Suscripción a Biblioteca: Guest
Second International Forum on Expert Systems and Computer Simulation in Energy Engineering
March, 17-20, 1992, Erlangen, Germany

DOI: 10.1615/ICHMT.1992.IntForumExpSysCompSimEE


ISBN Print: 978-1-56700-486-1

SENSOR SYSTEMS FOR AN ON-LINE DIAGNOSTIC EXPERT SYSTEM IN FOSSIL POWER PLANTS

pages 9.5.1-9.5.6
DOI: 10.1615/ICHMT.1992.IntForumExpSysCompSimEE.360
Get accessGet access

SINOPSIS

This paper outlines a framework for performing sensor validation in HEATXPRTTM, a data-driven on-line expert system for diagnosing heat rate degradation problems in fossil power plants (1) (2). Sensor validation plays a vital role in the ability of the overall system to correctly determine the state of a plant monitored by imperfect sensors. Two subsystems: Algorithmic (ASV) and Heuristic (HSV) Sensor Validation, separate activity according to the degree of plant knowledge required. ASV provides an estimate of continuous and discrete probability distributions for each of over a thousand sensor inputs. ASV also produces a confidence measure for each sensor based on previous behavior. HSV exploits deeper knowledge about parameter interaction within the plant to cull sensor faults from the data stream. HEATXPRTTM, provided with an updated sensory input stream containing only actual process deviations, then determines the most likely sources of heat rate performance degradation and calls for necessary operator action

Portal Digitalde Biblioteca Digital eLibros Revistas Referencias y Libros de Ponencias Colecciones Precios y Políticas de Suscripcione Begell House Contáctenos Language English 中文 Русский Português German French Spain