Assessment of Dynamic Bayesian Models for Gas Turbine Diagnostics, Part 1: Prior Probability Analysis

The reliability and cost-effectiveness of energy conversion in gas turbine systems are strongly dependent on an accurate diagnosis of possible process and sensor anomalies. Because data collected from a gas turbine system for diagnosis are inherently uncertain due to measurement noise and errors, pr...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Valentina Zaccaria, Amare Desalegn Fentaye, Konstantinos Kyprianidis
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	gas turbine diagnostics dynamic Bayesian network probabilistic diagnostics Mechanical engineering and machinery TJ1-1570
Acceso en línea:	https://doaj.org/article/db04f4b5508d4be4ad02e06d2c63308a
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:db04f4b5508d4be4ad02e06d2c63308a
record_format	dspace
spelling	oai:doaj.org-article:db04f4b5508d4be4ad02e06d2c63308a2021-11-25T18:12:23ZAssessment of Dynamic Bayesian Models for Gas Turbine Diagnostics, Part 1: Prior Probability Analysis10.3390/machines91102982075-1702https://doaj.org/article/db04f4b5508d4be4ad02e06d2c63308a2021-11-01T00:00:00Zhttps://www.mdpi.com/2075-1702/9/11/298https://doaj.org/toc/2075-1702The reliability and cost-effectiveness of energy conversion in gas turbine systems are strongly dependent on an accurate diagnosis of possible process and sensor anomalies. Because data collected from a gas turbine system for diagnosis are inherently uncertain due to measurement noise and errors, probabilistic methods offer a promising tool for this problem. In particular, dynamic Bayesian networks present numerous advantages. In this work, two Bayesian networks were developed for compressor fouling and turbine erosion diagnostics. Different prior probability distributions were compared to determine the benefits of a dynamic, first-order hierarchical Markov model over a static prior probability and one dependent only on time. The influence of data uncertainty and scatter was analyzed by testing the diagnostics models on simulated fleet data. It was shown that the condition-based hierarchical model resulted in the best accuracy, and the benefit was more significant for data with higher overlap between states (i.e., for compressor fouling). The improvement with the proposed dynamic Bayesian network was 8 percentage points (in classification accuracy) for compressor fouling and 5 points for turbine erosion compared with the static network.Valentina ZaccariaAmare Desalegn FentayeKonstantinos KyprianidisMDPI AGarticlegas turbine diagnosticsdynamic Bayesian networkprobabilistic diagnosticsMechanical engineering and machineryTJ1-1570ENMachines, Vol 9, Iss 298, p 298 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	gas turbine diagnostics dynamic Bayesian network probabilistic diagnostics Mechanical engineering and machinery TJ1-1570
spellingShingle	gas turbine diagnostics dynamic Bayesian network probabilistic diagnostics Mechanical engineering and machinery TJ1-1570 Valentina Zaccaria Amare Desalegn Fentaye Konstantinos Kyprianidis Assessment of Dynamic Bayesian Models for Gas Turbine Diagnostics, Part 1: Prior Probability Analysis
description	The reliability and cost-effectiveness of energy conversion in gas turbine systems are strongly dependent on an accurate diagnosis of possible process and sensor anomalies. Because data collected from a gas turbine system for diagnosis are inherently uncertain due to measurement noise and errors, probabilistic methods offer a promising tool for this problem. In particular, dynamic Bayesian networks present numerous advantages. In this work, two Bayesian networks were developed for compressor fouling and turbine erosion diagnostics. Different prior probability distributions were compared to determine the benefits of a dynamic, first-order hierarchical Markov model over a static prior probability and one dependent only on time. The influence of data uncertainty and scatter was analyzed by testing the diagnostics models on simulated fleet data. It was shown that the condition-based hierarchical model resulted in the best accuracy, and the benefit was more significant for data with higher overlap between states (i.e., for compressor fouling). The improvement with the proposed dynamic Bayesian network was 8 percentage points (in classification accuracy) for compressor fouling and 5 points for turbine erosion compared with the static network.
format	article
author	Valentina Zaccaria Amare Desalegn Fentaye Konstantinos Kyprianidis
author_facet	Valentina Zaccaria Amare Desalegn Fentaye Konstantinos Kyprianidis
author_sort	Valentina Zaccaria
title	Assessment of Dynamic Bayesian Models for Gas Turbine Diagnostics, Part 1: Prior Probability Analysis
title_short	Assessment of Dynamic Bayesian Models for Gas Turbine Diagnostics, Part 1: Prior Probability Analysis
title_full	Assessment of Dynamic Bayesian Models for Gas Turbine Diagnostics, Part 1: Prior Probability Analysis
title_fullStr	Assessment of Dynamic Bayesian Models for Gas Turbine Diagnostics, Part 1: Prior Probability Analysis
title_full_unstemmed	Assessment of Dynamic Bayesian Models for Gas Turbine Diagnostics, Part 1: Prior Probability Analysis
title_sort	assessment of dynamic bayesian models for gas turbine diagnostics, part 1: prior probability analysis
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/db04f4b5508d4be4ad02e06d2c63308a
work_keys_str_mv	AT valentinazaccaria assessmentofdynamicbayesianmodelsforgasturbinediagnosticspart1priorprobabilityanalysis AT amaredesalegnfentaye assessmentofdynamicbayesianmodelsforgasturbinediagnosticspart1priorprobabilityanalysis AT konstantinoskyprianidis assessmentofdynamicbayesianmodelsforgasturbinediagnosticspart1priorprobabilityanalysis
_version_	1718411529024438272

Assessment of Dynamic Bayesian Models for Gas Turbine Diagnostics, Part 1: Prior Probability Analysis

Ejemplares similares