Testing of a real-time health monitoring and diagnostic system for gas turbine engines

1998 ◽  
Author(s):  
Michael Roemer
Keyword(s):  
Real Time ◽  
Gas Turbine ◽  
Health Monitoring ◽  
Diagnostic System ◽  
Turbine Engines ◽  
Gas Turbine Engines

scholarly journals Real Time Neutron Radiography Applications in Gas Turbine and Internal Combustion Engine Technology

1988 ◽  
Author(s):  
John T. Lindsay ◽  
C. W. Kauffman
Keyword(s):  
Real Time ◽  
Gas Turbine ◽  
Internal Combustion Engines ◽  
Combustion Engine ◽  
Neutron Radiography ◽  
Three Dimensional ◽  
Basic Research ◽  
Internal Combustion ◽  
Turbine Engines ◽  
Gas Turbine Engines

Real Time Neutron Radiography (RTNR) is rapidly becoming a valuable tool for nondestructive testing and basic research with a wide variety of applications in the field of engine technology. The Phoenix Memorial Laboratory (PML) at the University of Michigan has developed a RTNR facility and has been using this facility to study several phenomena that have direct application to internal combustion and gas turbine engines. These phenomena include; 1) the study of coking and debris deposition in several gas turbine nozzles (including the JT8D), 2) the study of lubrication problems in operating standard internal combustion engines and in operating automatic transmissions (1, 2, 3), 3) the location of lubrication blockage and subsequent imaging of the improvement obtained from design changes, 4) the imaging of sprays inside metallic structures in both a two-dimensional, standard radiographic manner (4, 5) and in a computer reconstructed, three-dimensional, tomographic manner (2, 3), and 5) the imaging of the fuel spray from an injector in a single cylinder diesel engine while the engine is operating. This paper will show via slides and real time video, the above applications of RTNR as well as other applications not directly related to gas turbine engines.

Health Monitoring and Degradation Prognostics in Gas Turbine Engines Using Dynamic Neural Networks

2015 ◽  
Author(s):  
A. Vatani ◽  
K. Khorasani ◽  
N. Meskin
Keyword(s):  
Neural Network ◽  
Gas Turbine ◽  
Health Monitoring ◽  
Network Architecture ◽  
Information Criterion ◽  
Turbine Engines ◽  
Prediction Errors ◽  
Gas Turbine Engines ◽  
Dynamic Neural Networks ◽  
Turbine Engine

In this paper two artificially intelligent methodologies are proposed and developed for degradation prognosis and health monitoring of gas turbine engines. Our objective is to predict the degradation trends by studying their effects on the engine measurable parameters, such as the temperature, at critical points of the gas turbine engine. The first prognostic scheme is based on a recurrent neural network (RNN) architecture. This architecture enables ONE to learn the engine degradations from the available measurable data. The second prognostic scheme is based on a nonlinear auto-regressive with exogenous input (NARX) neural network architecture. It is shown that this network can be trained with fewer data points and the prediction errors are lower as compared to the RNN architecture. To manage prognostic and prediction uncertainties upper and lower threshold bounds are defined and obtained. Various scenarios and case studies are presented to illustrate and demonstrate the effectiveness of our proposed neural network-based prognostic approaches. To evaluate and compare the prediction results between our two proposed neural network schemes, a metric known as the normalized Akaike information criterion (NAIC) is utilized. A smaller NAIC shows a better, a more accurate and a more effective prediction outcome. The NAIC values are obtained for each case and the networks are compared relatively with one another.

Developing and Deploying ICAS-Capable CBM Software Modules: Best Practices and Lessons Learned

2005 ◽  
Author(s):  
Matthew J. Watson ◽  
Carl S. Byington ◽  
Bryan Donovan ◽  
Greg Kacprzynski ◽  
Assaad Krichene ◽  
...  
Keyword(s):  
Best Practices ◽  
Gas Turbine ◽  
Diagnostic System ◽  
Lessons Learned ◽  
Assessment System ◽  
Third Party ◽  
Turbine Engines ◽  
Gas Turbine Engines ◽  
Electrical Systems ◽  
Software Modules

The U.S. Navy’s Integrated Condition Assessment System (ICAS) is a shipboard monitoring system that helps enable the Navy’s Condition Based Maintenance (CBM) initiative. ICAS is installed on a large number of Navy Surface Combatants and provides data acquisition, display, and logging, as well as equipment diagnostic analysis for troubleshooting and maintenance tasking of hull mechanical and electrical systems. In recent years, it has been desirable to integrate specialized, third party diagnostic or prognostic software as plug ‘n play modules within the ICAS environment. A specific effort focused on such modules for shipboard LM2500 and Allison 501K gas turbine engines is well underway. Over the course of this three-year Prognostic Enhancement to Diagnostic System (PEDS) program, many lessons have been learned, best practices for ICAS integration have been identified, and the important steps required to field ICAS-capable modules have been realized. This paper summarizes these lessons and processes for future 3rd party integration efforts and provides specific examples for the developed gas turbine modules. The successful deployment of these modules aboard Navy ships is used to validate the ideas presented.

scholarly journals Generalized High Speed Simulation of Gas Turbine Engines

1990 ◽  
Author(s):  
Nanahisa Sugiyama
Keyword(s):  
Real Time ◽  
Gas Turbine ◽  
Gas Turbines ◽  
High Speed ◽  
Power Plants ◽  
Turbine Engines ◽  
Gas Turbine Engines ◽  
Jet Engines ◽  
Industrial Gas Turbine ◽  
High Degree

This paper describes a real-time or faster-than-real-time simulation of gas turbine engines, using an ultra high speed, multi-processor digital computer, designated the AD100. It is shown that the frame time is reduced significantly without any loss of fidelity of a simulation. The simulation program is aimed at a high degree of flexibility to allow changes in engine configuration. This makes it possible to simulate various types of gas turbine engines, including jet engines, gas turbines for vehicles and power plants, in real-time. Some simulation results for an intercooled-reheat type industrial gas turbine are shown.

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.

Measuring-Diagnostic System for Monitoring and Evaluating the Operational Reliability of Rotor Blades for Aircraft Gas Turbine Engines by Acoustic Emission Method

2020 ◽  
Vol 897 ◽  
pp. 190-194
Author(s):  
Margarita Urbaha ◽  
Alexander Urbah ◽  
Mukharbiy Banov ◽  
Vladimir Shestakov ◽  
Pavel Pogorodny
Keyword(s):  
Acoustic Emission ◽  
Gas Turbine ◽  
Early Stage ◽  
Diagnostic System ◽  
Operational Reliability ◽  
Rotor Blades ◽  
Turbine Engines ◽  
Gas Turbine Engines ◽  
Acoustic Emission Method ◽  
Emission Method

Diagnostics of the rotor blades of aircraft gas turbine engines at pre-operational stage and later on during repairs is carried out by instrumental methods of non-destructive testing. The requirements for increasing operational reliability and safety of flights require a search for new solutions in assessing the strength of rotor blades at an early stage of damage development. For these purposes, one of the perspective directions is the development of acoustic emission methods. This article represents an experimental setup and a measuring-diagnostic system for assessing the operational reliability of rotor blades by the acoustic emission method. It also discusses the results of testing.

Sign in / Sign up

Export Citation Format

Share Document