You need JavaScript to view this

Neural networks for sensor validation and plant-wide monitoring

Abstract

The feasibility of using neural networks to characterize one or more variables as a function of other than related variables has been studied. Neural network or parallel distributed processing is found to be highly suitable for the development of relationships among various parameters. A sensor failure detection is studied, and it is shown that neural network models can be used to estimate the sensor readings during the absence of a sensor. (author). 4 refs.; 3 figs.
Authors:
Eryurek, E; [1]  Turkcan, E [2] 
  1. Tennessee Univ., Knoxville, TN (United States). Dept. of Nuclear Engineering
  2. Netherlands Energy Research Foundation (ECN), Petten (Netherlands)
Publication Date:
Aug 01, 1991
Product Type:
Technical Report
Report Number:
ECN-RX-91-089
Reference Number:
SCA: 220400; 210400; PA: AIX-24:030151; SN: 93000955844
Resource Relation:
Other Information: PBD: Aug 1991
Subject:
22 GENERAL STUDIES OF NUCLEAR REACTORS; 21 SPECIFIC NUCLEAR REACTORS AND ASSOCIATED PLANTS; NEURAL NETWORKS; FEASIBILITY STUDIES; NUCLEAR POWER PLANTS; PARAMETRIC ANALYSIS; REACTOR CONTROL SYSTEMS; REACTOR SAFETY; 220400; 210400; CONTROL SYSTEMS; POWER REACTORS, NONBREEDING, OTHERWISE MODERATED OR UNMODERATED
OSTI ID:
10132117
Research Organizations:
Netherlands Energy Research Foundation (ECN), Petten (Netherlands)
Country of Origin:
Netherlands
Language:
English
Other Identifying Numbers:
Other: ON: DE93619424; TRN: NL92C0484030151
Availability:
OSTI; NTIS; INIS
Submitting Site:
NLN
Size:
[8] p.
Announcement Date:
Jul 04, 2005

Citation Formats

Eryurek, E, and Turkcan, E. Neural networks for sensor validation and plant-wide monitoring. Netherlands: N. p., 1991. Web.
Eryurek, E, & Turkcan, E. Neural networks for sensor validation and plant-wide monitoring. Netherlands.
Eryurek, E, and Turkcan, E. 1991. "Neural networks for sensor validation and plant-wide monitoring." Netherlands.
@misc{etde_10132117,
title = {Neural networks for sensor validation and plant-wide monitoring}
author = {Eryurek, E, and Turkcan, E}
abstractNote = {The feasibility of using neural networks to characterize one or more variables as a function of other than related variables has been studied. Neural network or parallel distributed processing is found to be highly suitable for the development of relationships among various parameters. A sensor failure detection is studied, and it is shown that neural network models can be used to estimate the sensor readings during the absence of a sensor. (author). 4 refs.; 3 figs.}
place = {Netherlands}
year = {1991}
month = {Aug}
}