http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
최의진,안석주 대한신장학회 1999 Kidney Research and Clinical Practice Vol.18 No.1
The status of renal replacement therapy in Korea as follows; 1) The response rate to questionaire was 57.9% of the 226 hemodialysis centers in Korea and data file was sent in the 62.4% of responder. 2) The number of dialysis center was 226 and the number of hemodialysis machine was 3,507 and annual increasing rate were 8,7%, 14.0%, respectively. 3) The total number of ESRD patients was 20,244 and prevalance and incidence of ESRD were 431.9 and 101.1 patients per million population(ppm). 4) The proportion of renal replacement therapy was hemodialysis(HD) 53.3%, peritoneal dialysis(PD) 17.196, renal transplants(KT) 29.5%. 5) The proportion of long-term and elderly patients was markedly increased comparing 1985 (long term dialysis 20% vs. 2%, over 60 year old patients 26.2% vs. 13.8%. 6) The primary cause of renal disease was diabetic nephropathy 34.09o, chronic glomerulone-phritis 20.8%, hypertensive nephropathy 15.7%. 7) The mean BMI(body mass index; kg/M²)in over 18 year old patients was 20.7±2.7 kg/M² in the HD and 22.2±3.0 kg/M² in the PD. 71.9M of HD patients and 73.2% of PD were in the normal range (18.5-24.9). 8) The fistula survival rate was 6 month 93.4%, 1 yr 91.7%, 3 yr 87.6%, 5 yr 84.7%. 9) The cause of death were cardiac disease 31.8%, miscellaneous 23.5%, vascular disease 17.2%, infection 14.2%, liver disease 1.2%, social cause 5.9%.
믹스업 알고리즘과 오토 인코더를 이용한 전동기 기어 고장 진단 실용화 기법 연구
최의진,한지훈,송승민,홍선기 대한전기학회 2024 전기학회논문지 Vol.73 No.1
In this paper, a practical data acquisition method and fault diagnosis method for applying motor fault diagnosis in the field are studied. Since it is very difficult to acquire fault data in the field, unsupervised learning methods that can be trained using only normal state data are mainly used. However, unsupervised learning methods are very vulnerable to disturbances and are difficult to express the fault level. Disturbances in the field include electrical noise, which can cause data acquisition devices to fail due to low power quality in the field and affect the measured signal, and mechanical noise, such as external vibrations, which directly affect the operation of the electric motor. To minimize the impact of electrical noise, it is common to use hardware filters. Unlike previous studies that use theoretical cutoff frequency setting methods, this paper proposes a method to find the appropriate cutoff frequency using LRP(Layer-wise Relevance Propagation) analysis, one of the XAI(eXplainable A.I) techniques, for practical data acquisition. Fault diagnosis in the field requires robust unsupervised learning algorithms that can ignore the presence of mechanical noise in the signal, such as transient shocks. This is solved by post-processing the output of the auto-encoder with a moving average filter. To represent the fault level a data generation technique, the mix-up algorithm, is used. A method is proposed to threshold the auto-encoder multiple times with data generated by the mix-up algorithm. This proposed method shows the availability of motor fault diagnosis considering the on-site data.