• 한국통신학회논문지
• /
• 제26권11C호
• /
• pp.75-84
• /
• 2001

본 논문에서는 신경망을 이용한 실시간 고장 검출 및 진단(FDD : Fault Detection and Diagnosis) 시스템을 제안한다. 제안된 시스템은 공조 시스템(FDD : Air Handling Unit)에서 발생 가능한 여러 고장들을 검출하고 진단할 수 있다. 고장 검출 및 진단 기법으로 3층 구조의 전방향(feed-forward) 신경망을 사용하였고, 여기에 사용된 학습 방법은 역전파(back-propagation) 학습 알고리즘이다. 공조 시스템에 적용된 실시간 고장 검출 및 진단 시스템은 비주얼 C++와 비주얼 베이직을 사용하여 구현하였다. 제안된 고장 검출 및 진단 시스템을 실제 운전 중인 공조 시스템에 적용하여 실험하였고, 정확한 고장 검출 및 진단이 수행됨을 실험 결과로서 입증하였다.

• 전기학회논문지
• /
• 제65권6호
• /
• pp.1103-1107
• /
• 2016

The automatic tensioning device of the catenary system constantly maintains the tension of the trolley wire by absorbing the variations due to the elasticity of the line caused by temperature variation. The tension plays an important role in affecting the electric motorcar operation directly. This paper suggests the methodology of the life cycle extension and the maintenance of the automatic tensioning device by means of performance diagnosis of the pulley type automatic tensioning device which has been commonly used for the electric railway system. Through conducting performance diagnosis and comparative test for the wornout pulley type automatic tensioning device by replacing the components such as the bearing and the bearing shaft without replacing all the assembly, the tensioning device is analyzed whether it is properly functioned. Provided that the maintenance regulation is reinforced so as to implement the bearing replacement through periodical precise inspection along with random check-up inspection which is now carried out by the operating organizations, it is ensured that the life cycle extension and the reduction of maintenance cost of the tensioning device could be achieved.

• 대한간호학회지
• /
• 제38권2호
• /
• pp.270-277
• /
• 2008

Purpose: This study was done to identify predictors of the fighting spirit or helplessness/hopelessness in the patients' mental adjustment to cancer. Cancer patients' characteristics like performance status, metastasis and duration of diagnosis with demographic factors, spiritual support and social support were used as predictors of a fighting spirit or helplessness/hopelessness. Methods: A total of 124 ambulatory cancer patients completed the Mental Adjustment to Cancer (MAC) scale and responded in a structured instrument about their characteristics, spiritual and social support. Results: The results of multiple regression analysis revealed that confidence in the supporter ($R^2=.114$, p=.000), duration of cancer diagnosis ($R^2=.041$, p=.000) and faith ($R^2=.030$, p=.000) were predictive of a fighting spirit ($R^2=.185$, p=.000); whereas, education ($R^2= .074$, p=.001), performance status ($R^2=.055$, p=.000), satisfaction with social support ($R^2=.046$, p=.000), and metastasis ($R^2=.037$, p=.000) were predictive of helplessness/hopelessness ($R^2=.202$, p=.000). Conclusion: Social support, spiritual support and disease related factors like metastasis, performance status, and duration of cancer diagnosis need to be considered in a psychosocial nursing intervention for a fighting spirit or helplessness/hopelessness.

• 한국마린엔지니어링학회:학술대회논문집
• /
• 한국마린엔지니어링학회 2005년도 전기학술대회논문집
• /
• pp.777-782
• /
• 2005

The importance of emergency diesel generator(EDG) has confirmed in the safety evaluation of PSA and the study on aging of EDG has been progressed actively as a part of the project of nuclear plant aging research in the U.S.A. As the result, the concept of performance evaluation is being transferred from statistical analysis of test results to performance monitoring and trending analysis for monitoring of aging and reliability. Recently, the study related aging characteristic and reliability for EDGS has begun in Korea. Consequently, the efficient performance monitoring based systematic and integrated monitoring and failure diagnostic technology is necessary. In the research, the knowledge basis of monitoring parameters for EDGS is constructed, and the prototype monitoring and diagnosis system applicable to Pielstick EDG is developed.

• 한국소음진동공학회논문집
• /
• 제22권5호
• /
• pp.413-421
• /
• 2012

In industry, various rotating machinery such as pumps, gas turbines, compressors, electric motors, generators are being used as an important facility. Due to the industrial development, they make high performance(high-speed, high-pressure). As a result, we need more intelligent and reliable machine condition diagnosis techniques. Diagnosis technique using hidden Markov-model is proposed for an accurate and predictable condition diagnosis of various rotating machines and also has overcame the speed limitation of time/frequency method by using compensation of the rotational speed of rotor. In addition, existing artificial intelligence method needs defect state data for fault detection. hidden Markov model can overcome this limitation by using normal state data alone to detect fault of rotational machinery. Vibration analysis of step-up gearbox for wind turbine was applied to the study to ensure the robustness of diagnostic performance about compensation of the rotational speed. To assure the performance of normal state alone method, hidden Markov model was applied to experimental torque measuring gearbox in this study.

• 보건의료산업학회지
• /
• 제14권1호
• /
• pp.93-102
• /
• 2020

Objectives: This study analyzed the prescription characteristics of medication for acute respiratory diseases before and after pay-for-performance to provide basic data on effective medical quality management policies. Methods: The research data were collected from the 2013-2014 sample cohort of the National Health Insurance Corporation, from Internal Medicine, Pediatrics, Otorhinolaryngology, Family Medicine and General practitioner clinics (classification of disease codes: J00-J06, J20-J22, J40 outpatients). Results: The antibiotics prescription rates decreased from 43.9% in 2013 to 43.5% in 2014 when the major diagnosis was for upper respiratory infections and increased from 62.0% in 2013 to 62.5% in 2014 when the major diagnosis was for lower respiratory infections. Conclusions: There is a need to identify the correct antibiotic prescription method by expanding the current assessment standards. Such standards must include acute lower respiratory infections and minor diagnoses as the current evaluation techniques focus only on the major diagnosis of acute upper respiratory infections.

• 한국멀티미디어학회논문지
• /
• 제25권8호
• /
• pp.1212-1223
• /
• 2022

Skin lesions are common diseases that range from skin rashes to skin cancer, which can lead to death. Note that early diagnosis of skin diseases can be important because early diagnosis of skin diseases considerably can reduce the course of treatment and the harmful effect of the disease. Recently, the development of computer-aided diagnosis (CAD) systems based on artificial intelligence has been actively made for the early diagnosis of skin diseases. In a typical CAD system, the accurate classification of skin lesion types is of great importance for improving the diagnosis performance. Motivated by this, we propose a novel deep ensemble classification with multi-scale attention networks. The proposed deep ensemble networks are jointly trained using a single loss function in an end-to-end manner. In addition, the proposed deep ensemble network is equipped with a multi-scale attention mechanism and segmentation information of the original skin input image, which improves the classification performance. To demonstrate our method, the publicly available human skin disease dataset (HAM 10000) and the private animal skin lesion dataset were used for the evaluation. Experiment results showed that the proposed methods can achieve 97.8% and 81% accuracy on each HAM10000 and animal skin lesion dataset. This research work would be useful for developing a more reliable CAD system which helps doctors early diagnose skin diseases.

• Journal of Biosystems Engineering
• /
• 제36권5호
• /
• pp.319-325
• /
• 2011

This study was conducted to figure out the diagnosis basis of cooling performance depending on water amount in the refrigerant of air conditioner, which can be estimated by the temperatures and pressures along the refrigerant circulation line. A car air conditioner of SONATA III (Hyundai motor Co., Korea) was tested at maximum cooling condition at the engine speed of 1500 rpm in the room controlled at 33~$35^{\circ}C$ air temperature and 55~57% relative humidity conditionally. Measured variables were temperature differences between inlet and outlet pipe surfaces of the compressor, condenser, receive drier and evaporator; and high pressure and low pressure in the refrigerant circulation line; and temperature difference between inlet and outlet air of the cooling vent of evaporator. In this study, changes of the water amount in the refrigerant were correlated to the temperatures and pressure changes and also water amount caused poor cooling performance. As water amount increased in the refrigerant in the air conditioner, the performance of the cooling or the heat transfer became worse. Temporal variations of the surface temperature of the evaporator outlet pipe and the low-side pressure showed various patterns that could estimate the water amount. When the water amount caused bad cooling performance, the patterns of the temperature of the evaporator outlet pipe indicated irregular fluctuation greater than $5^{\circ}C$. When the diagnosis system is using just external sensors of the low-side pressure and the temperatures of inlet and outlet air of cooling vent of the evaporator, the precise pattern of bad cooling performance caused by excess water amount in the cooling line was irregular pressure fluctuation, 25 kPa under 120 kPa, and temperature, $12^{\circ}C$ and less.

• KIEAE Journal
• /
• 제17권4호
• /
• pp.41-48
• /
• 2017

Purpose : Currently, 25% of the domestic energy consumption structure is used as building energy, and more than 18% of this energy is consumed in the residential. Accordingly, various efforts and policies that can save energy of the building is being performed. The various researchers are conducting research to diagnose the thermal performance of existing buildings. This study is to apply in the field of precision thermal insulation performance diagnostic method for thermal performance analysis of existing detached house in Seoul, Gangreung, Gyeongju, Pohang. And this paper is analyzed quantitatively measure the existing detached house energy performance. Method: Research methodology analyzed the thermal performance over the Heat Flow Meter method by applying the measurement process and method by applying the criteria of ISO 9869-1 & ASTR method. In this study, the surface heat transfer coefficient was calibrated by applying indoor surface heat transfer resistance with reference to ISO 6946 standard. The measurement error rate between the HFM diagnosis method and the ASTR diagnosis method was reduced and the measurement reliability was obtained through measurement method error verification. Result : As a result of the study, the thermal performance vulnerable parts of the building were quantitatively analyzed, and presented for methods which can be improved capable of efficient energy use buildings.

• 한국정보과학회논문지:시스템및이론
• /
• 제27권4호
• /
• pp.431-439
• /
• 2000

본 논문에서는 하이퍼큐브 병렬시스템을 진단하기 위한 알고리즘으로써 적응적 큐브 분할 방법을 적용한 진단 알고리즘을 제안한다. Feng[1]등이 제안한 하이퍼큐브 진단 알고리즘은 이전의 연구결과에 비교하여 비교적 적은 진단 비용을 필요로 하는 반면 진단 알고리즘의 수행 중에 나타나는 큐브의 분할이 신드롬의 분석이 없이 정적인 방법을 사용하여 진단함으로써 불필요한 진단 오버헤드를 야기하였다. 본 논문에서는 이를 보완하기 위한 방법으로써 신드롬 분석을 통하여 진단비용을 줄일 수 있는 분할을 선택하는 적응적 큐브 분할방법을 제안한다. 또한 시뮬레이션을 통하여 Feng이 제안한 방법에 비하여 효율적인 성능을 나타내는 것을 보인다.