skip to main content
OSTI.GOV title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: An identification scheme combining first principle knowledge, neural networks, and the liklihood function.

Abstract

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.

Authors:
; ;
Publication Date:
Research Org.:
Argonne National Lab. (ANL), Argonne, IL (United States)
OSTI Identifier:
942433
Report Number(s):
ANL/RA/JA-31390
Journal ID: ISSN 1063-6536; IETTE2; TRN: US200916%%467
DOE Contract Number:  
DE-AC02-06CH11357
Resource Type:
Journal Article
Journal Name:
IEEE Trans. Control Syst. Technol.
Additional Journal Information:
Journal Volume: 9; Journal Issue: 1 ; Jan. 2001; Journal ID: ISSN 1063-6536
Country of Publication:
United States
Language:
ENGLISH
Subject:
32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATION; 97 MATHEMATICS AND COMPUTING; DETECTION; EQUIPMENT; FAILURES; MAINTENANCE; NEURAL NETWORKS; PUMPS; SIMULATION; FORECASTING

Citation Formats

Vilim, R B, Garcia, H E, and Chen, F W. An identification scheme combining first principle knowledge, neural networks, and the liklihood function.. United States: N. p., 2001. Web. doi:10.1109/87.896759.
Vilim, R B, Garcia, H E, & Chen, F W. An identification scheme combining first principle knowledge, neural networks, and the liklihood function.. United States. https://doi.org/10.1109/87.896759
Vilim, R B, Garcia, H E, and Chen, F W. Mon . "An identification scheme combining first principle knowledge, neural networks, and the liklihood function.". United States. https://doi.org/10.1109/87.896759.
@article{osti_942433,
title = {An identification scheme combining first principle knowledge, neural networks, and the liklihood function.},
author = {Vilim, R B and Garcia, H E and Chen, F W},
abstractNote = {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.},
doi = {10.1109/87.896759},
url = {https://www.osti.gov/biblio/942433}, journal = {IEEE Trans. Control Syst. Technol.},
issn = {1063-6536},
number = 1 ; Jan. 2001,
volume = 9,
place = {United States},
year = {2001},
month = {1}
}