• Proceedings of the Korean Society of Propulsion Engineers Conference
• /
• 한국추진공학회 2006년도 제27회 추계학술대회논문집
• /
• 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 of Propulsion Engineers
• /
• 제12권1호
• /
• pp.44-50
• /
• 2008

In this study a turboshaft engine for a helicopter propulsion system was modeled using SIMULINK and the components' maps were generated from the limited performance deck data provided by engine supplier using a hybrid method with the genetic algorithms and the system identification method. In order to verify the SIMULINK performance model and the component maps generated by the hybrid method, the steady-state performance analysis results were compared with the performance data provided by engine manufacturer. In this investigation, it was confirmed that the analysis results by the proposed model are closely met with those by engine manufacturer's data.

• Proceedings of the Korean Society of Propulsion Engineers Conference
• /
• 한국추진공학회 2007년도 제28회 춘계학술대회논문집
• /
• pp.245-249
• /
• 2007

In this study a model-based diagnostic method using the Neural Network was proposed for PW206C turbo shaft engine and performance model was developed by SIMULINK. Fault and test database to build the NN was obtained at various off-design operating range such as flight altitude, flight Mach number and gas generator rotational speed variation. According to the fault detection analysis results, it was confirmed that the proposed fault detection method could find well the fault of compressor, compressor turbine and power turbine at on-design point as well as off-design point conditions.

• Journal of the Korean Society of Propulsion Engineers
• /
• 제10권2호
• /
• pp.102-109
• /
• 2006

In this Paper, Support Vector Machine(SVM) and Artificial Neural Network(ANN) are used for developing the defect diagnostic algorithm of the aircraft turbo-shaft engine. The system that uses the ANN falls in a local minima when it learns many nonlinear data, and its classification accuracy ratio becomes low. To make up for this risk, the Separate Learning Algorithm(SLA) of ANN has been proposed by using SVM. This is the method that ANN learns selectively after discriminating the defect position by SVM, then more improved performance estimation can be obtained than using ANN only. The proposed SLA can make the higher classification accuracy by decreasing the nonlinearity of the massive data during the training procedure.

• Journal of the Korean Society of Propulsion Engineers
• /
• 제11권3호
• /
• pp.29-34
• /
• 2007

In this study a model-based diagnostic method using the Neural Network was proposed for PW206C turbo shaft engine and performance model was developed by SIMULINK. Fault and test database to build the NN was obtained at various off-design operating range such as flight altitude, flight Mach number and gas generator rotational speed variation. According to the fault detection analysis results, it was confirmed that the proposed fault detection method could find well the fault of compressor, compressor turbine and power turbine at on-design point as well as off-design point conditions.

• Proceedings of the Korean Society of Propulsion Engineers Conference
• /
• 한국추진공학회 2008년도 제31회 추계학술대회논문집
• /
• 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.

• 연구논문집
• /
• 통권26호
• /
• pp.43-50
• /
• 1996

Present paper describes on/off design performance analysis of an 74KW industrial turboshaft gasturbine engine. Procedures to match between the compressor, combustor and turbine have been incorporated into the developed program satisfying compatibility requirement of flow and work and ratational speed. The validity of the performance results from the developed program are yet to be proved through performance experiments of the resultant engine, but comparison of the present results with those from "GASCAN(Thermoflow:America) under similar mass inlet flow, pressure ratio, and speed condition show good agreement despite present results underpredict 6-10% for power and up to 3% in efficiency, respectively.

• Journal of the Korea Institute of Military Science and Technology
• /
• 제6권2호
• /
• pp.83-94
• /
• 2003

Preliminary aerodynamic design of a compressor is carried out to meet the design requirements which are pressure ratio of 13, air mass flow rate of 4 ㎏/s and rotational speed of 45,000 rpm. The compressor type is chosen as an axial-centrifugal compressor from the design requirements which is suitable for a medium power class turboprop or turboshaft engine. Its overall isentropic efficiency is estimated to be 0.796 and its surge margin to be 20% exceeding the design requirement. This paper summarizes the aerodynamic design details including the design procedures and the results of the axial -centrifugal compressor.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• 제33권11호
• /
• pp.74-79
• /
• 2005

Computational studies on the hydrodynamic behavior of the forward-sweep inducers for the rocket-engine turbopump are presented in comparison with the conventional backward- sweep inducers. In the present study, two kinds of forward-sweep inducers are designed and numerically investigated. Forward-sweep inducers have bigger tip solidity compared to backward-sweep inducers even with shorter axial length due to their forward-sweep leading edge profiles. It is shown that back flows at the inlet decreases dramatically for forward- sweep inducers. And the low pressure region at the back flow are also decreased, which is assumed to promote the suction performance of the inducers. It seems that the hub located upstream of the tip at the leading edge induces pre whirl at the inlet blade tip for the backward sweep inducer. And this pre whirl leads to the big back flow.

• Aerospace Engineering and Technology
• /
• 제1권1호
• /
• pp.163-172
• /
• 2002

The turbine system composed of a nozzle and a rotor is used to drive turbopumps while gas passes through the nozzle, potential energy is converted to kinematic energy, which forces the rotor blades to spin. In this study, an aerodynamic design of a turbine system is investigated using compressible fluid dynamic theories with some pre-determined design requirements (i.e.,pressure ratio, rotational speed, required power etc.) obtained from a liquid rocket engine (L.R.E.) system design. For simplicity of a turbine system, impulse-type rotor blades for open type L.R.E. have been chosen. Usually, the open-type turbine system requires low mass flow rate compared to the close-type system. In this study, a partial admission nozzle is adopted to maximize the efficiency of the close-type turbine system. A design methodology of the a turbine system has been introduced. Especially, a partial admission nozzle has been designed by means of simple empirical correlations between efficiency and configuration of the nozzle. Finally, a turbine system design for a 10 ton thrust level of L.R.E is presented.