Fault Diagnosis and Prognosis for Fuel Supply System in Gas Turbine Engines

Kim, Kyu-Sung; Uluyol, Önder; Ball, Charles

doi:10.1115/detc2005-84615

Cited by 4 publications

(4 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, node 6, the chance node representing 'Control System Failure', has three parent nodes each with two states. This produces a parental distribution of the order of 2 3 . While this does not seem a large CPT, the nature of the node's scope limits the level of available data, and hence cannot be completed fully with hard data.…”

Section: Symmetric Methods Utilising Hard Datamentioning

confidence: 99%

“…These initial failures are defined in two categories: control system failures and physical or structural failures. 1–4 This should provide a base with which to expand the BN model to facilitate the requirement of having a dynamic risk assessment model that allows for accurate representation of the hazards and consequences associated with gas turbine fuel gas releases.…”

Section: Introductionmentioning

confidence: 99%

“…These final consequences were not expanded or demonstrated in great detail to keep the complexity of the model as low as possible while achieving valid results. 3,4,6,7 The model to be presented here is an expansion of the previous model, focused on the consequence, fuel gas release and fire. In Loughney and Wang, 5 fuel gas release and its consequences were represented as one node in the network.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Utilising Bayesian networks to demonstrate the potential consequences of a fuel gas release from an offshore gas-driven turbine

Loughney

Wang

Matellini

2018

Proceedings of the IMechE

View full text Add to dashboard Cite

This research proposes the application of Bayesian networks in conducting quantitative risk assessment of the integrity of an offshore gas driven turbine, used for electrical power generation. The focus of the research is centred on the potential release of fuel gas from a turbine and the potential consequences that follow the said release, such as fire, explosion and damage to equipment within the electrical generation module. The Bayesian network demonstrates the interactions of potential initial events and failures, hazards, barriers and consequences involved in a fuel gas release. This model allows for quantitative analysis to demonstrate partial verification of the model. The verification of the model is demonstrated in a series of test cases and through sensitivity analysis. Test case 1 demonstrates the effects of individual and combined control system failures within the fuel gas release model; 2 demonstrates the effects of the 100% probability of a gas release on the Bayesian network model, along with the effect of the gas detection system not functioning; and 3 demonstrates the effects of inserting evidence as a consequence and observing the effects on prior nodes.

show abstract

Section: Symmetric Methods Utilising Hard Datamentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Utilising Bayesian networks to demonstrate the potential consequences of a fuel gas release from an offshore gas-driven turbine

Loughney

Wang

Matellini

2018

Proceedings of the IMechE

View full text Add to dashboard Cite

show abstract

“…In many problems, reducing the number of input variables can sometimes lead to improved performance for a given data set, even though some information is being discarded. The fixed quantity of data is better able to specify the mapping in the lower dimension space and this more than compensates for the loss of information (Bishop 1995). In the practical perspective, there are several more advantages to condensing the data: 1) It minimizes the cost and space for data collection and storage; 2) Computationally faster data processing makes for timely prognostic decisions; and 3) Not all of the engine data collection system can record continuous high speed data.…”

Section: Fault Diagnosis Systemmentioning

confidence: 99%

Fault Diagnosis of Gas Turbine Engine LRUs Using the Startup Characteristics

Kim¹,

Uluyol²,

Parthasarathy³

et al. 2012

PHM_CONF

View full text Add to dashboard Cite

This paper introduces a feature-extraction method to characterize gas turbine engine dynamics. The extracted features are used to develop a fault diagnosis and prognosis method for startup related sub-systems in gas turbine engines - the starter system, the ignition system and the fuel delivery system. The startup of a gas turbine engine from ignition to idle speed is very critical not only for achieving a fast and efficient startup without incurring stall, but also for health monitoring of many subsystems involved. During startup, an engine goes through a number of phases during which various components become dominant. The proposed approach physically monitors the relevant phases of a startup by detecting distinct changes in engine behavior as it manifests in such critical variables as the core speed and the gas temperature. The startup process includes several known milestones, such as starter-on, light-off, peak gas temperature, and idle. As each of these is achieved, different engine components come into play and the dynamic response of the engine changes. Monitoring engine speed and exhaust gas temperature and their derivatives provides valuable insights into engine behavior. The approach of the fault diagnosis system is as follows. The engine startup profiles of the core speed (N2) and the gas temperature are obtained and processed into a compact data set by identifying critical-to-characterization instances. The principal component analysis is applied to a number of parameters, and the fault is detected and mapped into three engine component failures which are the starter system failure, the ignition system failure, and the fuel delivery system failure.

show abstract