• Smart Structures and Systems
• /
• 제23권4호
• /
• pp.393-403
• /
• 2019

Applying more features gives us better accuracy in modeling; however, increasing the inputs causes the curse of dimensions. In this paper, a new structure has been proposed for fault detecting and identifying (FDI) of high-dimensional systems. This structure consist of two structure. The first part includes Auto-Encoders (AE) as Deep Neural Networks (DNNs) to produce feature engineering process and summarize the features. The second part consists of the Local Model Networks (LMNs) with LOcally LInear MOdel Tree (LOLIMOT) algorithm to model outputs (multiple models). The fault detection is based on these multiple models. Hence the residuals generated by comparing the system output and multiple models have been used to alarm the faults. To show the effectiveness of the proposed structure, it is tested on single-shaft industrial gas turbine prototype model. Finally, a brief comparison between the simulated results and several related works is presented and the well performance of the proposed structure has been illustrated.

• 대한기계학회논문집B
• /
• 제24권7호
• /
• pp.994-1001
• /
• 2000

The dynamic behavior of a single-pressure heat recovery steam generator and turbine system for the combined cycle power plant is simulated on the basis of one-dimensional unsteady governing equations. A water level control and a turbine power control are also included in the calculation routine. Transient response of the system to the variation of gas turbine exit condition is simulated and effect of the turbine power control on the system response is examined. In addition, the effect of the treatment of inertia terms(fluid inertia and thermal inertia of heat exchanger metal) on the simulated transient response is investigated.

• 한국전산유체공학회지
• /
• 제6권4호
• /
• pp.15-25
• /
• 2001

Numerical prediction of the diffusion controlled transition in a turbine gas pass is important because it can change the local heat transfer rate over a turbine blade as much as three times. In this study, the gas flow over turbine blade is simplified to the flat plate boundary layer, and an adaptive grid scheme redistributing grid points within the computation domain is proposed with a great emphasis on the construction of the grid control function. The function is sensitized to the second invariant of the mean strain tensor, its spatial gradient, and the interaction of pressure gradient and flow deformation. The transition process is assumed to be described with a κ-ε turbulence model. An elliptic solver is employed to integrate governing equations. Numerical results show that the proposed adaptive grid scheme is very effective in obtaining grid independent numerical solution with a very low grid number. It is expected that present scheme is helpful in predicting actual flow within a turbine to improve computation efficiency.

• 한국전자통신학회논문지
• /
• 제18권5호
• /
• pp.841-852
• /
• 2023

국내 전력계통의 주파수 조정용 발전기로 사용되고 있는 가스터빈은 탄소중립 정책과 더불어 신속한 기동·정지 및 높은 열효율 등으로 인해 이용률이 증가하고 있다. 가스터빈은 고온의 화염을 이용하여 터빈을 회전시키기 때문에 터빈 입구온도가 기기의 성능과 수명을 좌우하는 핵심요소로 작용하고 있다. 하지만 입구온도는 직접적인 측정이 불가능함에 따라 제작사가 산출한 온도를 이용하거나, 현장 경험을 토대로 하여 예측된 온도를 적용하고 있어서 가스터빈의 안정적인 운전 및 유지관리에 많은 어려움을 겪고 있다. 이에 본 연구에서는 인공신경망에서 많이 사용되고 있는 DNN(: Deep Neural Network) 기반으로 하는 재열 가스터빈의 입구온도를 예측할 수 있는 모델을 제시하고 실측 데이터를 기반으로 제안된 DNN의 성능을 검증하고자 한다.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2004년도 학술대회 논문집 정보 및 제어부문
• /
• pp.638-640
• /
• 2004

The gas stripper system of a nuclear power plant provides gas-free water to a reactor and a turbine system. The gas tripper unit has two control systems to regulate pressure and level independently. Because the level and the pressure interact as a control disturbance each other, continuous operation of the system is difficult. In this paper, We describe the controllability evaluation of the gas stripper system and the results of the optimally tuned control gains.

• 한국유체기계학회 논문집
• /
• 제19권6호
• /
• pp.26-33
• /
• 2016

Combined heat and power (CHP) system is one of the power generation system which can generate both electricity and heat. Generally, mid-size and big-size CHP plant in Korea generate electricity from gas turbine and steam turbine, then supply heat from exhaust gas. Actually, CHP can supply heat using district heater which is located at low pressure turbine exit or inlet. When the district heater locates after low pressure turbine, which called back pressure type turbine, there need neither condenser nor mode change operating control logic. When the district heater locates in front of low pressure turbine or uses low pressure turbine extraction steam flow, which calls condensing type turbine, which kind of turbine requires condenser. In this case, mode change operation methods are used for generating maximum electricity or maximum heat according to demanding the seasonal electricity and heat.

• 유체기계공업학회:학술대회논문집
• /
• 유체기계공업학회 1998년도 유체기계 연구개발 발표회 논문집
• /
• pp.191-197
• /
• 1998

The recent results of the engine development performed in this you on Turbogreen 1200, the first industrial gas turbine engine developed in Korea, are presented. In order to improve the engine performance and structural stability from the first prototype engine, several variants of the engine and major components such as combustor and rotor assembly have been developed and tested. This paper shows these results especially focused on the engine test and performance analysis, in which test system, instrumentation and data processing are discussed as well. The engine performance and its trend give relatively good coincidence with the design ones. At design power of 1.2MW, the thermal efficiency of the engine is estimated over $25\%$ which is below the design target of $27.2\%$. This gap of efficiency is caused mainly by large tip clearance between turbine blades and casing. Considering high design efficiency superior to those of other competitive engines in this power class, Turbogreen 1200 would have a strong competition in its performance if the design efficiency is achieved by further developments such as tip clearance control, which are very possible and natural in final mass production of the developed gas turbine engine.

• 대한기계학회:학술대회논문집
• /
• 대한기계학회 2000년도 추계학술대회논문집B
• /
• pp.662-667
• /
• 2000

A simulation procedure for a full transient analysis of the start-up of heavy-duty gas turbines for power generation is constructed. Compressor stages are grouped into three categories (front, mid, rear) and three different stage characteristic curves are applied to consider the different low-speed operating characteristics. Start-up behavior of a typical single-shaft gas turbine for power generation is simulated. The predicted transient behavior shows a good agreement with the field data. Special attention is paid to the effects of the modulation of VIGV on start-up characteristics, which play a key role in the stable operation of gas turbines.

• 유체기계공업학회:학술대회논문집
• /
• 유체기계공업학회 2003년도 유체기계 연구개발 발표회 논문집
• /
• pp.80-87
• /
• 2003

Micro gas turbines are designed with low turbine inlet temperature and pressure ratio. To overcome the efficiency defect of the simple cycle, adoption of the recuperator is an inevitable choice. In addition to the design performance, we should also pay attention to the off-design performance of gas turbines since they usually operate at part-load conditions for a considerable amount of the time. This study aims at analyzing off-design performance characteristics of micro gas turbines and addressing the importance of the recuperator in the part load operation. Comparative analyses have been performed to evaluate the part load performance differences among various design and operating options : simple vs recuperative cycles, single vs two shaft configurations, various operating strategies for the single shaft configuration (fuel only control, variable speed operation, variable inlet guide vane control), and current vs advanced engines. Major finding is that maintaining turbine at high level is crucial in efficient operation of micro gas turbines.

• 에너지공학
• /
• 제12권1호
• /
• pp.1-10
• /
• 2003

가압유동층 연소 유닛은 1~1.5 MPa, 연소 온도 850~87$0^{\circ}C$ 조건으로 운전된다. 가압 석탄 연소 시스템은 전열관을 통한 열전달로 증기를 생산하며 가스터빈으로 공급될 고온 가스를 생산한다. 가스 중의 고체 잔류물에 의한 가스터빈의 성능 저하 때문에 가스 정제가 매우 중요하며 석탄과 흡수제 및 연소 공기를 가압하여야 하고 배가스와 회 제거 시스템에서는 감압을 해야 하기 때문에 운전이 다소 복잡하다. 증기터빈 대 가스터빈에서 생산되는 전력의 비율은 약 80:20이고 모든 부하 범위에서 연소기와 가스터빈이 서로 적절히 조화를 이루어야 하기 때문에 PFBC와 복합 사이클 발전 루트는 독특한 제어 방식을 갖는다. 유동층에 적용할 수 있는 가스의 최대 온도는 회 융점에 의해 제한을 받기 때문에 가스터빈은 일반 가스터빈에 비해 좀 특별하다고 할 수 있다. 회의 용융이 일어나지 않도록 하기 위한 최대 허용 가스 온도는 약 90$0^{\circ}C$이다. 가스터빈의 높은 압력비 때문에 압축시 인터쿨링을 사용하며 이는 상대적으로 낮은 터빈 입구의 온도를 상쇄하기 위한 것이다.