A real-time intelligent multiple fault diagnostic system

Modern manufacturing systems and their failure modes are very complex, and efficient fault diagnosis is essential for higher productivity. However, traditional fault diagnostic systems that perform sequential fault diagnosis can fail during diagnosis when fault propagation is very fast. This paper d...

Full description

Saved in:
Bibliographic Details
Published inInternational journal of advanced manufacturing technology Vol. 29; no. 5-6; pp. 590 - 597
Main Authors Bae, Yong-Hwan, Lee, Seok-Hee, Kim, Ho-Chan, Lee, Byung-Ryong, Jang, Jaejin, Lee, Jay
Format Journal Article
LanguageEnglish
Published Heidelberg Springer Nature B.V 01.09.2006
Subjects
Artificial neural networks
Diagnostic systems
Failure modes
Fault diagnosis
Graphical representations
Modules
Multiprocessing
Personal computers
Propagation
Real time
Signal generation
Signal generators
Workstations
Online AccessGet full text

Cover

More Information
Summary:Modern manufacturing systems and their failure modes are very complex, and efficient fault diagnosis is essential for higher productivity. However, traditional fault diagnostic systems that perform sequential fault diagnosis can fail during diagnosis when fault propagation is very fast. This paper describes a real-time intelligent multiple fault diagnostic system (RIMFDS). This system deals with multiple fault diagnosis, and is based on multiprocessing by using a strata hierarchical artificial neural network (SHANN). If another fault occurs while an existing symptom is being diagnosed, the corresponding diagnosis module is triggered, and the fault diagnosis module of the new faulty unit begins to diagnose the faults in real time. RIMFDS can diagnose multiple faults with fast fault propagation and complex physical phenomena. The system consists of two main parts. One is a personal computer for remote signal generation and transmission, and the other is a host system for multiple fault diagnosis. The signal generator generates various faulty signals and image information and sends them to the host. The host has various modules and agents for efficient multiple fault diagnosis. A SUN workstation is used as a host for multiple fault diagnosis and graphic representation of the results.
ISSN:0268-3768
1433-3015
DOI:10.1007/BF02729113