• Journal of the Korea Convergence Society
• /
• v.10 no.11
• /
• pp.79-84
• /
• 2019

Video image based technology is being used in various fields with continuous development. The demand for vision system technology that analyzes and discriminates image objects acquired through cameras is rapidly increasing. Image processing is one of the core technologies of vision systems, and is used for defect inspection in the semiconductor manufacturing field, object recognition inspection such as the number of tire surfaces and symbols. In addition, research into license plate recognition is ongoing, and it is necessary to recognize objects quickly and accurately. In this paper, propose a recognition model through the rotational alignment of objects after checking the angle value of the tilt of the object in the input video image for the recognition of inclined objects such as numbers or symbols marked on the surface. The proposed model can perform object recognition of the rotationally sorted image after extracting the object region and calculating the angle of the object based on the contour algorithm. The proposed model extracts the object region based on the contour algorithm, calculates the angle of the object, and then performs object recognition on the rotationally aligned image. In future research, it is necessary to study template matching through machine learning.

• Transactions of the Korean Society for Noise and Vibration Engineering
• /
• v.12 no.4
• /
• pp.287-293
• /
• 2002

The unexpected failure of the induction motor makes the downtime of production, and the cost of the process cessation enormous. To reduce the downtime and increase the reliability of the motor, the vibration measurements for the fault detection have been used previously. Recently motor current signature analysis(MCSA) has been adapted for the fault detection and diagnosis of the motors. MCSA provides a powerful analysis tool for detecting the presence of mechanical and electrical faults in both the motor and driven equipment. In this paper, the fault severity of the rotor bar has been derived in terms of the resistance change which is calculated from the equivalent circuit model. Results show that the fault of the rotor can be easily detected and the measured value of the resistance change is verified by the detected fault from on-site tests using MCSA for the induction motors in an iron foundry.

• 한국신재생에너지학회:학술대회논문집
• /
• 2007.11a
• /
• pp.391-394
• /
• 2007

Wind turbine gearbox is a complex mechanical system that includes gear trains, shafts, bearings, and gearbox housings. All these components are interacting with each other therefore it is important to assess the whole performance by considering the individual component design. In this paper, the performance assessment of 2MW wind turbine gearbox was conducted under various operating conditions at test bench and test result was compared with the design calculation.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2001.11a
• /
• pp.79-84
• /
• 2001

The motivation behind this work is to understand the phenomenon of friction-induced vibration and squeal due to misalignment. In present paper, it is studied on effect of misalignment between friction-induced vibration and squeal by an experiment using a pin-on-disk type experimental apparatus. In order to build an analytical model of the friction-induced vibration system with misalignment, the system is modeled as a single-DOF and 3-DOF system. The results show that the single DOF system can only show stick／slip phenomenon, but the 3-DOF system can show squeal due to misalignment. Consequently, it can be said that the misalignment in a friction-induced vibration system is a source of squeal noise.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2012.04a
• /
• pp.99-104
• /
• 2012

This paper analyzes the pitting's cause of elevator's worm gear type traction machine. To find a cause of pitting problem, we analyzed vibration, a proper design allowance and lubrication. We brought a conclusion that the cause of pitting is not a simple vibration problem, such as misalignment of worm reducer and rail, but mostly related to a designed allowance. In this case, the allowance is tight. In general, the allowance of traction machine and lubrication is varied by manufacturers. When the allowance is tight, a proper lubrication can diminish the pitting problem.

• Transactions of the Korean Society for Noise and Vibration Engineering
• /
• v.16 no.4 s.109
• /
• pp.366-371
• /
• 2006

As functional requirements of automatic office machines like printers, Automatic Tellex Machines(ATMs), copying machines are on a trend for the higher speed and precision, extensive technical advances are being developed and implemented in the industry. Media transport system is a device to convey a sheet of paper in ATMs and printers. The stability of media transport system is a matter of concern as their operating throughput rapidly increases. And defects of belts or rollers in a transport system directly affect the level of stability of the system. Therefore an automatic diagnostic system for predicting various defects is necessary for the stable operation of the media transport system. A simulation based on multi-body dynamics has been done for a feasibility study of a system design for the defect anticipation.

• Proceedings of the Korean Society For Composite Materials Conference
• /
• 2004.04a
• /
• pp.79-82
• /
• 2004

The rotor drive system in rotor-craft carries out power transmission from powerplant to rotors and the drive shafts are fallen into misaligned condition by the vibration of engine and shafts and the deformation of supporting structures. The high performance flexible coupling accommodates these misalignments of drive shafts. In this study, we compare the performance of the metalic flexible coupling with the composite flexible coupling through analytic method to develop the high performance flexible coupling used in the rotor drive system of UAV tilt-rotor.

• 유체기계공업학회:학술대회논문집
• /
• 1999.12a
• /
• pp.317-323
• /
• 1999

The necessity of diagnosis of the rotating machinery which is widely used in the industry is increasing. Many research has been conducted to manipulate field vibration signal data for diagnosing the fault of designated machinery. As the pattern recognition tool of that signal, neural network which use usually back-propagation algorithm was used in the diagnosis of rotating machinery. In this paper, self-organizing feature map(SOFM) which is unsupervised learning algorithm is used in the abnormal vibration diagnosis of rotating machinery and then learning vector quantization(LVQ) which is supervised teaming algorithm is used to improve the quality of the classifier decision regions.

• 한국신재생에너지학회:학술대회논문집
• /
• 2006.06a
• /
• pp.249-252
• /
• 2006

Wind turbine gearbox is a complex mechanical system that includes gear trains, shafts, bearings, and gearbox housings. All these component are interacting with each other therefore changing certain design parameter will affect other components. RomaxDesigner enables a reduction in development period by simulating the full gearbox system. The gear pairs, bearings and shafts are represented as analysis objects and the complex components are modelled by means of reduced stiffness matrices. The software allows durability analysis and advanced contact analysis including the effects of system misalignments in gear and bearing. In this paper the 2MW wind turbine gearbox was model led and a study on optimum design was conducted

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.31 no.6
• /
• pp.1127-1136
• /
• 2021

In the field of power analysis attacks, electrical noise and misalignment of the power consumption trace are the major factors that determine the success of the attack. Therefore, several studies have been conducted to overcome this problem, and one of them is a signal processing method based on wavelet transform. Up to now, discrete wavelet transform, which can compress the trace, has been mostly used for power side-channel power analysis because continuous wavelet transform techniques increase data size and analysis time, and there is no efficient scale selection method. In this paper, we propose an efficient scale selection method optimized for power analysis attacks. Furthermore, we show that the analysis performance can be greatly improved when using the proposed method. As a result of the CPA(Correlation Power Analysis) and DDLA(Differential Deep Learning Analysis) experiments, which are non-profiling attacks, we confirmed that the proposed method is effective for noise reduction and trace alignment.