,Shoureshi Rahmat A.²

Affiliation:

1. Harvard Medical School, Boston Children’s Hospital, Boston, MA

2. New York Institute of Technology, Old Westbury, NY

Abstract

In order to optimize the use of fault tolerant controllers for unmanned or autonomous aerial vehicles, a health diagnostics system is being developed. To autonomously determine the effect of damage on global vehicle health, a feature-based neural-symbolic network is utilized to infer vehicle health using historical data. Our current system is able to accurately characterize the extent of vehicle damage with 99.2% accuracy when tested on prior incident data. Based on the results of this work, neural-symbolic networks appear to be a useful tool for diagnosis of global vehicle health based on features of subsystem diagnostic information.

Publisher

American Society of Mechanical Engineers

Link

http://asmedigitalcollection.asme.org/DSCC/proceedings-pdf/doi/10.1115/DSCC2013-3831/4444400/v003t41a004-dscc2013-3831.pdf