The importance of input variables to a neural network fault-diagnostic system for nuclear power plants

Date
1992
Authors
Lanc, Terry
Journal Title
Journal ISSN
Volume Title
Publisher
Altmetrics
Authors
Research Projects
Organizational Units
Mechanical Engineering
Organizational Unit
Journal Issue
Series
Abstract

This thesis explores safety enhancement for nuclear power plants. Emergency response systems currently in use depend mainly on automatic systems engaging when certain parameters go beyond a pre-specified safety limit. Often times the operator has little or no opportunity to react since a fast scram signal shuts down the reactor smoothly and efficiently. These accidents are of interest to technical support personnel since examining the conditions that gave rise to these situations help determine causality. In many other cases an automated fault-diagnostic advisor would be a valuable tool in assisting the technicians and operators to determine what just happened and why.

Description
Keywords
Citation
Source