Accommodating power plant anomalies via an artificial neural network-based reconfigurable control

James A. Turso, Robert Edwards, Brie E. Turso

Research output: Contribution to journalArticle

Abstract

A reconfigurable control strategy has been developed using a feed-forward Artificial Neural Network (ANN) implemented on a Bailey Network 90 digital control system requiring relatively minor modifications to the plant controller. An experimentally verified simulation of a secondary system's deaerating feedwater heater of a nuclear power plant was used to demonstrate the feasibility of the concept. The controller uses the ANN to decide when to switch from normal level control to alternate pressure control (via the level control valves) in the event of a rapid pressure decrease, possibly due to loss of feedwater heating, i.e., a phenomenon known as deaerator quenching. A prolonged rapid pressure decrease would result in feedpump cavitation (i.e., Net Positive Suction Head less than zero) due to the change in pressure reaching the pump suction before the corresponding change in saturation temperature. The ANN uses the deaerator level, pressure, and rate of change of pressure to develop a system status signal (i.e., reconfiguration switch signal) between 0.0 and 1.0. The existing level controller, with some minor modifications, is reconfigured to a pressure controller upon receiving a switch signal of 0.485. When tested with a simulated pressure regulator malfunction the reconfigurable control scheme displayed superior performance (compared with the original system) by arresting the pressure decrease and maintaining NPSH above zero for a prolonged period of time.

Original languageEnglish (US)
Pages (from-to)75-91
Number of pages17
JournalJournal of Intelligent Systems
Volume16
Issue number1
DOIs
StatePublished - Jan 1 2007

Fingerprint

Power plants
Neural networks
Controllers
Level control
Switches
Feedwater heaters
Pressure regulators
Digital control systems
Signal systems
Pressure control
Cavitation
Nuclear power plants
Quenching
Pumps
Heating
Temperature

All Science Journal Classification (ASJC) codes

  • Software
  • Information Systems
  • Artificial Intelligence

Cite this

@article{fc752f7b8a024e0f907ba2c837a681af,
title = "Accommodating power plant anomalies via an artificial neural network-based reconfigurable control",
abstract = "A reconfigurable control strategy has been developed using a feed-forward Artificial Neural Network (ANN) implemented on a Bailey Network 90 digital control system requiring relatively minor modifications to the plant controller. An experimentally verified simulation of a secondary system's deaerating feedwater heater of a nuclear power plant was used to demonstrate the feasibility of the concept. The controller uses the ANN to decide when to switch from normal level control to alternate pressure control (via the level control valves) in the event of a rapid pressure decrease, possibly due to loss of feedwater heating, i.e., a phenomenon known as deaerator quenching. A prolonged rapid pressure decrease would result in feedpump cavitation (i.e., Net Positive Suction Head less than zero) due to the change in pressure reaching the pump suction before the corresponding change in saturation temperature. The ANN uses the deaerator level, pressure, and rate of change of pressure to develop a system status signal (i.e., reconfiguration switch signal) between 0.0 and 1.0. The existing level controller, with some minor modifications, is reconfigured to a pressure controller upon receiving a switch signal of 0.485. When tested with a simulated pressure regulator malfunction the reconfigurable control scheme displayed superior performance (compared with the original system) by arresting the pressure decrease and maintaining NPSH above zero for a prolonged period of time.",
author = "Turso, {James A.} and Robert Edwards and Turso, {Brie E.}",
year = "2007",
month = "1",
day = "1",
doi = "10.1515/JISYS.2007.16.1.75",
language = "English (US)",
volume = "16",
pages = "75--91",
journal = "Journal of Intelligent Systems",
issn = "0334-1860",
publisher = "Walter de Gruyter GmbH",
number = "1",

}

Accommodating power plant anomalies via an artificial neural network-based reconfigurable control. / Turso, James A.; Edwards, Robert; Turso, Brie E.

In: Journal of Intelligent Systems, Vol. 16, No. 1, 01.01.2007, p. 75-91.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Accommodating power plant anomalies via an artificial neural network-based reconfigurable control

AU - Turso, James A.

AU - Edwards, Robert

AU - Turso, Brie E.

PY - 2007/1/1

Y1 - 2007/1/1

N2 - A reconfigurable control strategy has been developed using a feed-forward Artificial Neural Network (ANN) implemented on a Bailey Network 90 digital control system requiring relatively minor modifications to the plant controller. An experimentally verified simulation of a secondary system's deaerating feedwater heater of a nuclear power plant was used to demonstrate the feasibility of the concept. The controller uses the ANN to decide when to switch from normal level control to alternate pressure control (via the level control valves) in the event of a rapid pressure decrease, possibly due to loss of feedwater heating, i.e., a phenomenon known as deaerator quenching. A prolonged rapid pressure decrease would result in feedpump cavitation (i.e., Net Positive Suction Head less than zero) due to the change in pressure reaching the pump suction before the corresponding change in saturation temperature. The ANN uses the deaerator level, pressure, and rate of change of pressure to develop a system status signal (i.e., reconfiguration switch signal) between 0.0 and 1.0. The existing level controller, with some minor modifications, is reconfigured to a pressure controller upon receiving a switch signal of 0.485. When tested with a simulated pressure regulator malfunction the reconfigurable control scheme displayed superior performance (compared with the original system) by arresting the pressure decrease and maintaining NPSH above zero for a prolonged period of time.

AB - A reconfigurable control strategy has been developed using a feed-forward Artificial Neural Network (ANN) implemented on a Bailey Network 90 digital control system requiring relatively minor modifications to the plant controller. An experimentally verified simulation of a secondary system's deaerating feedwater heater of a nuclear power plant was used to demonstrate the feasibility of the concept. The controller uses the ANN to decide when to switch from normal level control to alternate pressure control (via the level control valves) in the event of a rapid pressure decrease, possibly due to loss of feedwater heating, i.e., a phenomenon known as deaerator quenching. A prolonged rapid pressure decrease would result in feedpump cavitation (i.e., Net Positive Suction Head less than zero) due to the change in pressure reaching the pump suction before the corresponding change in saturation temperature. The ANN uses the deaerator level, pressure, and rate of change of pressure to develop a system status signal (i.e., reconfiguration switch signal) between 0.0 and 1.0. The existing level controller, with some minor modifications, is reconfigured to a pressure controller upon receiving a switch signal of 0.485. When tested with a simulated pressure regulator malfunction the reconfigurable control scheme displayed superior performance (compared with the original system) by arresting the pressure decrease and maintaining NPSH above zero for a prolonged period of time.

UR - http://www.scopus.com/inward/record.url?scp=34249903354&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=34249903354&partnerID=8YFLogxK

U2 - 10.1515/JISYS.2007.16.1.75

DO - 10.1515/JISYS.2007.16.1.75

M3 - Article

VL - 16

SP - 75

EP - 91

JO - Journal of Intelligent Systems

JF - Journal of Intelligent Systems

SN - 0334-1860

IS - 1

ER -