• Proceedings of the Korean Society of Propulsion Engineers Conference
• /
• 2006.05a
• /
• pp.209-212
• /
• 2006

In this study, Support Vector Machine(SVM) and Artificial Neural Network(ANN) are used for developing the defect diagnostic algorithm of the aircraft turbo-shaft engine. Effect of altitude variation on the Defect Diagnostics algorithm has been included and evaluated. Separate learning Algorithm(SLA) suggested with ANN to loam the performance data selectively after classifying the position of defects by SVM improves the classification speed and accuracy.

• Journal of the Korean Society of Propulsion Engineers
• /
• v.11 no.1
• /
• pp.43-50
• /
• 2007

In this study, Hybrid Separate Learning Algorithm(SLA) consisting of Support Vector Machine(SVM) and Artificial Neural Network(ANN) has been used for developing the defect diagnostic algorithm of the aircraft turbo-shaft engine in the off-design range considering altitude variation. Although the number of teaming data and test data highly increases more than 6 times compared with those required for the design condition, the proposed defect diagnostics of gas turbine engine using SLA was verified to give the high defect classification accuracy in the off-design range considering altitude variation.

• Proceedings of the Korean Society of Propulsion Engineers Conference
• /
• 2008.11a
• /
• pp.23-27
• /
• 2008

In this study, Real Coded Genetic Algorithm(RCGA) and Artificial Neural Network(ANN) are used for developing the defect diagnostics of the aircraft turbo-shaft engine. ANN accompanied with large amount data has a most serious problem to fall in the local minima. Because of this weak point, it becomes very difficult to obtain good convergence ratio and high accuracy. To solve this problem, GA based ANN has been suggested. GA is able to search the global minima better than ANN. GA based ANN has shown the RMS defect error of 5% less in single and dual defect cases.

• Proceedings of the Korean Society of Propulsion Engineers Conference
• /
• 2006.11a
• /
• pp.289-292
• /
• 2006

In this paper, the hybrid algorithm of Support Vector Machine md Artificial Neural Network is used for the defect diagnostics algorithm for the aircraft turbo-shaft engine. The results of learning of ANN, especially, accuracy or speed of convergence are sensitive to the number of data, so a comparison between design point and off-design area, especially, Mach number and fuel flow variable area, is essential research. From application results for diagnostics of gas turbine engine, it was confirmed that the hybrid algorithm could detect well in the of-design area as well as design point.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.35 no.3
• /
• pp.238-247
• /
• 2007

Genetic Algorithms(GA) which searches optimum solution using natural selection and the law of heredity has been applied to learning algorithms in order to estimate performance deterioration of the aircraft gas turbine engine. The compressor, gas generator turbine and power turbine are considered for engine performance deterioration and estimation for performance deterioration of a single component at design point was conducted. As a result of that, defect diagnostics has been conducted. The input criteria for the genetic algorithm to guarantee the high stability and reliability was discussed as increasing learning data sets. As a result, the accuracy of defect estimation and diagnostics were verified with its RMS error within 3%.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2002.11b
• /
• pp.611-616
• /
• 2002

Bearing diagnostics is difficult in a gearbox because bearing signals are masked by the strong gear signals. Self adaptive noise cancellation(SANC) is useful technique to seperate bearing signals from gear signals. While gear signals are correlated with a long correlation length, bearing signals are not correlated with a short length. SANC seperates two components on the basis of correlation length. Then we can find defect frequency component in the envelope spectrum of the bearing signals.

• Proceedings of the Korean Society of Propulsion Engineers Conference
• /
• 2006.11a
• /
• pp.285-288
• /
• 2006

Genetic Algorithms(GA) which searches optimum solution using natural selection and the law of heredity has been applied to teaming algorithms in order to estimate performance deterioration of the aircraft gas turbine engine. The compressor, gas generation turbine and power turbine are considered for estimation for performance deterioration of a complex component at design point was conducted. As a result of that, complex defect diagnostics has been conducted. As a result, the accuracy of diagnostics were verified with its relative error with in 10% at each component.

• Journal of the Korean Society of Propulsion Engineers
• /
• v.12 no.3
• /
• pp.60-67
• /
• 2008

In this study, the genetic algorithm has been used for the real-time defect diagnosis on the operation of the aircraft gas-turbine engine. The component elements of the gas-turbine engine for consideration of the performance deterioration consist of the compressor, the gas generation turbine and the power turbine. Compared to the on-design point, the teaming data has been increased 200 times in case off-design conditions for the altitude, the flight mach number and the fuel consumption. Therefore, enormous learning time has been required for the satisfied convergence. The optimal division has been proposed for learning time decrease as well as the high accuracy. As results, the RMS errors of the defect diagnosis using the genetic algorithm have been confirmed under 5 %.

• Proceedings of the Korean Society of Propulsion Engineers Conference
• /
• 2007.11a
• /
• pp.350-353
• /
• 2007

In this study, the genetic algorithm has been used for the real-time defect diagnosis on the operation of the aircraft gas-turbine engine. The component elements of the gas-turbine engine for consideriation of the performance deterioration is consist of the compressor, the gas generation turbine and the power turbine, repectively. Compared to the on-design point on the sea-level condition, the learning data has been increased 200 times in case of the off-design conditions for the altitude, the flight mach number and the fuel consumption. Therefore, enormous learning time has been required for the satisfied convergence. The optimum division has been proposed to decrease learning time as well as to obtain high accuracy. As results, the RMS errors of the defect diagnosis using the genetic algorithm have been estimated under 5 %.

• Proceedings of the Korean Society of Propulsion Engineers Conference
• /
• v.y2005m4
• /
• pp.248-251
• /
• 2005

In this paper, health monitoring technique has been studied for performance deterioration caused by the defects of the gas turbine. The parameters for performance diagnostics have been extracted by using GSP program for modeling the target engine. The virtual sensor model for the health monitoring has been built of those data. The position and magnitude of the defects of the engine components have been determined by using Multiple Linear Regression technique and the method using the weight in order to diagnose the single and multiple defects.