http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Estimation of LOCA Break Size Using Cascaded Fuzzy Neural Networks
최건필,유쾌환,백주현,나만균 한국원자력학회 2017 Nuclear Engineering and Technology Vol.49 No.3
Operators of nuclear power plants may not be equipped with sufficient information during aloss-of-coolant accident (LOCA), which can be fatal, or they may not have sufficient time toanalyze the information they do have, even if this information is adequate. It is not easy topredict the progression of LOCAs in nuclear power plants. Therefore, accurate information ontheLOCAbreak positionandsize should be provided to efficientlymanage the accident. In thispaper, the LOCA break size is predicted using a cascaded fuzzy neural network (CFNN) model. The input data of theCFNNmodel are the time-integrated values of each measurement signalfor an initial short-time interval after a reactor scram. The training of the CFNN model isaccomplished by a hybrid method combined with a genetic algorithm and a least squaresmethod. As a result, LOCA break size is estimated exactly by the proposed CFNN model.
구영도,유쾌환,나만균 한국원자력학회 2017 Nuclear Engineering and Technology Vol.49 No.4
Residual stress is a critical element in determining the integrity of parts and the lifetime of weldedstructures. It is necessary to estimate the residual stress of a welding zone because residual stress is amajor reason for the generation of primary water stress corrosion cracking in nuclear power plants. That is, it is necessary to estimate the distribution of the residual stress in welding of dissimilarmetals under manifold welding conditions. In this study, a cascaded support vector regression (CSVR)model was presented to estimate the residual stress of a welding zone. The CSVR model was seriallyand consecutively structured in terms of SVR modules. Using numerical data obtained from finiteelement analysis by a subtractive clustering method, learning data that explained the characteristicbehavior of the residual stress of a welding zone were selected to optimize the proposed model. Theresults suggest that the CSVR model yielded a better estimation performance when compared with aclassic SVR model.
Reactor Vessel Water Level Estimation During Severe Accidents Using Cascaded Fuzzy Neural Networks
Dong Yeong Kim,유쾌환,Geon Pil Choi,Ju Hyun Back,나만균 한국원자력학회 2016 Nuclear Engineering and Technology Vol.48 No.3
Global concern and interest in the safety of nuclear power plants have increased considerablysince the Fukushima accident. In the event of a severe accident, the reactor vesselwater level cannot be measured. The reactor vessel water level has a direct impact onconfirming the safety of reactor core cooling. However, in the event of a severe accident, itmay be possible to estimate the reactor vessel water level by employing other information. The cascaded fuzzy neural network (CFNN) model can be used to estimate the reactor vesselwater level through the process of repeatedly adding fuzzy neural networks. The developedCFNN model was found to be sufficiently accurate for estimating the reactor vessel waterlevel when the sensor performance had deteriorated. Therefore, the developed CFNN modelcan help provide effective information to operators in the event of a severe accident.