http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
AAKR을 이용한 원자력 발전소 고장 패턴 추출에 관한 연구
박기범,안홍민,강성기,채장범,Park, Kibeom,Ahn, Hongmin,Kang, Seongki,Chai, Jangbom 한국압력기기공학회 2017 한국압력기기공학회 논문집 Vol.13 No.1
In this paper, we investigate the feasibility of a strategy of failure detection and identification. The point of proposed strategy includes a pattern extraction approach for failure identification using Auto-Associative Kernel Regression (AAKR). We consider a simulation data concerning 605 signals of a Generic Pressurized Water Reactor(GPWR). In the application, the reconstructions are provided by a set of AAKR models, whose input signals have been selected by Correlation Analysis(CA) for the identification of the groups. The failure pattern is extracted by analyzing the residuals of observations and reconstructions. We present the possibility of extraction of patterns for six failure.
원자력발전소 시뮬레이터 데이터의 패턴인식을 이용한 압력경계기기 고장 진단 연구
안홍민,최현우,강성기,채장범,Ahn, Hongmin,Choi, Hyunwoo,Kang, Seongki,Chai, Jangbom 한국압력기기공학회 2017 한국압력기기공학회 논문집 Vol.13 No.1
We diagnosed the defect using the data obtained from the nuclear power plant simulator. In this paper, we diagnosed faults in the nuclear power plant system for discovery instead of the traditional single-component or device unit. We created the six fault scenarios and used a fault simulator to obtain the fault data. It was extracted pattern from acquired failure data. Neural network model was trained and simple pattern matching algorithm was applied. We presented a simulation result and confirmed that the applied algorithm works correctly.
빌딩 에너지 절감을 위한 MTS를 이용한 효율적인 재실감지 방법에 관한 연구
차재민(Jae-Min Cha),김준영(Joon-Young Kim),신중욱(Junguk Shin),염충섭(Choongsub Yeom),강성기(Seongki Kang) 한국에너지기후변화학회 2016 에너지기후변화학회지 Vol.11 No.2
To deal with greenhouse gas reduction and limited energy resources, the necessity for efficient building energy management has recently been focused. For the efficient building energy management, accurate occupancy detection is required and also is well-know problem. This study proposed an accurate occupancy detection method based on Mahalanobis-Taguchi System (MTS) which is widely used pattern classification method in other faults diagnosis problems. To validate the MTS based occupancy detection method, we conducted the experiments using two test dataset. The experiential results show accuracies of 97.75%, 86.67% with all variables. However, after useful variable optimization, results shows accuracies of 97.64% and 96.28%.