Study on Fault Diagnostics of a Turboprop Engine Using Inverse Performance Model and Artificial Intelligent Methods

2011 ◽  
Author(s):  
Changduk Kong ◽  
Semyeong Lim
Keyword(s):  
Fuzzy Logic ◽  
Diagnostic System ◽  
Engine Performance ◽  
Performance Model ◽  
Performance Parameters ◽  
Artificial Intelligent ◽  
Turboprop Engine ◽  
Base Engine ◽  
Intelligent Methods ◽  
Learning Data

Recently, the health monitoring system of major gas path components of gas turbine uses mostly the model based method like the Gas Path Analysis (GPA). This method is to find quantity changes of component performance characteristic parameters such as isentropic efficiency and mass flow parameter by comparing between measured engine performance parameters such as temperatures, pressures, rotational speeds, fuel consumption, etc. and clean engine performance parameters without any engine faults which are calculated by the base engine performance model. Recently, the expert engine diagnostic systems using the artificial intelligent methods such as Neural Networks (NNs), Fuzzy Logic and Genetic Algorithms (GAs) have been studied to improve the model based method. Among them the NNs are mostly used to the engine fault diagnostic system due to its good learning performance, but it has a drawback due to low accuracy and long learning time to build learning data base if there are large amount of learning data. In addition, it has a very complex structure for finding effectively single type faults or multiple type faults of gas path components. This work builds inversely a base performance model of a turboprop engine to be used for a high altitude operation UAV using measured performance data, and proposes a fault diagnostic system using the base engine performance model and the artificial intelligent methods such as Fuzzy logic and Neural Network. The proposed diagnostic system isolates firstly the faulted components using Fuzzy Logic, then quantifies faults of the identified components using the NN leaned by fault learning data base, which are obtained from the developed base performance model. In leaning the NN, the Feed Forward Back Propagation (FFBP) method is used. Finally, it is verified through several test examples that the component faults implanted arbitrarily in the engine are well isolated and quantified by the proposed diagnostic system.

Study on Practical Application of Turboprop Engine Condition Monitoring and Fault Diagnostic System Using Fuzzy-Neuro Algorithms

2012 ◽  
Author(s):  
Changduk Kong ◽  
Semyeong Lim ◽  
Keonwoo Kim
Keyword(s):  
Neural Networks ◽  
Diagnostic System ◽  
Engine Performance ◽  
Performance Model ◽  
Performance Data ◽  
Turboprop Engine ◽  
The Neural Networks ◽  
Fault Diagnostic ◽  
Intelligent Methods ◽  
Learning Data

Recently, the expert engine diagnostic systems using the artificial intelligent methods such as Neural Networks, Fuzzy Logic and Genetic Algorithms have been studied to improve the model based engine diagnostic methods. Among them the Neural Networks is mostly used to engine fault diagnostic system due to its good learning performance, but it has a drawback due to low accuracy and long learning time to build learning data base if only use of the Neural Networks. In addition, it has a very complex structure due to finding effectively faults of single type faults and multiple type faults of gas path components. This work builds inversely a base performance model of a turboprop engine to be used for a high altitude operation UAV using measuring performance data, and proposes a fault diagnostic system using the base performance model and artificial intelligent methods such as Fuzzy and Neural Networks. Each real engine performance model, which is named as the base performance model that can simulate a new engine performance, is inversely made using its performance test data. Therefore the condition monitoring of each engine can be more precisely carried out through comparison with measuring performance data. The proposed diagnostic system identifies firstly the faulted components using Fuzzy Logic, and then quantifies faults of the identified components using Neural Networks leaned by fault learning data base obtained from the developed base performance model. In leaning the measuring performance data of the faulted components, the FFBP(Feed Forward Back Propagation) is used. In order to user’s friendly purpose, the proposed diagnostic program is coded by the GUI type using MATLAB. The proposed program is verified by application of several case studies having the arbitrary implanted engine component faults as well as real engine performance data.

Development of GUI Type On-Line Condition Monitoring Program for a Turboprop Engine Using LabVIEW®

2011 ◽  
Author(s):  
Changduk Kong ◽  
Keonwoo Kim ◽  
Jihyun Kim
Keyword(s):  
Monitoring System ◽  
Condition Monitoring ◽  
Monitoring Program ◽  
Engine Performance ◽  
Performance Simulation ◽  
Turboprop Engine ◽  
Base Engine ◽  
On Line ◽  
Performance Results ◽  
Line Condition

Recently, the health monitoring system has been developed for precaution and maintenance action against faults or performance degradations of the advanced propulsion system which may be occurred in severe environments such as high altitude, foreign object damage particles, hot and heavy rain and snowy atmospheric conditions. However to establish this health monitoring system, the on-line condition monitoring program is firstly required, and the program must monitor the engine performance trend through comparison between measuring engine performance data and base performance results calculated by base engine performance model. This work aims to develop a GUI type on-line condition monitoring program for the PT6A-67 turboprop engine of a high altitude and long endurance operation UAV using LabVIEW. The base engine performance of the on-line condition monitoring program is simulated using component maps inversely generated from the limited performance deck data provided by engine manufacturer. The base engine performance simulation program is evaluated because analysis results by this program are well agreed with the performance deck data. The proposed on-line condition program can monitor the real engine performance as well as the trend through precise comparison between clean engine performance results calculated by the base performance simulation program and measuring engine performance signals. In the development phase of this monitoring system, a signal generation module is proposed to evaluate the proposed on-line monitoring system. For user friendly purpose, all monitoring program are coded by LabVIEW, and monitoring examples are demonstrated using the proposed GUI type on-condition monitoring program.

Effect of Manufacturing Variability on Turbine Engine Performance: A Probabilistic Study

2013 ◽  
Author(s):  
Michael Gorelik ◽  
Jacob Obayomi ◽  
Jack Slovisky ◽  
Dan Frias ◽  
Howie Swanson ◽  
...  
Keyword(s):  
Performance Metrics ◽  
Model Development ◽  
Engine Performance ◽  
Performance Model ◽  
Probabilistic Methods ◽  
System Level ◽  
Turbine Engine ◽  
Probabilistic Study ◽  
Blade Geometry

While turbine engine Original Equipment Manufacturers (OEMs) accumulated significant experience in the application of probabilistic methods (PM) and uncertainty quantification (UQ) methods to specific technical disciplines and engine components, experience with system-level PM applications has been limited. To demonstrate the feasibility and benefits of an integrated PM-based system, a numerical case study has been developed around the Honeywell turbine engine application. The case study uses experimental observations of engine performance such as horsepower and fuel flow from a population of engines. Due to manufacturing variability, there are unit-to-unit and supplier-to-supplier variations in compressor blade geometry. Blade inspection data are available for the characterization of these geometric variations, and CFD analysis can be linked to the engine performance model, so that the effect of blade geometry variation on system-level performance characteristics can be quantified. Other elements of the case study included the use of engine performance and blade geometry data to perform Bayesian updating of the model inputs, such as efficiency adders and turbine tip clearances. A probabilistic engine performance model was developed, system-level sensitivity analysis performed, and the predicted distribution of engine performance metrics was calibrated against the observed distributions. This paper describes the model development approach and key simulation results. The benefits of using PM and UQ methods in the system-level framework are discussed. This case study was developed under Defense Advanced Research Projects Agency (DARPA) funding which is gratefully acknowledged.

Adaptation Application to Engine Modelling

2007 ◽  
Author(s):  
Jude Iyinbor
Keyword(s):  
Measurement Data ◽  
Engine Performance ◽  
Performance Model ◽  
Operating Conditions ◽  
Adaptation Process ◽  
Design Point ◽  
Component Map ◽  
Important Measurement ◽  
Unknown Component ◽  
Selection Of

The optimisation of engine performance by predictive means can help save cost and reduce environmental pollution. This can be achieved by developing a performance model which depicts the operating conditions of a given engine. Such models can also be used for diagnostic and prognostic purposes. Creating such models requires a method that can cope with the lack of component parameters and some important measurement data. This kind of method is said to be adaptive since it predicts unknown component parameters that match available target measurement data. In this paper an industrial aeroderivative gas turbine has been modelled at design and off-design points using an adaptation approach. At design point, a sensitivity analysis has been used to evaluate the relationships between the available target performance parameters and the unknown component parameters. This ensured the proper selection of parameters for the adaptation process which led to a minimisation of the adaptation error and a comprehensive prediction of the unknown component and available target parameters. At off-design point, the adaptation process predicted component map scaling factors necessary to match available off-design point performance data.

Development and Integration of Rain Ingestion Effects in Engine Performance Simulations

2014 ◽  
Vol 137 (4) ◽  
Author(s):  
I. Roumeliotis ◽  
A. Alexiou ◽  
N. Aretakis ◽  
G. Sieros ◽  
K. Mathioudakis
Keyword(s):  
Engine Performance ◽  
Velocity Slip ◽  
Droplet Surface ◽  
Performance Model ◽  
Droplet Breakup ◽  
Test Case ◽  
Case Scenario ◽  
Worst Case ◽  
Engine Model ◽  
Component Models

Rain ingestion can significantly affect the performance and operability of gas turbine aero-engines. In order to study and understand rain ingestion phenomena at engine level, a performance model is required that integrates component models capable of simulating the physics of rain ingestion. The current work provides, for the first time in the open literature, information about the setup of a mixed-fidelity engine model suitable for rain ingestion simulation and corresponding overall engine performance results. Such a model can initially support an analysis of rain ingestion during the predesign phase of engine development. Once components and engine models are validated and calibrated versus experimental data, they can then be used to support certification tests, the extrapolation of ground test results to altitude conditions, the evaluation of control or engine hardware improvements and eventually the investigation of in-flight events. In the present paper, component models of various levels of fidelity are first described. These models account for the scoop effect at engine inlet, the fan effect and the effects of water presence in the operation and performance of the compressors and the combustor. Phenomena such as velocity slip between the liquid and gaseous phases, droplet breakup, droplet–surface interaction, droplet and film evaporation as well as compressor stages rematching due to evaporation are included in the calculations. Water ingestion influences the operation of the components and their matching, so in order to simulate rain ingestion at engine level, a suitable multifidelity engine model has been developed in the Proosis simulation platform. The engine model's architecture is discussed, and a generic high bypass turbofan is selected as a demonstration test case engine. The analysis of rain ingestion effects on engine performance and operability is performed for the worst case scenario, with respect to the water quantity entering the engine. The results indicate that rain ingestion has a strong negative effect on high-pressure compressor surge margin, fuel consumption, and combustor efficiency, while more than half of the water entering the core is expected to remain unevaporated and reach the combustor in the form of film.

Comparison and Synthesis of Performance and Aerodynamic Modeling of a Pass-Off Turbofan Engine Test Cell

2015 ◽  
Author(s):  
Martin Marx ◽  
Michael Kotulla ◽  
André Kando ◽  
Stephan Staudacher
Keyword(s):  
Research Effort ◽  
Engine Performance ◽  
Cell System ◽  
Performance Model ◽  
Test Cell ◽  
Test Facility ◽  
Engine Test ◽  
Combined System ◽  
Installation Effects ◽  
Engine Testing

To ensure the quality standards in engine testing, a growing research effort is put into the modeling of full engine test cell systems. A detailed understanding of the performance of the combined system, engine and test cell, is necessary e.g. to assess test cell modifications or to identify the influence of test cell installation effects on engine performance. This study aims to give solutions on how such a combined engine and test cell system can be effectively modeled and validated in the light of maximized test cell observability with minimum instrumentation and computational requirements. An aero-thermodynamic performance model and a CFD model are created for the Fan-Engine Pass-Off Test Facility at MTU Maintenance Berlin-Brandenburg GmbH, representing a W-shape configuration, indoor Fan-Engine test cell. Both models are adjusted and validated against each other and against test cell instrumentation. A fast-computing performance model is delivering global parameters, whereas a highly-detailed aerodynamic simulation is established for modeling component characteristics. A multi-disciplinary synthesis of both approaches can be used to optimize each of the specific models by calibration, optimized boundary conditions etc. This will result in optimized models, which, in combination, can be used to assess the respective design and operational requirements.

Sign in / Sign up

Export Citation Format

Share Document