• Journal of Electrical Engineering and Technology
• /
• v.10 no.4
• /
• pp.1558-1565
• /
• 2015

In this paper, we propose a new method for detecting bearing faults using vibration signals. The proposed method is based on support vector machines (SVMs), which treat the harmonics of fault-related frequencies from vibration signals as fault indices. Using SVMs, the cross-validations are used for a training process, and a two-stage classification process is used for detecting bearing faults and their status. The proposed approach is applied to outer-race bearing fault detection in three-phase squirrel-cage induction motors. The experimental results show that the proposed method can effectively identify the bearing faults and their status, hence improving the accuracy of fault diagnosis.

• Journal of Welding and Joining
• /
• v.15 no.1
• /
• pp.81-91
• /
• 1997

In this study, a magnetic sensor to make use of eddy current was developed to detect the weld seam of butt joint in the sheet metal arc welding. This system consist of the sensor device for detecting the weld line, the servo control device for driving the weld torch movement and the control unit. A signal processing was applied to smooth the output signal of the sensor. The weld joint was determined by using a 1st order differential method. To improve tracking accuracy of the system, moving average method which has an effect of proportional and weighted integral control was applied to a series of the weld joint positions obtained above. The weld line for tracking was generated by using data regeneration algorithm. Based on these results, each servo motor was controlled by pulse generator. From experimental results, it was revealed that this system has excellent detecting ability for weld line and seam tracking ability.

• Journal of Institute of Control, Robotics and Systems
• /
• v.16 no.12
• /
• pp.1143-1149
• /
• 2010

Because the noise is the main cause for decreasing the performance at speech recognition, the place or environment is very important in speech recognition. To improve the speech recognition performance in the real situations where various extraneous noises are abundant, a novel combination of FIR and Wiener filters is proposed and experimented. The combination resulted in improved accuracy and reduced processing time, enabling fast analysis and response in emergency situations. Usually, there are many dangerous situations in our city life, so for the smarter city it is necessary to detect many types of sound in various environment. Therefore this paper is about how to detect many types of sound in real city, especially on CCTV. This paper is for implementing the smarter city by detecting many types of sounds and filtering one of the emergency sound in this sound stream. And then it can be possible to handle with the emergency or dangerous situation.

• Proceedings of the KIEE Conference
• /
• 2001.11c
• /
• pp.365-368
• /
• 2001

This work describes a real-time method, based on motion energy detection, for detecting and tracking moving object in the consecutive image sequences. The motion of moving objects is detected by taking the difference of the two consecutive image frames. In addition an edge information of the current image is utilized in order to further increase the accuracy of detection. We can track the moving objects continuously by detecting the motion of objects from the sequence of image frames. A prototype system has been implemented using a TI TMS320C6201 EVM fixed-point DSP board, which can successfully track a moving human in real-time.

• Journal of Institute of Control, Robotics and Systems
• /
• v.12 no.7
• /
• pp.650-657
• /
• 2006

The LPMS (Loose Part Monitoring Systems) are used widely for detecting the impact position in the nuclear reactor. There are some major methods to detect impact position in LPMS such as the triangular method, the rectangular method, the circular intersection method and so on. The time difference of these methods are calculated using S0-mode and A0-mode waves of each sensor. In this paper, we propose a method to detect impact position using the enveloped waves of acquired signals. The result of this paper show that the position detecting accuracy and reducing the processing time are proposed method is improved than traditional methods.

• Journal of the Korean Society for Precision Engineering
• /
• v.16 no.10
• /
• pp.203-208
• /
• 1999

By tilting the reference mirror of Twynman-Green interferometer having a reference mirror and a moving mirror, firinge pattern composed of bright and dark parallel lines can be obtained and the fringe pattern is shifted according to the displacement of the mowing mirror. Several studies are executed for displacement measurement by detecting the intensity of the fringe with photo-diodes having small detecting area. In this study, to improve the sensitivity and robustness, the intensity of fringe is detected by using a large-area quadratic photo-diode masked with a grating panel having four kinds of binary grating having phase-difference of 0, {\pi}$/4, {\pi}$/2, 3 {\pi}$/4. The phase of the fringe is calculated with a simple 4-buckets algorithm. A experimental result shows that standard deviation of 5.653 nm is obtained comparing with a capacitive type gap sensor having nearly 1 nm accuracy.

• Journal of Institute of Control, Robotics and Systems
• /
• v.22 no.4
• /
• pp.266-270
• /
• 2016

In this paper, we propose a technique of drowsiness detection using machine vision. The drowsiness of vehicle driver is often the primary cause of motor vehicle accidents. Therefore, the checking of eye images for detecting drowsiness status of driver is critical for preventing these accidents. In our suggested method, we analyze the changes of histogram and edge of eye region images which are acquired using CCD camera. We developed a drowsiness detection system using the histogram and edge change information. The experimental results show that our proposed method enhances the accuracy of detecting drowsiness nearly to 98%, and can be used for preventing vehicle accidents due to the drowsiness of drivers.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.20 no.2
• /
• pp.171-181
• /
• 2002

As the result of the analysis of the underground utility map made before, we could have divided the kind of errors into the two types, position error of geometric data and attribute error and knew the fact that mainly position error is derived from the process of detecting and surveying the underground utility, and attribute is inputting data. In this study we showed the way improving accuracy in detecting and surveying underground utility by field test, and the way to reduce attribute error by process refinement.

• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.30 no.1
• /
• pp.49-54
• /
• 2016

There is needed the quard channel triple wave lengths pyroelectric infrared flame detector to recognize the unique characteristics of fire sources in various type. This system detects the triple wave lengths of infrared flame emitting maximum radient energy and scattering frequency of flame. The quard channel infrared flame detector detects the duplicate wave lengths of maximum radient energy to enhance the accuracy of detecting fire. Especially this paper focuss on development of the self diagnosis function system including contamination, temperature and input voltage. Therefore, the prevention and early suppression of fire is available.

• 한국정보통신설비학회:학술대회논문집
• /
• 2008.08a
• /
• pp.181-185
• /
• 2008

Recently, location based service(LBS) expended based on personal specialized service, however since commercialized GPS based emergency rescue service comes with shadow zone for GPS signal such as inside building, the accuracy and reliability are not guaranteed. Therefore to improve such problem, we propose an active location detecting algorithm using RFID-TAG and Yagiantenna. To track the location of RFID-TAG where signal is generated, location tracking device in which Yagi-Antenna is installed moves around. Since directed wave and reflected wave co-exist during signal reception, final signal generated location is searched by setting up multiple of locations where signal can be generated on the map and moving location tracking device along minimum length of path. The algorithm proposed in this paper was verified of its technical validity through simulator.