Diagnosing process faults using neural network models

Conference · Mon Nov 01 00:00:00 EST 1993

OSTI ID:10193614

Buescher, K L; Jones, R D; Messina, M J

In order to be of use for realistic problems, a fault diagnosis method should have the following three features. First, it should apply to nonlinear processes. Second, it should not rely on extensive amounts of data regarding previous faults. Lastly, it should detect faults promptly. The authors present such a scheme for static (i.e., non-dynamic) systems. It involves using a neural network to create an associative memory whose fixed points represent the normal behavior of the system.

• Research Organization: Los Alamos National Lab., NM (United States)
• Sponsoring Organization: USDOE, Washington, DC (United States)
• DOE Contract Number: W-7405-ENG-36
• OSTI ID: 10193614
• Report Number(s): LA-UR-93-3598; CONF-9309272-1; ON: DE94002633; TRN: 93:004510
• Resource Relation: Conference: Allerton conference on communication, control, and computing,Urbana, IL (United States),29 Sep - 1 Oct 1993; Other Information: PBD: [1993]
• Country of Publication: United States
• Language: English

Related Subjects

99 GENERAL AND MISCELLANEOUS//MATHEMATICS, COMPUTING, AND INFORMATION SCIENCE
42 ENGINEERING
DIAGNOSTIC TECHNIQUES
MATHEMATICAL MODELS
RELIABILITY
FAILURES
PROBABILISTIC ESTIMATION
NEURAL NETWORKS
NONLINEAR PROBLEMS
SIGNAL CONDITIONING
PULSE GENERATORS
ARTIFICIAL INTELLIGENCE
SYSTEM FAILURE ANALYSIS
990200
426000
MATHEMATICS AND COMPUTERS
COMPONENTS
ELECTRON DEVICES AND CIRCUITS