Gas Turbine Diagnostics Under Variable Operating Conditions

2007 ◽  
Author(s):  
Igor Loboda ◽  
Yakov Feldshteyn ◽  
Sergiy Yepifanov
Keyword(s):  
Gas Turbine ◽  
Health Monitoring ◽  
Correct Diagnosis ◽  
Diagnostic System ◽  
Diagnostic Technique ◽  
Operating Conditions ◽  
Diagnostic Process ◽  
Ambient Conditions ◽  
Operating Points ◽  
Variable Operating Conditions

Operating conditions (control variables and ambient conditions) of gas turbine plants and engines vary considerably. The fact that health monitoring has to be uninterrupted creates the need for a run time diagnostic system to operate under any conditions. The diagnostic technique described in this paper utilizes the thermodynamic models in order to simulate gaspath faults and uses neural networks for the faults localization. This technique is repeatedly executed and the diagnoses are registered. On the basis of these diagnoses and beforehand known faults, the correct diagnosis probabilities are then calculated. The present paper analyses the influence of the operating conditions on a diagnostic process. In the technique, different options are simulated of a diagnostic treatment of the measured values obtained under variable operating conditions. The mentioned above probabilities help to compare these options. The main focus of the paper is on the so called multipoint (multimode) diagnosis that groups the data from different operating points (modes) to set only a single diagnosis.

A Generalized Fault Classification for Gas Turbine Diagnostics on Steady States and Transients

2006 ◽  
Author(s):  
Igor Loboda ◽  
Sergey Yepifanov ◽  
Yakov Feldshteyn
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Steady State ◽  
Gas Turbine ◽  
Correct Diagnosis ◽  
Diagnostic Techniques ◽  
Operating Conditions ◽  
Fault Classification ◽  
Diagnostic Process ◽  
Transient Operation

Gas turbine diagnostic techniques are often based on the recognition methods using the deviations between actual and expected thermodynamic performances. The problem is that the deviations depend on real operating conditions. However, our studies show that such a dependency can be reduced. In this paper, we propose the generalized fault classification that is independent of the operating conditions. To prove this idea, the averaged probabilities of the correct diagnosis are computed and compared for two cases: the proposed classification and the traditional one based on the fixed operating conditions. The probabilities are calculated through a stochastic modeling of the diagnostic process, in which a thermodynamic model generates deviations that are induced by the faults. Artificial neural networks recognize these faults. The proposed classification principle has been realized for both, steady state and transient operation of the gas turbine units. The results show that the acceptance of the generalized classification practically does not reduce the diagnosis trustworthiness.

Research on Prediction of NOx Emission Performance of Marine Gas Turbine Under Variable Operating Conditions

2020 ◽  
Author(s):  
Jian Li ◽  
Zhitao Wang ◽  
Tielei Li ◽  
Shuying Li
Keyword(s):  
Gas Turbine ◽  
Chemical Reactor ◽  
Operating Conditions ◽  
Nox Emissions ◽  
Chemical Reactor Network ◽  
Computational Fluid Dynamics Cfd ◽  
Reactor Network ◽  
D Model ◽  
Operating Points ◽  
Variable Operating Conditions

Abstract With the global warming, many countries pay more attention to environmental pollution. The NOx emissions has become an important index when gas turbine designed. This paper provides a method for predicting NOx emissions of marine gas turbine under variable operating conditions. Firstly build the 3-D model of combustor. The characteristic regions of combustor were divided according to the reaction principle. Then build the chemical reactor network (CRN) models of different characteristic regions. According to the NOx emissions of several specific operating points simulated by computational fluid dynamics (CFD), fit the relation between residence time and operating conditions by Newton interpolation in the CRN models. Then the prediction model of NOx emissions of gas turbine was established by using neural network. The NOx emissions under 0.7∼1.0 working conditions and 0.019∼0.023 fuel-air ratios can be predicted efficiently.

Heavy Duty Gas Turbine Simulation: Global Performances Estimation and Secondary Air System Modifications

2006 ◽  
Author(s):  
Carlo Carcasci ◽  
Bruno Facchini ◽  
Stefano Gori ◽  
Luca Bozzi ◽  
Stefano Traverso
Keyword(s):  
Gas Turbine ◽  
Gas Turbines ◽  
Cooling System ◽  
Energy System ◽  
Operating Conditions ◽  
Coupled Analysis ◽  
Ambient Conditions ◽  
Air System ◽  
Secondary Air ◽  
And Performance

This paper reviews a modular-structured program ESMS (Energy System Modular Simulation) for the simulation of air-cooled gas turbines cycles, including the calculation of the secondary air system. The program has been tested for the Ansaldo Energia gas turbine V94.3A, which is one of the more advanced models in the family Vx4.3A with a rated power of 270 MW. V94.3A cooling system has been modeled with SASAC (Secondary Air System Ansaldo Code), the Ansaldo code used to predict the structure of the flow through the internal air system. The objective of the work was to investigate the tuning of the analytical program on the basis of the data from design and performance codes in use at Ansaldo Energy Gas Turbine Department. The results, both at base load over different ambient conditions and in critical off-design operating points (full-speed-no-load and minimum-load), have been compared with APC (Ansaldo Performance Code) and confirmed by field data. The coupled analysis of cycle and cooling network shows interesting evaluations for components life estimation and reliability during off-design operating conditions.

Incremental Fuel Cost Prediction for a Gas Turbine Combined Cycle Utility

1989 ◽  
Author(s):  
D. Little ◽  
H. Nikkels ◽  
P. Smithson
Keyword(s):  
Gas Turbine ◽  
Fuel Consumption ◽  
Gas Turbines ◽  
Operating Experience ◽  
Load Level ◽  
Combined Cycle ◽  
Operating Conditions ◽  
Fuel Cost ◽  
Ambient Conditions ◽  
Cost Prediction

For a medium sized (300 MW) utility producing electricity from a 130 MW combined cycle, and supplemental 15 MW to 77 MW capacity simple cycle gas turbines, the incremental fuel costs accompanying changes in generating capacity vary considerably with unit, health, load level, and ambient. To enable incremental power to be sold to neighbouring utilities on an incremental fuel cost basis, accurate models of all gas turbines and the combined cycle were developed which would allow a realistic calculation of fuel consumption under all operating conditions. The fuel cost prediction program is in two parts; in the first part, gas turbine health is diagnosed from measured parameters; in the second part, fuel consumption is calculated from compressor and turbine health, ambient conditions and power levels. The paper describes the program philosophy, development, and initial operating experience.

Multipoint Non-Linear Method for Enhanced Component and Sensor Malfunction Diagnosis

2006 ◽  
Author(s):  
Philippos Kamboukos ◽  
Kostas Mathioudakis
Keyword(s):  
Gas Turbine ◽  
Linear Method ◽  
Computational Cost ◽  
Diagnostic System ◽  
Turbine Engines ◽  
Gas Turbine Engines ◽  
Engine Component ◽  
Malfunction Diagnosis ◽  
Operating Points ◽  
Health Parameters

Operating gas turbine engines are usually equipped with a limited number of sensors. This situation is the common issue of gas turbine diagnostics where the absence of sufficient measurements from the engine gas path reduces the effectiveness of the applied methods. In addition the installed sensors of the engine deteriorate with time or present abrupt malfunctions which are not always detectable. One way to overcome this problem is the exploitation of information from a number of different operating points by constructing a multipoint diagnostic procedure. Information from different operating points is combined in order to increase the number of measurements and thus to form a well determined diagnostic system for the estimation of engine component health parameters. The paper presents the extension of the method in order to be able to assess both engine and sensors state. Initially the ability of the method to estimate the condition of a high bypass turbofan engine, exploiting information from different instances of its flight envelop is depicted. The problem of selecting the appropriate operating points is analyzed on the basis of the numerical condition of the formed diagnostic system. The method is also applied to a single shaft turbojet, for estimation of engine component health parameters and sensors state. Finally a number of aspects related to the formulation of the method are examined. These are the comparison between full method and its linear approximation, the effect of measurement noise on the derived estimation and the computational cost.

An Evaluation of the Effect of Ambient Conditions on the Integration of Inlet Conditioning Systems With Industrial Gas Turbine Engines

2003 ◽  
Author(s):  
Janel N. Nixon ◽  
Mark Waters ◽  
Dimitri Mavris
Keyword(s):  
Power Plant ◽  
Power Systems ◽  
Gas Turbine ◽  
Robust Design ◽  
Operating Conditions ◽  
Turbine Engines ◽  
Gas Turbine Engines ◽  
Ambient Conditions ◽  
Temperature And Humidity ◽  
Industrial Gas Turbine

All industrial power systems are influenced by ambient parameters, and power plant output fluctuates significantly with changes in ambient conditions such as pressure, temperature, and humidity. The use of an inlet conditioning system is frequently proposed to lower the temperatures at the inlet of an industrial gas turbine engine, particularly in hot and arid regions. To evaluate such a system, a robust design methodology has been developed whereby ambient operating conditions and their impacts can be modeled easily and accurately. Ambient models are developed that are specific to a given locale and consider daily and annual variations in temperature and humidity. A robust design is one that has a high probability of meeting design goals, and at the same time, is insensitive to operational uncertainty. This paper addresses the possibility of enhancing the robustness of gas turbine engines by means of technology additions. The results of this study have been developed in part using the probabilistic analysis techniques developed at the Aerospace System Design Laboratory at Georgia Tech, and they demonstrate how differing ambient conditions can affect the decision to install an inlet conditioning system with the engine [1]. An industrial gas turbine power plant is modeled, and the ambient models are integrated with the engine model and used to predict the overall impact on power plant net revenue over a year-long period of operation. This is done at four specified locales each with widely different ambient characteristics.

scholarly journals Quantification of Gear Tooth Damage by Optimal Tracking of Vibration Signatures

1997 ◽  
Vol 3 (3) ◽  
pp. 143-151 ◽  
Author(s):  
F. K. Choy ◽  
R. J. Veillette ◽  
V. Polyshchuk ◽  
M. J. Braun ◽  
R. C. Hendricks
Keyword(s):  
Monitoring System ◽  
Health Monitoring ◽  
Gear Tooth ◽  
Operating Conditions ◽  
Diagnostic Process ◽  
Data Set ◽  
Health Monitoring System ◽  
Gear Teeth ◽  
Gear Mesh ◽  
Machine Health Monitoring

This paper presents a technique for quantifying the wear or damage of gear teeth in a transmission system. The procedure developed in this study can be applied as a part of either an onboard machine health-monitoring system or a health diagnostic system used during regular maintenance. As the developed methodology is based on analysis of gearbox vibration under normal operating conditions, no shutdown or special modification of operating parameters is required during the diagnostic process.The process of quantifying the wear or damage of gear teeth requires a set of measured vibration data and a model of the gear mesh dynamics. An optimization problem is formulated to determine the profile of a time-varying mesh stiffness parameter for which the model output approximates the measured data. The resulting stiffness profile is then related to the level of gear tooth wear or damage.The procedure was applied to a data set generated artificially and to another obtained experimentally from a spiral bevel gear test rig. The results demonstrate the utility of the procedure as part of an overall health-monitoring system.

Sign in / Sign up

Export Citation Format

Share Document