• KEPCO Journal on Electric Power and Energy
• /
• v.4 no.2
• /
• 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.

• Korean Journal of Veterinary Research
• /
• v.34 no.1
• /
• 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.

• Journal of the Korean Dietetic Association
• /
• v.22 no.1
• /
• 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
• /
• v.47 no.2
• /
• 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.

• Proceedings of the KSR Conference
• /
• 2005.11a
• /
• 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.

• Journal of Physiology & Pathology in Korean Medicine
• /
• v.23 no.6
• /
• 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
• /
• v.8 no.1
• /
• 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.

• Journal of Physiology & Pathology in Korean Medicine
• /
• v.28 no.6
• /
• 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.

• Journal of KIISE:Information Networking
• /
• v.31 no.3
• /
• pp.335-346
• /
• 2004

In this paper, we present a high-performance fault-tolerant switching networks using a deflection self-routing scheme, and present fault-diagnosis method for the network. We use the facts: 1) Each stage of the Banyan network is arrayed as the sequences of a Cyclic group of SEs. 2) There is the homomorphism between adjacent stages from a view of self-routing, so that all of each Cyclic group is the subgroup of the Cyclic group in the next stage, and there are factor groups due to such subgroup and homomorphism. We provide high-performance fault-tolerant switching networks of which the all links including augmented links are used as the alternate links detouring faulty links. We also present the fault diagnosis scheme for the proposed switching network that provide multiple paths for each input-output pair.

• The Journal of the Convergence on Culture Technology
• /
• v.10 no.2
• /
• pp.511-516
• /
• 2024

The recently enacted detailed guidelines on the performance evaluation of track facilities presented the necessary requirements regarding the evaluation procedures and implementation methods of track performance evaluation. However, the grade of rail surface damage is determined by external inspection (visual inspection), and there is no choice but to rely only on qualitative evaluation based on the subjective judgment of the inspector. Therefore, in this study, we attempted to develop a diagnostic application that can diagnose rail internal defects using rail surface damage. In the field investigation, rail surface damage was investigated and patterns were analyzed. Additionally, in the indoor test, SEM testing was used to construct image data of rail internal damage, and crack length, depth, and angle were quantified. In this study, a deep learning model (Fast R-CNN) using image data constructed from field surveys and indoor tests was applied to the application. A rail surface damage diagnosis application (App) using a deep learning model that can be used on smart devices was developed. We developed a smart diagnosis system for rail surface damage that can be used in future track diagnosis and performance evaluation work.