• Transactions on Control, Automation and Systems Engineering
• /
• v.1 no.1
• /
• pp.54-61
• /
• 1999

FCM(Fuzzy Cognitive Map) is proposed for representing causal reasoning. Its structure allows systematic causal reasoning through a forward inference. By using the FCM, authors have proposed FCM-based fault diagnostic algorithm. However, it can offer multiple interpretations for a single fault. In process engineering, as experience accumulated, some form of quantitative process knowledge is available. If this information can be integrated into the FCM-based fault diagnosis, the diagnostic resolution can be further improved. The purpose of this paper is to propose an enhanced FCM-based fault diagnostic scheme. Firstly, the membership function of fuzzy set theory is used to integrate quantitative knowledge into the FCM-based diagnostic scheme. Secondly, modified TAM recall procedure is proposed. Considering that the integration of quantitative knowledge into FCM-based diagnosis requires a great deal of engineering efforts, thirdly, an automated procedure for fusing the quantitative knowledge into FCM-based diagnosis is proposed by utilizing self-learning feature of neural network. Finally, the proposed diagnostic scheme has been tested by simulation on the two-tank system.

• Journal of the Korean Society of Manufacturing Process Engineers
• /
• v.4 no.3
• /
• pp.57-62
• /
• 2005

Neural networks, which have learning and self-organizing abilities, can be advantageously used in the pattern recognition. Neural network techniques have been widely used in monitoring and diagnosis, and compare favourable with traditional statistical pattern recognition algorithms, heuristic rule-based approaches, and fuzzy logic approaches. In this study the fault diagnosis of the face-milling using the artificial neural network was investigated. After training, the sample which measure load current was monitored by constant output results.

• Journal of information and communication convergence engineering
• /
• v.17 no.2
• /
• pp.128-134
• /
• 2019

Based on the concept of Industry 4.0, various sensors are attached to facilities and equipment to collect data in real time and diagnose faults using analyzing techniques. Diagnostic technology continuously monitors faults or performance degradation of facilities and equipment in operation and diagnoses abnormal symptoms to ensure safety and availability through maintenance before failure occurs. In this paper, we propose a model to analyze the data and diagnose the state or failure using machine learning. The diagnosis model is based on a support vector machine (SVM)-based diagnosis model and a self-learning one-class SVM-based diagnostic model. In the future, it is expected that this model can be applied to facilities used in the entire industry by applying the actual data to the diagnostic model proposed in this paper, conducting the experiment, and verifying it through the model performance evaluation index.

• Structural Engineering and Mechanics
• /
• v.17 no.3_4
• /
• pp.347-356
• /
• 2004

In order to extend the lifetime of buildings and civil infrastructure, patch type fibrous composite retrofitting materials are widely used. Retrofitted concrete columns and beams gain stiffness and strength, but lose toughness and show brittle failure. Usually, the cracks in concrete structures are visible to the naked eye and the status of the structure in the life cycle is estimated through visual inspections. After retrofitting of the structure, crack visibility is blocked by retrofitted composite materials. Therefore, structural monitoring after retrofitting is indispensable and self diagnosis method with optical fiber sensors is very useful. In this paper, we try to detect the peel out effect and find the strain difference between the main structure and retrofitting patch material when they separate from each other. In the experiment, two fiber optic Bragg grating sensors are applied to the main concrete structure and the patching material separately at the same position. The sensors show coincident behaviors at the initial loading, but different behaviors after a certain load. The test results show the possibility of optical fiber sensor monitoring of beam structures retrofitted by the composite patches.

• Proceedings of the KIEE Conference
• /
• 2005.10b
• /
• pp.264-266
• /
• 2005

Recently, on-line diagnosis methods through wired and wireless networks are widely adopted in the diagnosis of industrial Electric Facilities, such as generators, transformers and motors. Also smart sensors which includes sensors, signal conditioning circuits and micro-controller in one board are widely studied in the field of condition monitoring. This paper suggests an self-powered system suitable for condition-monitoring smart sensors, which uses parasitic vibrations of the facilities as energy source. First, vibration-driven noise patterns of the electric facilities are presented. And then, an electromagnetic generator which uses mechanical mass-spring vibration resonance are suggested and designed. Finally energy consumption of the presented smart sensor, which consists of MEMS vibration sensors, signal conditioning circuits, a low-power consumption micro-controller, and a ZIGBEE wireless tranceiver, are presented. The usefulness and limits of the presented electromagnetic generators in the field of electric facility monitoring are also suggested.

• Journal of Yeungnam Medical Science
• /
• v.39 no.2
• /
• pp.81-88
• /
• 2022

Vertigo is the sensation of self-motion of the head or body when no self-motion is occurring or the sensation of distorted self-motion during an otherwise normal head movement. Representative peripheral vertigo disorders include benign paroxysmal positional vertigo, Ménière disease, and vestibular neuritis. Vestibular neuritis, also known as vestibular neuronitis, is the third most common peripheral vestibular disorder after benign paroxysmal positional vertigo and Ménière disease. The cause of vestibular neuritis remains unclear. However, a viral infection of the vestibular nerve or ischemia of the anterior vestibular artery is known to cause vestibular neuritis. In addition, recent studies on immune-mediated mechanisms as the cause of vestibular neuritis have been reported. The characteristic clinical features of vestibular neuritis are abrupt true-whirling vertigo lasting for more than 24 hours, and no presence of cochlear symptoms and other neurological symptoms and signs. To accurately diagnose vestibular neuritis, various diagnostic tests such as the head impulse test, bithermal caloric test, and vestibular-evoked myogenic potential test are conducted. Various treatments for vestibular neuritis have been reported, which are largely divided into symptomatic therapy, specific drug therapy, and vestibular rehabilitation therapy. Symptomatic therapies include generalized supportive care and administration of vestibular suppressants and antiemetics. Specific drug therapies include steroid therapy, antiviral therapy, and vasodilator therapy. Vestibular rehabilitation therapies include generalized vestibular and customized vestibular exercises.

• 전기의세계
• /
• v.43 no.6
• /
• pp.19-26
• /
• 1994

본 고에서는 고속철도에 사용된 자기진단기술의 특성 및 요소기술을 설명하고 프랑스 TGV의 차량용 On board 자기진단시스템의 기능과 열차제어 및 신호시스템에 적용된 자기진단 기능을 소개함으로써 관련 기술의 이해를 돕고자 한다.

• Journal of information and communication convergence engineering
• /
• v.6 no.2
• /
• pp.207-212
• /
• 2008

There are several sensors in the liquid cargo ship. In the liquid cargo ship, we can get values from various sensors that are level sensor, temperature sensor, pressure sensor, oxygen sensor, VOCs sensor, high overfill sensor, etc. It is important to guarantee the reliability of sensors. In order to guarantee the reliability of sensors, we have to study the diagnosis of sensor fault. The technology of smart sensor is widely used. In this paper, the technology of smart sensor is applied to diagnosis of level sensor fault for liquid cargo ship. In order to diagnose sensor fault and find the sensor position, in this paper, we proposed algorithms of diagnosis of sensor fault using independent sensor diagnosis unit and self fault diagnosis using sensor modeling. Proposed methods are demonstrated by experiment and simulation. The results show that the proposed approach is useful. Proposed methods are useful to develop smart level sensor.

• Fashion & Textile Research Journal
• /
• v.16 no.2
• /
• pp.218-227
• /
• 2014

In this study, we ran a collage fashion illustration program. We used in depth personal interviews to find if there are any change in self-image by psychologically analyzing the features of self-images expressed in the pieces of fashion illustration. The total number of objects were five females students majoring in fashion design in Busan. They were hoping to have a psychology consultation to resolve their concerns about the future, family affairs, appearance, and careers. Collage fashion illustration program was used as a experimental tool to find the psychological features shown in the formats and content of collage fashion illustration. We then figure out how pre and post diagnosis were different from each other in terms of ego-identity and DAP. As a result, the formats in collage fashion illustration are related to the self images such as psychological energy, incompetency, suppression, and tendency of self-centered. Also, the contents of the fashion expression are related to the self-images such as dependency, avoidance, wariness, and self-regard. All of the participants have improved self-regard and active action due to improvements in subjectivity, initiative, and goal orientation. Therefore, they could change from pessimistic self-images to optimistic ones.

• The Korean Journal of Health Service Management
• /
• v.10 no.3
• /
• pp.51-61
• /
• 2016

Objectives : The purpose of this study was to find factors influencing compliance with the national cancer screening program in middle-aged men. Methods : The data were collected from July 28, to October 31, 2015. Total subjects were 615 middle-aged men living in Busan. Results : The Rate of compliance with the NCSP(National Cancer Screening Program) for middle-aged men was 52.2%. There were significant differences in the compliance with the NCSP for the following barrier of exam(${\chi}^2=7.327$, p=.007), self-efficacy(${\chi}^2=23.074$, p<.001), age(${\chi}^2=38.823$, p<.001), marital status(${\chi}^2=19.012$, p<.001), cancer diagnosis in family(${\chi}^2=7.615$, p=.006), smoking(${\chi}^2=9.012$, p=.011), drinking(${\chi}^2=7.073$, p=.008), exercise(${\chi}^2=14.615$, <.001). Factors influencing the rate of compliance for the NCSP in middle-aged men were self-efficacy, age, marital status, exercise, and cancer diagnosis in family. Conclusion: To increase the rate of compliance to the NCSP in middle-aged men it is necessary to elevate the self-efficacy. Additional more positive support needed in men who are younger have no cancer diagnosis in their family are smokers and not m married encourage and improvve paticipation in the examination.