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

Title: Predictive based monitoring of nuclear plant component degradation using support vector regression

Abstract

Nuclear power plants (NPPs) are large installations comprised of many active and passive assets. Degradation monitoring of all these assets is expensive (labor cost) and highly demanding task. In this paper a framework based on Support Vector Regression (SVR) for online surveillance of critical parameter degradation of NPP components is proposed. In this case, on time replacement or maintenance of components will prevent potential plant malfunctions, and reduce the overall operational cost. In the current work, we apply SVR equipped with a Gaussian kernel function to monitor components. Monitoring includes the one-step-ahead prediction of the component’s respective operational quantity using the SVR model, while the SVR model is trained using a set of previous recorded degradation histories of similar components. Predictive capability of the model is evaluated upon arrival of a sensor measurement, which is compared to the component failure threshold. A maintenance decision is based on a fuzzy inference system that utilizes three parameters: (i) prediction evaluation in the previous steps, (ii) predicted value of the current step, (iii) and difference of current predicted value with components failure thresholds. The proposed framework will be tested on turbine blade degradation data.

Authors:
 [1];  [2];  [2]
  1. Idaho National Lab. (INL), Idaho Falls, ID (United States). Dept. of Human Factors, Controls, Statistics
  2. Purdue Univ., West Lafayette, IN (United States). School of Nuclear Engineering
Publication Date:
Research Org.:
Idaho National Lab. (INL), Idaho Falls, ID (United States)
Sponsoring Org.:
USDOE Office of Nuclear Energy (NE)
OSTI Identifier:
1179374
Report Number(s):
INL/CON-14-32980
TRN: US1500161
DOE Contract Number:
AC07-05ID14517
Resource Type:
Conference
Resource Relation:
Conference: 9. International Topical Meeting on Nuclear Plant Instrumentation, Control, and Human Machine Interface Technologies, Charlotte, NC (United States), 23-26 Feb 2015
Country of Publication:
United States
Language:
English
Subject:
22 GENERAL STUDIES OF NUCLEAR REACTORS; NUCLEAR POWER PLANTS; OPERATING COST; MONITORING; REGRESSION ANALYSIS; VECTORS; FUZZY LOGIC; FAILURES; FORECASTING; MAINTENANCE; TURBINE BLADES; FUNCTIONS; INSPECTION; KERNELS; REACTOR COMPONENTS; Degradation Trend; Fuzzy Inference System; Prediction; Support Vector Regression

Citation Formats

Agarwal, Vivek, Alamaniotis, Miltiadis, and Tsoukalas, Lefteri H. Predictive based monitoring of nuclear plant component degradation using support vector regression. United States: N. p., 2015. Web.
Agarwal, Vivek, Alamaniotis, Miltiadis, & Tsoukalas, Lefteri H. Predictive based monitoring of nuclear plant component degradation using support vector regression. United States.
Agarwal, Vivek, Alamaniotis, Miltiadis, and Tsoukalas, Lefteri H. Sun . "Predictive based monitoring of nuclear plant component degradation using support vector regression". United States. doi:. https://www.osti.gov/servlets/purl/1179374.
@article{osti_1179374,
title = {Predictive based monitoring of nuclear plant component degradation using support vector regression},
author = {Agarwal, Vivek and Alamaniotis, Miltiadis and Tsoukalas, Lefteri H.},
abstractNote = {Nuclear power plants (NPPs) are large installations comprised of many active and passive assets. Degradation monitoring of all these assets is expensive (labor cost) and highly demanding task. In this paper a framework based on Support Vector Regression (SVR) for online surveillance of critical parameter degradation of NPP components is proposed. In this case, on time replacement or maintenance of components will prevent potential plant malfunctions, and reduce the overall operational cost. In the current work, we apply SVR equipped with a Gaussian kernel function to monitor components. Monitoring includes the one-step-ahead prediction of the component’s respective operational quantity using the SVR model, while the SVR model is trained using a set of previous recorded degradation histories of similar components. Predictive capability of the model is evaluated upon arrival of a sensor measurement, which is compared to the component failure threshold. A maintenance decision is based on a fuzzy inference system that utilizes three parameters: (i) prediction evaluation in the previous steps, (ii) predicted value of the current step, (iii) and difference of current predicted value with components failure thresholds. The proposed framework will be tested on turbine blade degradation data.},
doi = {},
journal = {},
number = ,
volume = ,
place = {United States},
year = {Sun Feb 01 00:00:00 EST 2015},
month = {Sun Feb 01 00:00:00 EST 2015}
}

Conference:
Other availability
Please see Document Availability for additional information on obtaining the full-text document. Library patrons may search WorldCat to identify libraries that hold this conference proceeding.

Save / Share: