Open AccessDevelopment of a Pattern Recognition Methodology for Determining Operationally Optimal Heat Balance Instrumentation Calibration Schedules
Author(s) -
Kurt Beran,
J.M. Christenson,
Dragoş Nica,
Kenneth C. Gross
Publication year - 2002
Language(s) - English
Resource type - Reports
DOI - 10.2172/806854
Subject(s) - instrumentation (computer programming) , extension (predicate logic) , reliability (semiconductor) , calibration , computer science , sensitivity (control systems) , state (computer science) , balance (ability) , data mining , reliability engineering , artificial intelligence , engineering , statistics , mathematics , algorithm , programming language , electronic engineering , medicine , power (physics) , physics , quantum mechanics , physical medicine and rehabilitation
The goal of the project is to enable plant operators to detect with high sensitivity and reliability the onset of decalibration drifts in all of the instrumentation used as input to the reactor heat balance calculations. To achieve this objective, the collaborators developed and implemented at DBNPS an extension of the Multivariate State Estimation Technique (MSET) pattern recognition methodology pioneered by ANAL. The extension was implemented during the second phase of the project and fully achieved the project goal