An identification scheme combining first principle knowledge, neural networks, and the likelihood function

An identification scheme is described for modeling uncertain systems. The method combines a physics-based model with a nonlinear mapping for capturing unmodeled physics and a statistical estimation procedure for quantifying any remaining process uncertainty. The technique has been used in predictive...

Full description

Saved in:
Bibliographic Details
Published inIEEE transactions on control systems technology Vol. 9; no. 1; pp. 186 - 199
Main Authors Vilim, R.B., Garcia, H.E., Chen, F.W.
Format Journal Article
LanguageEnglish
Published New York IEEE 01.01.2001
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects
Artificial neural networks
Control systems
Equations
False alarms
Feedforward neural networks
Fitting
Maintenance
Mathematical models
Multi-layer neural network
Neural networks
Nonlinearity
Physics
Predictive maintenance
Representations
System identification
Uncertain systems
Uncertainty
Online AccessGet full text

Cover

More Information
Summary:An identification scheme is described for modeling uncertain systems. The method combines a physics-based model with a nonlinear mapping for capturing unmodeled physics and a statistical estimation procedure for quantifying any remaining process uncertainty. The technique has been used in predictive maintenance applications to detect operational changes of mechanical equipment by comparing the model output with the actual process output. Tests conducted on a peristaltic pump to detect incipient failure are described. The inclusion of unmodeled physics and a statistical representation of uncertainties results in lower false alarm and missed detection rates than other methods.
Bibliography:ObjectType-Article-2
SourceType-Scholarly Journals-1
ObjectType-Feature-1
content type line 23
ObjectType-Article-1
ObjectType-Feature-2
ISSN:1063-6536
1558-0865
DOI:10.1109/87.896759