Open architecture framework for distributed real-time fault diagnosing

Hongan Wang; Guozhong Dai

doi:10.1117/12.339954

4 February 1999 Open architecture framework for distributed real-time fault diagnosing

Hongan Wang, Guozhong Dai

Proceedings Volume 3589, Process Control and Sensors for Manufacturing II; (1999) https://doi.org/10.1117/12.339954
Event: Nondestructive Evaluation Techniques for Aging Infrastructures and Manufacturing, 1999, Newport Beach, CA, United States

Abstract

Fault diagnosing has recently received considerable attention. Its applicability is severely restricted by the computational complexity involved in the diagnosing process. In this paper, it is presented an open architecture framework for distributed real-time fault diagnosing in an industrial environment. Within this framework, all work units comprising the manufacturing system are modeled using intelligent agents. Each agent has autonomous and cooperative functions, observing the local fault diagnosing process via the combination of model-based qualitative and heuristic reasoning with learning techniques; and cooperatively reporting the primary diagnosis result to the diagnosis manager, which supervises the global fault diagnosing process using the constraint propagation technology. To fast the constraint propagation, a matrix- based constraint parallel propagation method is discussed, which greatly reduces the computational overhead. Also, a formal description method for agent's structure is given, which can be used to describe agents and verify their functions.

Citation Download Citation

Hongan Wang and Guozhong Dai "Open architecture framework for distributed real-time fault diagnosing", Proc. SPIE 3589, Process Control and Sensors for Manufacturing II, (4 February 1999); https://doi.org/10.1117/12.339954

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available