The Use of Kalman Filter and Neural Network Methodologies in Gas Turbine Performance Diagnostics: A Comparative Study

2000 ◽  
Author(s):  
Allan J. Volponi ◽  
Hans DePold ◽  
Ranjan Ganguli ◽  
Chen Daguang
Keyword(s):  
Neural Network ◽  
Kalman Filter ◽  
Gas Turbine ◽  
Engine Operation ◽  
The Past ◽  
Fuel Flow ◽  
Turbine Performance ◽  
Engine System ◽  
Module Performance ◽  
Performance Diagnostics

The goal of Gas Turbine Performance Diagnostics is to accurately detect, isolate and assess the changes in engine module performance, engine system malfunctions and instrumentation problems from knowledge of measured parameters taken along the engine’s gas path. Discernable shifts in engine speeds, temperatures, pressures, fuel flow, etc., provide the requisite information for determining the underlying shift in engine operation from a presumed nominal state. Historically, this type of analysis was performed through the use of a Kalman Filter or one of its derivatives to simultaneously estimate a plurality of engine faults. In the past decade, Artificial Neural Networks (ANN) have been employed as a pattern recognition device to accomplish the same task. Both methods have enjoyed a reasonable success.

The Use of Kalman Filter and Neural Network Methodologies in Gas Turbine Performance Diagnostics: A Comparative Study

2003 ◽  
Vol 125 (4) ◽  
pp. 917-924 ◽  
Author(s):  
A. J. Volponi ◽  
H. DePold ◽  
R. Ganguli ◽  
C. Daguang
Keyword(s):  
Neural Network ◽  
Artificial Intelligence ◽  
Gas Turbine ◽  
Kalman Filters ◽  
Fault Isolation ◽  
Turbine Performance ◽  
Reasonable Degree ◽  
Engine System ◽  
Module Performance ◽  
Performance Diagnostics

The goal of gas turbine performance diagnositcs is to accurately detect, isolate, and assess the changes in engine module performance, engine system malfunctions and instrumentation problems from knowledge of measured parameters taken along the engine’s gas path. The method has been applied to a wide variety of commercial and military engines in the three decades since its inception as a diagnostic tool and has enjoyed a reasonable degree of success. During that time many methodologies and implementations of the basic concept have been investigated ranging from the statistically based methods to those employing elements from the field of artificial intelligence. The two most publicized methods involve the use of either Kalman filters or artificial neural networks (ANN) as the primary vehicle for the fault isolation process. The present paper makes a comparison of these two techniques.

Comparison of Linear and Non-Linear Gas Turbine Performance Diagnostics

2003 ◽  
Author(s):  
Ph. Kamboukos ◽  
K. Mathioudakis
Keyword(s):  
Gas Turbine ◽  
Condition Monitoring ◽  
Theoretical Background ◽  
Diagnostic Methods ◽  
Turbine Performance ◽  
Different Types ◽  
Non Linear ◽  
Computational Procedures ◽  
Monitoring And Diagnostics ◽  
Performance Diagnostics

The features of linear performance diagnostic methods are discussed, in comparison to methods based on full non-linear calculation of performance deviations, for the purpose of condition monitoring and diagnostics. First, the theoretical background of linear methods is overviewed to establish a relationship to the principles used by non-linear methods. Then computational procedures are discussed and compared. The effectiveness of determining component performance deviations by the two types of approaches is examined, on different types of diagnostic situations. A way of establishing criteria to define whether non-linear methods have to be employed is presented. An overall assessment of merits or weaknesses of the two types of methods is attempted, based on the results presented in the paper.

Neural Network for Balance of Plant SOFC-GT Actuator Control

2020 ◽  
Author(s):  
Alex Tsai ◽  
Tooran Emami ◽  
David Tucker
Keyword(s):  
Neural Network ◽  
Gas Turbine ◽  
Open Loop ◽  
Fuel Flow ◽  
Balance Of Plant ◽  
Anodic Side ◽  
Artificial Neural Network Ann ◽  
Turbine Speed ◽  
Actuator Control ◽  
Operational Issues

Abstract This work aims to study the feasibility of using an online feedforward artificial neural network (ANN) to control various actuators in a hybrid fuel cell gas turbine (FC-GT) simulation plant. This unique facility known as Hybrid Performance, or HYPER, is housed at the US Department of Energy’s National Energy Technology Laboratory in Morgantown, WV. Using a cyber-physical approach, HYPER incorporates a high-fidelity FC model in software, which interacts with a gas turbine and corresponding balance of plant components in hardware, in real time. This methodology allows research of FC-GT operational issues as well as control application studies for such systems in a safe manner. An open loop perturbation of the FC model load current is used to retrieve target data from load bank and bypass airflow valve actuators which control turbine speed and FC cathode airflow respectively. The steady state FC anodic side fuel flow is also fed to a supervised ANN which learns the pattern of actuator response to the given FC perturbations. By mimicking the manually operated actuators, the FC solid temperature gradient is maintained within safe operating bounds. The feedforward ANN is useful for its simplicity and flexibility in controlling a variety of desired actuator responses based on input combinations. The benefits and drawbacks of using ANN’s are discussed, as well as suggestions for improvement.

Optimum Gain-Scheduling PID Controllers for Gas Turbine Engines Based on NARMAX and Neural Network Models

2003 ◽  
Author(s):  
Junxia Mu ◽  
David Rees ◽  
Neophytos Chiras
Keyword(s):  
Neural Network ◽  
Gas Turbine ◽  
Pid Controller ◽  
Network Models ◽  
Gain Scheduling ◽  
Pid Controllers ◽  
Neural Network Models ◽  
Turbine Engine ◽  
Dynamic Relationship ◽  
Fuel Flow

This paper presents PID controller designs based on NARMAX and feedforward neural network models of a Spey gas turbine engine. Both models represent the dynamic relationship between the fuel flow and shaft speed. Due to the engine non-linearity, a single set of PID controller parameters is not sufficient to control the gas turbine throughout the operating range. Gain-scheduling PID controllers are therefore used in order to obtain optimum control. A comparison between the controller designs based on the two model representations is also made.

Some Aspects of Modelling Compressor Behavior in Gas Turbine Performance Calculations

2000 ◽  
Author(s):  
Claus Riegler ◽  
Michael Bauer ◽  
Joachim Kurzke
Keyword(s):  
Gas Turbine ◽  
Operating Conditions ◽  
Order Effects ◽  
Specific Work ◽  
Performance Modelling ◽  
Engine Operation ◽  
Turbine Performance ◽  
Major Interest ◽  
Compressor Map ◽  
Bypass Ratio

Performance calculation procedures for gas turbine engines are usually based on the performance characteristics of the engine components, and especially the turbo components are of major interest. In this paper methods of modelling compressors in gas turbine performance calculations are discussed. The basic methodologies based on Mach number similarity are summarized briefly including some second order effects. Under extreme enginepartload conditions, as for example subidle or windmilling, the operating points in the compressor map are located in a region which is usually not covered by rig tests. In addition the parameters usually used in compressor maps are no longer appropriate. For these operating conditions a method is presented to extrapolate compressor maps towards very low spool speed down to the locked rotor. Instead of the efficiency more appropriate parameters as for example specific work or specific torque are suggested. A compressor map prepared with the proposed methods is presented and discussed. As another relevant topic the performance modelling of fans for low bypass ratio turbofans is covered. Due to the flow splitter downstream of such a fan the core and bypass stream may be throttled independently during engine operation and bypass ratio becomes a third independent parameter in the map. Because testing a fan on the rig for various bypass ratios is a very costly task, a simplified method has been developed which accounts for the effects of bypass ratio.

scholarly journals Humidity Effects on Gas Turbine Performance

1991 ◽  
Author(s):  
J. Bird ◽  
W. Grabe
Keyword(s):  
Gas Turbine ◽  
Absolute Humidity ◽  
Performance Data ◽  
Specific Humidity ◽  
High Humidity ◽  
Engine Operation ◽  
Humidity Effects ◽  
Turbine Performance ◽  
Test Conditions ◽  
And Performance

Moisture in the intake air of a gas turbine can affect its operation and performance in two different ways: by possible condensation in the inlet and by changing the gas properties throughout the cycle. Condensation can be controlled by restricting engine operation with limits on relative and absolute humidities. Two fundamental correction approaches for the effects of humidity on major engine parameters were investigated; they were found to compare very well. Both methods correct parameters as a function of absolute humidity, yielding corrections of between 0.1 and 0.8%, for high humidity test conditions. Additional operational, engine-specific humidity corrections were examined: some notable differences were observed. Recommendations are made for the correction of major performance data for absolute humidity.

Comparison of Linear and Nonlinear Gas Turbine Performance Diagnostics

2005 ◽  
Vol 127 (1) ◽  
pp. 49-56 ◽  
Author(s):  
Ph. Kamboukos ◽  
K. Mathioudakis
Keyword(s):  
Gas Turbine ◽  
Theoretical Background ◽  
Diagnostic Methods ◽  
Nonlinear Methods ◽  
Turbine Performance ◽  
Different Types ◽  
Linear And Nonlinear ◽  
Computational Procedures ◽  
Monitoring And Diagnostics ◽  
Performance Diagnostics

The features of linear performance diagnostic methods are discussed, in comparison to methods based on full nonlinear calculation of performance deviations, for the purpose of condition monitoring and diagnostics. First, the theoretical background of linear methods is reviewed to establish a relationship to the principles used by nonlinear methods. Then computational procedures are discussed and compared. The effectiveness of determining component performance deviations by the two types of approaches is examined, on different types of diagnostic situations. A way of establishing criteria to define whether nonlinear methods have to be employed is presented. An overall assessment of merits or weaknesses of the two types of methods is attempted, based on the results presented in the paper.

Some Aspects of Modeling Compressor Behavior in Gas Turbine Performance Calculations

2000 ◽  
Vol 123 (2) ◽  
pp. 372-378 ◽  
Author(s):  
Claus Riegler ◽  
Michael Bauer ◽  
Joachim Kurzke
Keyword(s):  
Gas Turbine ◽  
Operating Conditions ◽  
Order Effects ◽  
Specific Work ◽  
Performance Modelling ◽  
Engine Operation ◽  
Turbine Performance ◽  
Major Interest ◽  
Compressor Map ◽  
Bypass Ratio

Performance calculation procedures for gas turbine engines are usually based on the performance characteristics of the engine components, and especially the turbo components are of major interest. In this paper methods of modelling compressors in gas turbine performance calculations are discussed. The basic methodologies based on Mach number similarity are summarized briefly including some second order effects. Under extreme engine partload conditions, as for example subidle or windmilling, the operating points in the compressor map are located in a region which is usually not covered by rig tests. In addition the parameters usually used in compressor maps are no longer appropriate. For these operating conditions a method is presented to extrapolate compressor maps towards very low spool speed down to the locked rotor. Instead of the efficiency more appropriate parameters as for example specific work or specific torque are suggested. A compressor map prepared with the proposed methods is presented and discussed. As another relevant topic the performance modelling of fans for low bypass ratio turbofans is covered. Due to the flow splitter downstream of such a fan the core and bypass stream may be throttled independently during engine operation and bypass ratio becomes a third independent parameter in the map. Because testing a fan on the rig for various bypass ratios is a very costly task, a simplified method has been developed which accounts for the effects of bypass ratio.

Uncertainty Reduction in Gas Turbine Performance Diagnostics by Accounting for Humidity Effects

2001 ◽  
Author(s):  
K. Mathioudakis ◽  
A. Tsalavoutas
Keyword(s):  
Gas Turbine ◽  
Gas Turbines ◽  
Ambient Conditions ◽  
Ambient Temperatures ◽  
Turbine Performance ◽  
Industrial Gas Turbines ◽  
Industrial Gas Turbine ◽  
The Impact ◽  
Performance Diagnostics ◽  
Health Parameters

The paper presents an analysis of the effect of ambient humidity on the performance of industrial gas turbines and examines the impact of humidity on methods used for engine condition assessment and fault diagnostics. First, the way of incorporating the effect of humidity into a computer model of gas turbine performance is described. The model is then used to derive parameters indicative of the “health” of a gas turbine and thus diagnose the presence of deterioration or faults. The impact of humidity magnitude on the values of these health parameters is studied and the uncertainty introduced, if humidity is not taken into account, is assessed. It is shown that the magnitude of the effect of humidity depends on ambient conditions and is more severe for higher ambient temperatures. Data from an industrial gas turbine are presented to demonstrate these effects and to show that if humidity is appropriately taken into account, the uncertainty in the estimation of health parameters is reduced

Performance Evaluation of a Variable Geometry Gas Turbine in a CHP Plant

2015 ◽  
Vol 798 ◽  
pp. 59-63
Author(s):  
Aklilu Tesfamichael Baheta ◽  
S.I. Gilani ◽  
Shaharin Anwar Sulaiman
Keyword(s):  
Gas Turbine ◽  
Pressure Ratio ◽  
Design Calculation ◽  
Variable Geometry ◽  
Gas Temperature ◽  
Turbine Plant ◽  
Fuel Flow ◽  
Turbine Performance ◽  
Exhaust Gas Temperature ◽  
Good Agreement

This study is to develop mathematical models and evaluate the performance of a gas turbine with variable geometry compressor working in a CHP plant. A single shaft gas turbine plant can maintain the exhaust gas temperature if the load is not below 50 % of the full load by simultaneously regulating the compressor variable vanes position and fuel flow. For load less than 50% the engine is running to meet the power demand. This is achieved by controlling the fuel flow and air bleed at the downstream of the compressor to avoid surge formation while variable vanes are opened fully. To accommodate change of compressor parameters during variable vanes re-stagger correction coefficients are introduced. A behavior of a 4.2 MW gas turbine performance was evaluated. The effect of variation of load and ambient temperature on the gas turbine specific fuel consumption, temperature, pressure ratio, variable vanes opening and efficiency were examined. Comparison between the field data and simulation results demonstrate good agreement. The off-design calculation was done by in-house developed program in MATLAB environment.

Sign in / Sign up

Export Citation Format

Share Document