• 제어로봇시스템학회논문지
• /
• 제4권3호
• /
• pp.372-377
• /
• 1998

This paper deals with the detection, feature extraction and classification of surface defects in cold rolled strips. Inspection systems are one of the most important fields in factory automation. Defects such as slipmark and dullmark can be effectively detected with a Gaussian matched filter because their shapes are similar to Gaussian. It is justified that the proposed WF(Wavelet Frame) method could be regarded as multiscale Gaussian matched filter which can be applied to the inspection of cold rolled strip. After a wavelet frame transform, the entropies and moments are computed for each subband which pass through both local low pass filter and nonlinear operator. With these features as input, a MLP(Multi Layer Perceptron) is used as a classifier. The proposed inspection method was applied to the real images with defects, and hence showed good performance. The role of each extracted feature is analyzed by KLT(Karhunen-Loeve Transform).

• 한국정밀공학회지
• /
• 제32권7호
• /
• pp.619-625
• /
• 2015

There is a large interest to find reliable and automatic methods for crack detection and quantification in the railway bogie frame. The non-destructive inspection of railway bogie frame has been performed by ultrasonic and magnetic particle testing in general inspection. The magnetic particle method has been utilized in the defect inspection of the bogie frame but the grinding process is required before inspection and the dust is developed resulting from the processing. The objective of this paper is to apply the inspection method of bogie frame using infra-red thermography. The infra-red thermography system using the excitation of eddy current was performed for the defect evaluation of weld specimen inserted artificial defects. The result shows that the infra-red thermography method can detect the surface and inner defects in weld specimen for bogie frame.

• 한국정보통신학회:학술대회논문집
• /
• 한국해양정보통신학회 2010년도 춘계학술대회
• /
• pp.574-576
• /
• 2010

본 논문에서는 CCD 카메라를 이용해 리드프레임의 내부 리드부의 넓이와 선명도 및 결함 등을 고속으로 검사하는 시스템을 개발한다. 본 시스템은 조명부, 검사부, 조명 제어부, GUI 등으로 구성된다. 개발 기술로는 조명 제어, 고속 검사 알고리즘, 검사 분해능을 올리기 위한 계측기술 등이다. 현장 실험을 통해 개발된 시스템의 유효성을 검증한다.

• 한국산학기술학회논문지
• /
• 제12권4호
• /
• pp.1559-1564
• /
• 2011

본 논문에서는 생산 현장에서 작업자가 육안으로 하고 있는 자동차 부품 카시트 프레임의 전수(全數) 검사를 위한 머신 비전 시스템의 개발에 관한 연구를 다룬다. 이러한 제안된 머신비전 검사시스템은 생산 현장에서 날로 증가하는 품질 향상에 대한 요구와 수요를 충족시키기 위해 설계되었다. 이 컴퓨터 기반의 검사시스템은 실시간으로 제품의 다양한 결함들에 대한 품질 검사를 할 수 있도록 설계되었다. 본 연구의 검사방법에 사용된 소프트웨어는 NI-LabVIEW가 사용하였으며, LabVIEW Vision 이미지 함수를 사용하여 검사 프로그램을 개발하였다. 개발된 검사 알고리즘은 생산 부품의 실시간 검사에 적용 될 수 있으며, 검사 영역과 설정 값을 비전 시스템 운용자가 설정할 수있도록 프로그램이 만들어져 검증되었다. 제안된 검사시스템은 카시트 프레임 검사를 성공적으로 수행하였다.

• 한국정보전자통신기술학회논문지
• /
• 제10권5호
• /
• pp.359-363
• /
• 2017

LED(Liquid Emitting Diode)프레임 장치는 한국을 대표하는 디스플레이 분야에서 큰 비중을 차지하고 있다. LED는 TV나 모니터, 노트북, 핸드폰 등 에 필수적인 부품이다. 일본이나 대만, 중국 등에서 LED에 대한 투자를 강화하면서 생산성 향상이 중요한 사항이 되고 있다. 하지만 부품의 크기가 점점 작아지면서, 사람의 눈에 의한 일관적이지 못한 검사는 신뢰성이 문제가 되어 LED 모듈 검사 분야에서 자동 검사 공정은 필수적인 사항이 되고 있다. 본 논문에서는 컴퓨터 비전 기술을 이용하여 시각 검사 공정의 결함을 검사한다. LED 프레임에 대한 검사를 신속하고 정확하게 함으로써 공정상의 효율을 높이고 검사시간을 단축하였다. 검사 시스템을 현장에 적용한 결과 빠르고 정확하게 검사가 가능함을 확인하였다.

• 한국소음진동공학회:학술대회논문집
• /
• 한국소음진동공학회 2014년도 추계학술대회 논문집
• /
• pp.827-829
• /
• 2014

This paper presents a design methodology for improving dynamic stiffness of an inspection robot frame to prevent resonance. Finite element models of robot frame are developed for natural frequency analysis. Natural frequency analysis of robot frame is conducted to compare with sub-span oscillation which is excitation frequency. Reinforcement beams are applied to the sensitive parts of the robot frame to improve dynamic stiffness using case study. To reduce mass of the robot frame, thickness optimization of the robot frame is carried out by utilizing response surface method. The result of optimization show that dynamic stiffness of robot frame is increased. As a result, natural frequency of an optimal model is not included in range of frequencies of the sub-span oscillation.

• 자동차안전학회지
• /
• 제9권4호
• /
• pp.55-60
• /
• 2017

This paper presents the motorcycle inspection standards of electrical system, frame & body, lights and speedometers. 187 real-world motorcycles are visually and mechanically inspected according to the developed inspection standards. The non-compliance rate of inspection standards of the lights is 23.7% and main causes are damage, tinting, painting and coloration of head-lamp, number plate lamp, front-rear position lights, stop lamp and direction indicators of motorcycles. Also, 28.4% of motorcycles are dropped from the luminous intensity inspection standard. Motorcycle electrical system cannot be visually inspected. The motorcycle inspections standards are improved reflecting 187 cases of real-world motorcycle inspection results.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 1994년도 추계학술대회 논문집
• /
• pp.492-498
• /
• 1994

The bicycle production process mainly consists of welding process of pipes and its quality is determined by geometrical symmetry of arrangement of welded pipes. Hence, manual quality control of bicycle frames was very inefficient and required much time in dimentional inspection and does not reserve high precision. In this paper we introduce a method of fast and accurate dimensional inspection of bicycle frame using the Stereo Vision system and related some image processing techniques.

• International Journal of Control, Automation, and Systems
• /
• 제6권5호
• /
• pp.740-745
• /
• 2008

This paper presents a new non-contact 3D robotic inspection system to measure the precise positions of screw and punch holes on a car body frame. The newly developed sensor consists of a CCD camera, two laser line generators and LED light. This lightweight sensor can be mounted on an industrial robot hand. An inspection algorithm and system that work with this sensor is presented. In performance evaluation tests, the measurement accuracy of this inspection system was about 200 ${\mu}m$, which is a sufficient accuracy in the automotive industry.

• 제어로봇시스템학회논문지
• /
• 제21권12호
• /
• pp.1109-1114
• /
• 2015

This paper presents an improved learning-based visual inspection method for auto parts inspection in severe lighting changes. Automobile sunroof frames are produced automatically by robots in most production lines. In the sunroof frame manufacturing process, there is a quality problem with some parts such as volts are missed. Instead of manual sampling inspection using some mechanical jig instruments, a learning-based machine vision system was proposed in the previous research[1]. But, in applying the actual sunroof frame production process, the inspection accuracy of the proposed vision system is much lowered because of severe illumination changes. In order to overcome this capricious environment, some selective feature vectors and cascade classifiers are used for each auto parts. And we are able to improve the inspection accuracy through the re-learning concept for the misclassified data. The effectiveness of the proposed visual inspection method is verified through sufficient experiments in a real sunroof production line.