Expert Diagnostic System for Gas Turbines

Author(s):  
G. Sisti ◽  
G. Ferrari Aggradi
Machines ◽  
2022 ◽  
Vol 10 (1) ◽  
pp. 36
Author(s):  
Mikael Stenfelt ◽  
Konstantinos Kyprianidis

In gas turbines used for airplane propulsion, the number of sensors are kept at a minimum for accurate control and safe operation. Additionally, when data are communicated between the airplane main computer and the various subsystems, different systems may have different constraints and requirements regarding what data transmit. Early in the design process, these parameters are relatively easy to change, compared to a mature product. If the gas turbine diagnostic system is not considered early in the design process, it may lead to diagnostic functions having to operate with reduced amount of data. In this paper, a scenario where the diagnostic function cannot obtain airplane installation effects is considered. The installation effects in question is air intake pressure loss (pressure recovery), bleed flow and shaft power extraction. A framework is presented where the unknown installation effects are estimated based on available data through surrogate models, which is incorporated into the diagnostic framework. The method has been evaluated for a low-bypass turbofan with two different sensor suites. It has also been evaluated for two different diagnostic schemes, both determined and underdetermined. Results show that, compared to assuming a best-guess constant-bleed and shaft power, the proposed method reduce the RMS in health parameter estimation from 26% up to 80% for the selected health parameters. At the same time, the proposed method show the same degradation pattern as if the installation effects were known.


Author(s):  
R. Bettocchi ◽  
M. Pinelli ◽  
P. R. Spina ◽  
M. Venturini ◽  
S. Sebastianelli

This paper illustrates the policy and objectives in compression system maintenance and describes a system for the health state determination of natural gas compression gas turbines based on “Gas Path Analysis”. Some results of the application of the diagnostic system to gas turbines working in a natural gas compression plant are presented.


Author(s):  
Carl A. Palmer ◽  
Royce L. Abel ◽  
Peter Sandvik

This paper describes the development and initial application studies for an active combustion pattern factor controller (APFC) for gas turbines. The system is based around use of a novel silicon carbide (SiC) optical ultraviolet (UV) dual diode flame temperature sensor (FTS) developed by General Electric’s Global Research Center and GE Energy. The APFC system determines combustion flame temperatures, validates the values, and integrates an assessment of signal and combustion hardware health to determine how to trim the fuel flow to individual fuel nozzles. Key aspects of the system include: • Determination of each flame’s bulk temperature using the FTS. • Assessment of the reliability of the flame temperature data and physical combustion hardware health through analysis of the high frequency output of the sensor. • Validation of the flame temperature signal using a data-driven approach (model based validation - MBV). • Fusion of sensor ‘health indices’ into the APFC to alter the trim control signal based on the health (or ‘believability’) of each sensor and fuel nozzle/combustor. • Fault-tolerant peak/valley detection and control module that selects individual fuel valves to target for reducing pattern factor, while simultaneously balancing the overall fuel flow. The authors demonstrated feasibility of the approach by performing simulations using a quasi-2D T700 turbine engine model. Tests were run on the simulated platform with no faults, simulated sensor faults, and on a system with underlying combustion hardware issues. The final APFC system would be applicable for aviation, naval and land-based commercial gas turbines, and can be used in closed-loop control or adapted as an open-loop advisory / diagnostic system.


Author(s):  
Frank Fanuele ◽  
Richard A. Rio

The rapidly increasing costs of maintenance, the demand for increased equipment utilization, fuel costs and the difficulty of correctly diagnosing internal mechanical problems in operating gas turbine engines has stressed the requirement for more effective monitoring and diagnostic equipment. Such equipment must be capable of performing three functions: 1. Acquiring condition data from operating gas turbines, 2. Analyzing the acquired data, and 3. Associating the cause and effect relationship to an incipient malfunction. This paper describes the MTI Automated Vibration Diagnostic System (AVID) developed for the U. S. Air Force jet engine overhaul centers. The AVID concept is to automate troubleshooting procedures for fully assembled gas turbine engines. The System extracts high-frequency vibration data from existing, standard instrumentation to provide input to a specialized Symptom/Fault Matrix. This Symptom/Fault Matrix is configured to analyze the incoming data and assign a particular malfunction (or malfunctions) to a specified data set. This diagnosis is then printed out to provide maintenance personnel with exact knowledge of what the problem is and how to correct it. This System, plus the growing awareness on the part of personnel of the capabilities of such automated equipment, will enable the Air Force to significantly reduce expenses at their jet engine overhaul facilities.


Author(s):  
M. P. Boyce ◽  
J. C. Bowman ◽  
C. B. Meher-Homji ◽  
A. B. Focke

This paper presents techniques in which greater productivity and fuel savings can be achieved by the use of online monitoring and diagnostic systems and compressor management systems applied to turbo-compressors. With maintenance life cycle costs for gas turbines being about one-fifth of fuel life cycle costs, the incentives for maintaining good operating efficiency is high. An online monitoring and diagnostic system can go a long way in pin-pointing areas in which performance decrements occur. There is also large monetary savings by operating load compressors with minimum recirculation. Secondary benefits of such systems include automated vibration analysis and automated diagnostic of common faults. This paper also covers some case histories that illustrate benefits and generic system diagrams that illustrate such systems.


Author(s):  
E. Loukis ◽  
K. Mathioudakis ◽  
K. Papailiou

A methodology for the design of automated diagnostic systems for Gas Turbines is presented. The first stage of the proposed methodology consists in an initial selection of instruments and measuring positions on the engine, based on a basic knowledge of the engine itself and previous experience, as well as modelling capabilities of the phenomena happening in it. It is followed by a stage of “learning” experiments. One purpose of these experiments is to provide measurement data, on which a final selection of instruments will be based. The instruments most suitable for the fault cases of interest are selected, according to the diagnostic potential they offer. Another purpose is to develop procedures of automated fault diagnosis. The necessary background information for the later exploitation of the system is also established. The applicability of the entire methodology is demonstrated for the case of designing a blade fault diagnostic system for an Industrial Gas Turbine.


Author(s):  
Carl A. Palmer ◽  
Royce L. Abel ◽  
Peter Sandvik

This paper describes the development and initial application studies for an active combustion pattern factor controller (APFC) for gas turbines. The system is based around the use of a novel silicon carbide optical ultraviolet dual diode flame temperature sensor (FTS) developed by General Electric Co. The APFC system determines combustion flame temperatures, validates the values, and integrates an assessment of signal and combustion hardware health to determine how to trim the fuel flow to individual fuel nozzles. Key aspects of the system include the following: determination of each flame’s bulk temperature using the FTS, assessment of the reliability of the flame temperature data and physical combustion hardware health through analysis of the high-frequency output of the sensor, validation of the flame temperature signal using a data-driven approach, fusion of sensor “health indices” into the APFC to alter the trim control signal based on the health (or “believability”) of each sensor and fuel nozzle/combustor, fault-tolerant peak/valley detection and control module that selects individual fuel valves to target for reducing pattern factor while simultaneously balancing the overall fuel flow. The authors demonstrated feasibility of the approach by performing simulations using a quasi-2D T700 turbine engine model. Tests were run on the simulated platform with no faults, simulated sensor faults, and on a system with underlying combustion hardware issues. The final APFC system would be applicable for aviation, naval, and land-based commercial gas turbines, and can be used in closed-loop control or adapted as an open-loop advisory/diagnostic system.


1995 ◽  
Author(s):  
Robert L. Spitzer ◽  
Kurt Kroenke ◽  
Mark Linzer ◽  
Steven R. Hahn ◽  
Janet B. W. Williams ◽  
...  
Keyword(s):  

Sign in / Sign up

Export Citation Format

Share Document