Hybrid Diagnosis with Unknown Behavioral Modes

Abstract

A novel capability of discrete model-based diagnosis methods is the ability to handle unknown modes where no assumption is made about the behavior of one or several components of the system. This paper incorporates this novel capability of model-based diagnosis into a hybrid estimation scheme by calculating partial filters. The filters are based on causal and structural analysis of the specified components and their interconnection within the hybrid automaton model. Incorporating unknown modes provides a robust estimation scheme that can cope, unlike other hybrid estimation and multi-model estimation schemes, with unmodeled situations and partial information.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
May 04, 2002
Accession Number
ADP012700

Entities

People

  • Brian C. Williams
  • Michael W. Hofbaur

Organizations

  • University of Graz

Tags

Communities of Interest

  • Space

DTIC Thesaurus Topics

  • Algorithms
  • Artificial Intelligence
  • Automata
  • Computational Science
  • Computer Science
  • Control Systems
  • Difference Equations
  • Equations
  • Estimators
  • Failure Mode And Effect Analysis
  • Hidden Markov Models
  • Hybrid Systems
  • Kalman Filters
  • Lisp Programming Language
  • Mathematical Models
  • Plant Growth
  • Structural Analysis

Fields of Study

  • Engineering

Readers

  • Computational Modeling and Simulation
  • Neural Network Machine Learning.
  • Statistical inference.