• Proceedings of the Korean Information Science Society Conference
• /
• 2012.06c
• /
• pp.415-417
• /
• 2012

본 논문에서는 산업용 CT 영상에서 다중 해상도 기반의 밝기값 정보와 형태 정보를 이용하여 내부 기공결함을 정확하고 빠르게 검출하는 기법을 제안한다. 첫째, 대용량 CT 데이터에서 계산량을 줄이기 위하여 1/2 해상도로 변환 후 관심영역을 자동 산정하고, 링 또는 금속 인공물 등의 잡음을 제거하기 위해 비등방성 확산 필터링을 수행한다. 둘째, 기공 결함 후보군을 검출하기 위해 밝기값 기반의 결함 검출 기법을 제안한다. 셋째, 결함 검출의 민감도를 향상시키기 위해 형태 정보를 이용한 기공 결함 검출 기법을 제안한다. 넷째, 수행시간 가속화를 위하여 다중 해상도 영상 처리 및 Open MP를 적용한다. 제안방법의 평가를 위하여 육안평가와 정확성 평가, 수행시간을 측정하였다. 정확성 평가는 실제 기공 결함과 제안방법 적용 후 결함 간 중복 픽셀 수로 측정하였다. 실험 결과 평균 중복 픽셀 비율은 91%로 측정되었고, 가장 큰 비율은 99%, 가장 작은 비율은 80%로 측정되었다. 다중 해상도 기법 및 Open MP를 적용함으로써 해상도 데이터 수행시간보다 90% 가속화되었다.

• Journal of the Korean Society for Nondestructive Testing
• /
• v.30 no.5
• /
• pp.429-436
• /
• 2010

Recently, (terahertz ray) applications have emerged as one of the most promising new powerful nondestructive evaluation (NDE) techniques. In this study, a new T-ray time-domain spectroscopy system was utilized for detecting and evaluating layup effect and flaw in FRP composite laminates. Extensive experimental measurements in reflection and thru-transmission modes were made to map out the T-ray images. Especially this was demonstrated in thick GFRP laminates containing double saw slots. In carbon composites the penetration of terahertz waves is limited to some degree and the detection of flaws is strongly affected by the angle between the electric field(E-field) vector of the terahertz waves and the intervening fiber directions. The artificial defects investigated by terahertz waves were bonded foreign material, simulated disbond and delamination and mechanical impact damage. The effectiveness and limitations of terahertz radiation for the NDE of composites are discussed.

• Journal of the Korean Society for Railway
• /
• v.18 no.5
• /
• pp.401-409
• /
• 2015

Defects generated in a railroad track that guides the railroad vehicle have the characteristic of growing fast; as such, the detection technology for railroad track defects is very important because defects can eventually cause mass disasters like derailments. In this study, a speed-up test facility was fabricated to investigate the feasibility of using magnetic flux leakage (MFL) technology for defect detection in a railroad track under speed-up condition; a test was conducted using a railroad track specimen with defects. For this purpose, an MFL sensor head dedicated to the configuration of the railroad was designed and test specimens with artificial defects on their surfaces were manufactured. Using the test facility, a speed-up test ranging from 4km/h to 12km/h was performed and defects including locations were successfully detected from MFL signals induced by defects with enhanced visibility by differentiating raw MFL signals. In the future, it should be possible to apply this system to a high-speed railroad inspection car by improving the lift-off stability that is necessary for speed-up of the developed MFL sensor system.

• Journal of the Korean Society for Nondestructive Testing
• /
• v.30 no.4
• /
• pp.311-316
• /
• 2010

Defects positioning of underground gas pipelines using MFL(magnetic flux leakage) inspection which is one of non-destructive evaluation techniques is proposed in this paper. MFL signals acquired from MFL PIG(pipeline inspection gauge) have nonlinearity and distortion caused by various external disturbances. SQI(self quotient image), a compensation technique for nonlinearity and distortion of MFL signal, is used to correct positioning of pipeline defects. Through the experiments using artificial defects carved in the KOGAS pipeline simulation facility, it is found that the performance of proposed defect detection is greatly improved compared to that of the conventional DCT(discrete cosine transform) coefficients based detection.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.6
• /
• pp.834-841
• /
• 2022

Recently, applying artificial intelligence technologies in various fields of production has drawn an upsurge of research interest due to the increase for smart factory and artificial intelligence technologies. A great deal of effort is being made to introduce artificial intelligence algorithms into the defect detection task. Particularly, detection of defects on the surface of metal has a higher level of research interest compared to other materials (wood, plastics, fibers, etc.). In this paper, we compare and analyze the speed and performance of defect classification by combining machine learning techniques (Support Vector Machine, Softmax Regression, Decision Tree) with dimensionality reduction algorithms (Principal Component Analysis, AutoEncoders) and two convolutional neural networks (proposed method, ResNet). To validate and compare the performance and speed of the algorithms, we have adopted two datasets ((i) public dataset, (ii) actual dataset), and on the basis of the results, the most efficient algorithm is determined.

• Journal of Internet of Things and Convergence
• /
• v.9 no.2
• /
• pp.61-69
• /
• 2023

In recent years, due to heightened environmental awareness, Electric Power Steering (EPS) has been increasingly adopted as the steering control unit in manufactured vehicles. This has had numerous benefits, such as improved steering power, elimination of hydraulic hose leaks and reduced fuel consumption. However, for EPS systems to respond to actions, sensors must be employed; this means that the consistency of the sensor's linear variation is integral to the stability of the steering response. To ensure quality control, a reliable method for detecting defects and assessing linearity is required to assess the sensitivity of the EPS sensor to changes in the internal design characters. This paper proposes a data-driven defect and linearity assessment monitoring system, which can be used to analyze EPS component defects and linearity based on vehicle speed interval division. The approach is validated experimentally using data collected from an EPS test jig and is further enhanced by the inclusion of a Graphical User Interface (GUI). Based on the design, the developed system effectively performs defect detection with an accuracy of 0.99 percent and obtains a linearity assessment score at varying vehicle speeds.

• Transactions of the Korean Society of Machine Tool Engineers
• /
• v.12 no.6
• /
• pp.56-63
• /
• 2003

In this study, an automatic ultrasonic testing system is used to detect the defects of the natural flaw test specimen and of the artificial flaw test specimen. We evaluate the detection performance of the acceptance standard for the natural flaw test specimen and of the acceptance standard for the artificial flaw test specimen. We also study the potential problems of those acceptance standards. The results indicate that the acceptance standard for the detection of defects in weldzone is good then the sensitivity correction is performed and that we must clearly specify special check points of the acceptance standard for the system in use.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2019.07a
• /
• pp.9-10
• /
• 2019

본 논문은 구동장치의 진동에서 특징 데이터를 추출하고 인공신경망에 학습을 시킨 후, 구동 장치의 결함을 분류하는 시스템을 구현하였다. 딥러닝 기술을 이용함으로써 특정 장치에 종속되지 않고 학습할 데이터의 특징에 따라 쉽게 변경 가능하다. 또한, 실제 적용될 현장에서 발생할 수 있는 예측외의 진동 환경에 유연하게 대처하기 위해 딥러닝 모델 중 CNN을 적용한 시스템을 설계하였으며, 본 연구팀의 이전 연구에서 제안된 DNN 기반의 진단시스템을 학습데이터의 환경과 다른 처리배제가 필요한 진동 환경에서 비교 실험하여 제안된 시스템이 새로운 환경적응 성능향상에 대하여 우수한 결과를 얻었음을 확인하였다.

• Journal of Welding and Joining
• /
• v.16 no.3
• /
• pp.64-73
• /
• 1998

This paper is concerned with defects detection and evaluation of heat affected zone (HAZ) in austenitic stainless steel type 304 by ultrasonic wave and neural network. In experiment, the reflected ultrasonic defect signals from artificial defects (side hole, vertical hole, notch) of HAZ appears as beam distance of prove-defect, distance of probe-surface, depth of defect-surface on CRT. For defect classification simulation, neural network system was organized using total results of ultrasonic experiment. The organized neural network system was learned with the accuracy of 99%. Also it could be classified with the accuracy of 80% in side hole, and 100% in vertical hole, 90% in notch about ultrasonic pattern recognition. Simulation results of neural network agree fairly well with results of ultrasonic experiment. Thus were think that the constructed system (ultrasonic wave - neural network) in this work is useful for defects dection and classification such as holes and notches in HAZ of austenitic stainless steel 304.

• Journal of the Korean Society for Nondestructive Testing
• /
• v.19 no.5
• /
• pp.369-377
• /
• 1999

Recently, it is gradually raised necessity that thickness of thin film is measured accuracy and managed in industrial circles and medical world. Ultrasonic signal processing method is likely to become a very powerful method for NDE method of detection of microdefects and thickness measurement of thin film below the limit of ultrasonic distance resolution in the opaque materials, provides useful information that cannot be obtained by a conventional measuring system. In the present research. considering a thin film below the limit of ultrasonic distance resolution sandwiched between three substances as acoustical analysis model, demonstrated the usefulness of ultrasonic signal processing technique using information of ultrasonic frequency for NDE of measurements of thin film thickness. Accordingly, for the detection of delamination between the junction condition of boundary microdefect of thin film sandwiched between three substances the results from digital image processing.