• KEPCO Journal on Electric Power and Energy
• /
• 제4권2호
• /
• pp.89-99
• /
• 2018

Downtime and malfunction of industrial rotor machines represents a crucial cost burden and productivity loss. Fault diagnosis of this equipment has recently been carried out to detect their fault(s) and cause(s) by using fault classification methods. However, these methods are of limited use in detecting rotor faults because of their hypersensitivity to unexpected and different equipment conditions individually. These limitations tend to affect the accuracy of fault classification since fault-related features calculated from vibration signal are moved to other regions or changed. To improve the limited diagnosis accuracy of existing methods, we propose a new approach for fault diagnosis of rotor machines based on the model generated by supervised learning. Our work is based on feature residual values from vibration signals as fault indices. Our diagnostic model is a robust and flexible process that, once learned from historical data only one time, allows it to apply to different target systems without optimization of algorithms. The performance of the proposed method was evaluated by comparing its results with conventional methods for fault diagnosis of rotor machines. The experimental results show that the proposed method can be used to achieve better fault diagnosis, even when applied to systems with different normal-state signals, scales, and structures, without tuning or the use of a complementary algorithm. The effectiveness of the method was assessed by simulation using various rotor machine models.

• 대한수의학회지
• /
• 제34권1호
• /
• pp.173-180
• /
• 1994

Milk progesterone concentrations were measured in 111 dairy cows for confirming the estrus observation and for the early pregnancy diagnosis. Of the 56 cows inseminated, 52 cows(92.8%) were an ovulatory estrus, 2 cows(3.6%) were an unovulatory estrus, and 2 cows(3.6%) were the error of estrus observation, respectively. Milk progesterone concentrations at 21 and 24 days after artificial insemination were significantly higher in 23 pregnant cows compared with those in 5 non-pregnant cows(P<0.05). The accuracy rate for early pregnancy diagnosis in 27 cows achieved when the discriminatory concentration at 21 days after artificial insemination was placed at 2.0 ng/ml skim milk, was 91.3% for positive diagnosis and 100% for negative diagnosis, respectively. These results indicated that milk progesterone determination at 0, 6 and 21 days after artificial insemination can be utilized for confirming the estrus observation and for early pregnancy diagnosis. In conclusion, milk progesterone determination is useful diagnostic tool for monitoring the reproductive performance.

• 대한영양사협회학술지
• /
• 제22권1호
• /
• pp.26-40
• /
• 2016

This study aimed to compare perception of job importance, job performance, and job difficulty between clinical dietitians working at small and medium hospitals in Busan. The survey was conducted from July 15 to August 31, 2014, and data were analyzed using the SPSS program. The mean scores for perception of job importance, job performance, and job difficulty of clinical dietitian's task elements were 3.88, 2.87, and 3.18 out of 5.0, respectively. Perception of job importance had a positive relationship with job performance. However, job performance showed a negative relationship with job difficulty. There were strong positive relationships among nutrition assessment, nutrition diagnosis, nutrition intervention, nutrition monitoring & evaluation, nutrition research in perception of job importance (P<0.05, P<0.01). Nutrition assessment, nutrition diagnosis, nutrition intervention, and nutrition research showed positive relationships with job performance (P<0.05, P<0.01). There was also a positive relationship among clinical dietitian's task with job difficulty (P<0.05, P<0.01). These results suggest that it would be effective to adopt training programs for appropriate nutrition service and to provide continuous education programs for professional development.

• Nuclear Engineering and Technology
• /
• 제47권2호
• /
• pp.176-186
• /
• 2015

Pattern classifications have become important tools for fault diagnosis in nuclear power plants (NPP). However, it is often difficult to obtain training data under fault conditions to train a supervised classification model. By contrast, normal plant operating data can be easily made available through increased deployment of supervisory, control, and data acquisition systems. Such data can also be used to train classification models to improve the performance of fault diagnosis scheme. In this paper, a fault diagnosis scheme based on semisupervised classification (SSC) scheme is developed. In this scheme, new measurements collected from the plant are integrated with data observed under fault conditions to train the SSC models. The trained models are subsequently applied to new measurements for fault diagnosis. In comparison with supervised classifiers, the proposed scheme requires significantly fewer data collected under fault conditions to train the classifier. The developed scheme has been validated using different fault scenarios on a desktop NPP simulator as well as on a physical NPP simulator using a graph-based SSC algorithm. All the considered faults have been successfully diagnosed. The results have demonstrated that SSC is a promising tool for fault diagnosis in NPPs.

• 한국철도학회:학술대회논문집
• /
• 한국철도학회 2005년도 추계학술대회 논문집
• /
• pp.332-337
• /
• 2005

In order to investigate performance changes, the acceleration, vibration, and braking performance tests were carried out on the electric multiple units (EMUs) with over 20 years operation. According to the testing results, in vibration and braking performance, the similar performance results were obtained as compared with newly manufactured EMUs. However, in terms of acceleration performance, below reference value (3.0 km/h/s) has been obtained. This is mainly due to performance deterioration including traction motor. The precision diagnosis evaluation of deteriorated EMUs will be provided through the overall evaluation of corrosion testing and structural performance of car body.

• 동의생리병리학회지
• /
• 제23권6호
• /
• pp.1221-1225
• /
• 2009

The pulse diagnosis is an important and universally used method in Oriental Medicine. Since the traditional method of palpating the pulse relies on the subjective sense in the fingers of an Oriental Medical Doctor(OMD), there has been continued need for more objective method for pulse diagnosis. Recently, various pulse analyzers have been developed to meet such objective palpation and interpretation. However, most of these attempts were not successful to replace OMD's own palpation by fingers. To improve the performance of the pulse analyzers, one should develop machine-appropriate interpretations for the pulse images in the literature, in addition to the improvement in the repeatability and reproducibility. One of such widely-used pulse images to be interpreted is the floating and sinking pulse. The floating and sinking pulses are the two representative pulse images informing us how strong pressure one should apply to obtain the maximal pulse strength. A previous study suggested a convenient and unified measure for the floating and sinking pulses by defining the coefficient of the floating-sinking pulse(CFS). We found the original definition of the CFS could be erroneous under some situations. To improve the performance, we introduce new CFS algorithm for determining the floating and sinking pulse with a pulse analyzers(3-D MAC). To test the performance of the newly suggested algorithm, we conducted a clinical study comparing the agreement ratio with the floating and sinking pulse diagnosis by the OMDs. We found that, among the subjects who are diagnosed with having either the floating pulse or sinking pulse, the new CFS algorithm showed 55.3% diagnosis rate and 73.0% concordance rate, which are about 3% and 6% improvement in the diagnosis rate and agreement rate, respectively, compared to the original CFS algorithm.

• PNF and Movement
• /
• 제8권1호
• /
• pp.41-50
• /
• 2010

Pain originating from the sacroiliac joint(SIJ) has been associated with poor performance, yet specific diagnosis of sacroiliac dysfunction(SID) has been difficult to achieve. Clinical presentation of SID appears that pain and poor performance is responsive to local analgesia of periarticular structures with poorly defined pathology, and poor performance with bony pathological changes present as a result of chronic instability. Previous research indicates that physical examination cannot diagnose SIJ pathology. Earlier studies have not reported sensitivities and specificities of composites of provocation tests known to have acceptable inter-examiner reliability. Tests based on mechanics as manual provocation for SIJ pain have formed the basis of tests used to diagnose SIJ dysfunction. In this review summary, the purpose of this study was to describe the sacroiliac tests with a model of examination, diagnosis, and management of SID. Further research is warranted to determine whether SIJ tests is reliable means of evaluating innominate impairments.

• 동의생리병리학회지
• /
• 제28권6호
• /
• pp.662-667
• /
• 2014

The purpose of this clinical study is to develop structured clinical trial protocol and guideline for improvement of safety, useful and effective of pulse diagnosis devices. As a first step, papers on pulse diagnosis and pulse diagnosis devices from 2001 and 2013 were systematically reviewed. In the next step, we have collected the opinions from the specialists, companies, and statistician in pulse diagnosis to evaluate the current condition, the state and problem of domestic clinical trial cases of pulse diagnosis device. And we have to created protocol and case report form (CRF) in regards to site condition and characteristics of pulse diagnosis devices, and showed the guideline of eligibility criteria, operation process, investigation items, evaluation items and so on. This clinical protocol will become a basic information for a researcher in designing or performing a clinical study of pulse diagnosis devices, and be used as a useful material during acquisition of good clinical data. Furthermore, we hope to enhance the invigoration of pulse diagnosis clinical trials and the performance improvement of pulse diagnosis devices.

• 한국정보과학회논문지:정보통신
• /
• 제31권3호
• /
• pp.335-346
• /
• 2004

본 논문에서는 편향 자기 경로 제어 방법을 사용하는 새로운 고성능 고장 감내 스위칭 망을 제시하고, 이 스위칭 망의 고장 진단 방법을 제안한다. 우리는 기본 스위치인 벤얀 망의 각 스위칭 단계들이 하나의 순환 군의 나열로 구성되어 있다는 사실과 자기 경로제어 관점에서 인접한 스위칭 단계들 간에 준동형(Homomorphism)이 존재하기 때문에, 모든 각 단계의 순환 군이 이 다음 단계의 부분군이고, 이들 단계들로 구성된 펙터 군이 존재한다는 성질과 사용하여, 결함이 생긴 링크들을 우회하는 대체 경로들로 추가한 링크들을 포함하는 모든 링크들을 사용하는 확장 벤얀 망인 다단 스위칭 망을 제시한다. 그리고 이 망의 성능을 시뮬레이션을 통해서 분석하여, 성능의 우수함을 보인다. 또한 이들 다중 경로를 제공하는 스위칭 망을 사용하는데 필수적인 결함 진단법을 제시한다.

• 문화기술의 융합
• /
• 제10권2호
• /
• pp.511-516
• /
• 2024

최근 제정된 궤도시설의 성능평가에 관한 세부지침에서 궤도성능평가의 평가절차 및 실시방법 등에 관한 필요사항을 제시하였다. 그러나 외관조사(육안조사)에 의해 레일표면손상의 등급이 결정되며, 점검자의 주관적인 판단으로 정성적인 평가에만 의존할 수밖에 없는 실정이다. 따라서 본 연구에서는 레일표면손상을 이용하여 레일내부결함까지 진단할 수 있는 진단애플리케이션을 개발하고자 하였다. 현장조사에서는 레일표면손상을 조사하고 패턴을 분석하였다. 또한 실내시험에서는 레일내부손상 이미지 데이터를 구축하기 위하여 SEM 시험을 이용하였으며, 균열 길이, 깊이 및 각도를 정량화하였다. 본 연구에서는 현장조사와 실내시험에서 구축한 이미지 데이터를 적용한 딥러닝 모델(Fast R-CNN)을 애플리케이션에 적용하였다, 스마트기기에서 사용이 가능한 딥러닝 모델을 이용한 레일표면손상 진단 애플리케이션(App)을 개발하여 향후 궤도진단 및 성능평가 업무에 활용 가능한 레일표면손상 스마트 진단시스템을 개발하였다.