Publication type: Conference other
Type of review: Not specified
Title: Predictive-prescriptive analytics for combustion monitoring in gas turbine power plants
Authors: Danafar, Somayeh
Kryszczuk, Krzysztof
Gassner, Martin
Bernero, Stefano
Conference details: Predictive Maintenance, Swiss Association for Analytics (SAA), Lausanne, 27 September 2017
Issue Date: 27-Sep-2017
Language: English
Subjects: Predictive Maintenance; Analytics; Emission prediction
Subject (DDC): 003: Systems
Abstract: Why do many Predictive Maintenance systems fail? The proposition of Predictive Maintenance paradigm is that a failure of a give system can be expected and predicted. However, complex systems in industrial applications are rarely stable, and the expected time to failure can vary rapidly as the operating conditions and regime change. Therefore, a clear strategy must be devised regarding how and when to act upon received prediction. We refer to this strategy as Prescriptive Maintenance, and describe it as an optimization problem. In this talk we discuss an example of moving from Predictive to Prescriptive Maintenance scheme using as an example a system we developed in collaboration with GE Power (Switzerland).
Fulltext version: Published version
License (according to publishing contract): Licence according to publishing contract
Departement: Life Sciences and Facility Management
Organisational Unit: Institute of Computational Life Sciences (ICLS)
Published as part of the ZHAW project: Predictive - Prescriptive Analytics for Emission & Combustion Monitoring Agents in Gas Turbine Combined Cycle Power Plants
Appears in collections:Publikationen Life Sciences und Facility Management

Files in This Item:
There are no files associated with this item.

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.