• 대한기계학회논문집A
• /
• 제23권7호
• /
• pp.1065-1074
• /
• 1999

This study proposes the analysis and evaluation method of time series ultrasonic signal using the chaotic feature extraction for ultrasonic pattern recognition. Features extracted from time series data using the chaotic time series signal analysis quantitatively welding defects. For this purpose analysis objective in this study is fractal dimension and Lyapunov exponent. Trajectory changes in the strange attractor indicated that even same type of defects carried substantial difference in chaoticity resulting from distance shills such as 0.5 and 1.0 skip distance. Such differences in chaoticity enables the evaluation of unique features of defects in the weld zone. In experiment fractal(correlation) dimension and Lyapunov exponent extracted from 6dB ultrasonic defect signals of weld zone showed chaoticity. In quantitative chaotic feature extraction, feature values(mean values) of 4.2690 and 0.0907 in the case of porosity and 4.2432 and 0.0888 in the case of incomplete penetration were proposed on the basis of fractal dimension and Lyapunov exponent. Proposed chaotic feature extraction in this study enhances ultrasonic pattern recognition results from defect signals of weld zone such as vertical hole.

• Journal of Welding and Joining
• /
• 제28권1호
• /
• pp.66-71
• /
• 2010

With large specific strength and outstanding corrosion resistance and erosion resistance in sea water, titanium and titanium alloy are widely used in heat exchanger production. In particular, pure titanium demonstrates outstanding molding performance and may be considered optimal for production of heat exchanger. Since titanium is very vulnerable to oxidation and embrittlement during welding, processes with less heat input are widely used, and laser welding is widely applied by considering production performance and shield etc in atmosphere. So far, 1st report and 2nd report compared and analyzed embrittlement degrees by bead colors of weldment through oxygen and nitrogen quantitative analysis and hardness measurement, and evaluated welding performance and mechanical properties of butt welding. This study evaluated field applicability of lap welding to heat exchange plate of LPG re-liquefaction device for ships through tensile stress test, hardness test and internal pressure test etc after deducing optimal weding condition and applying to actual heat exchange plate. In bead overlap area, the experiment produced sound welds with no porosity or defect by increasing and decreasing laser power, and tensile-shear test results indicated virtually the same tension and yield strength as base metal. As a result of measuring hardness at lateral cross section and bead overlap zone of actual heat exchanger welds, hardness difference within 20Hv was produced at base metal, HAZ and weldment, and as a result of pneumatic and hydraulic pressure test, no leakage occurred.

• 융합신호처리학회논문지
• /
• 제22권4호
• /
• pp.185-192
• /
• 2021

용접 비드의 불량유무를 판단하기 위하여 다양한 방법들이 제안되어왔으며, 최근에는 센서 자료 검사와 영상 자료 검사가 꾸준히 발표되고 있다. 센서 자료 검사는 정확도가 높고, 2차원 기반의 영상 자료 검사는 용접된 비드의 위치를 파악할 수 있다는 장점이 있다. 하지만 센서 자료만으로 분석 할 경우 정확한 위치에 용접이 되었는지 파악하기가 어렵다. 반면 영상 자료 방법은 잡음과 측정오차가 발생하여 정확도가 높지 않다. 본 논문에서는 평균 전압, 평균 전류, 혼합가스인 센서 자료 검사와 영상 검사 방법을 융합함으로써 각 검사 방법들의 단점을 보완하고 장점을 높여서 정확도를 향상시키고 검사 속도를 높일 수 있는 방법과 이를 소프트웨어로 구현하였다. 그리고 그래픽 사용자 인터페이스(graphical user interface; GUI)를 이용하여 분석을 수행하고 검사에 사용된 자료와 검사 결과를 확인할 수 있도록 하여 사용자가 편리하고 직관적으로 분석을 수행하고 결과를 파악할 수 있도록 하고자 한다. 이 때 각 센서 자료의 특성을 이용하여 센서 검사가 수행되고, 모폴로지 축지적 활성화 윤곽선을 적용하여 영상 자료가 검사된다. 실험 결과를 통하여 98%의 정확도를 보였으며, 네 개의 용접 영상과 센서 자료 검사를 모두 수행할 경우 검사 시간은 약 1.9초로서 용접공정에서 실시간 검사기로 사용 가능한 소프트웨어의 성능을 보였다.

• Journal of Welding and Joining
• /
• 제13권2호
• /
• pp.42-52
• /
• 1995

In the evaluation of aging degradation on the structural materials based on the fracture mechanics, the detection and size prediction of defect are very important. Aiming at nondestructive detection and size prediction ol defect with high accuracy and resolution, therefore, an lnduced Current Focusing Potential Drop(ICFPD) technique has been developed. The principle of this technique is to induce a focusing current at an exploratory region by an induction wire flowing an alternating current(AC) that is a constant ampere and frequency. Defects are assessed with the potential drops that are measured the induced current on the surface of metallic material by the potential pick-up pins. In this study, the lCFPD technique was applied for evaluating the location and size of the surface crack and blind crack made in plate specimens, and also for detecting the defects existing in valve, a field component, that were developed by SCC etc. during the service. The results of this present study show that surface crack and blind crack are able to defect with potential drop. these cracks are distinguished with the distribution of potential drop, and the crack depths can be estimated with each normalized potential drop that are parameters estimating the depth of each type crack. In the field component, the defects estimated by experiment result correspond with those in the cutting face of the measuring point within a higher sensitivity.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제14권3호
• /
• pp.1086-1103
• /
• 2020

The automatic identification and classification of image-based weld defects is a difficult task due to the complex texture of the X-ray images of the weld defect. Several depth learning methods for automatically identifying welds were proposed and tested. In this work, four different depth convolutional neural networks were evaluated and compared on the 1631 image set. The concavity, undercut, bar defects, circular defects, unfused defects and incomplete penetration in the weld image 6 different types of defects are classified. Another contribution of this paper is to train a CNN model "RayNet" for the dataset from scratch. In the experiment part, the parameters of convolution operation are compared and analyzed, in which the experimental part performs a comparative analysis of various parameters in the convolution operation, compares the size of the input image, gives the classification results for each defect, and finally shows the partial feature map during feature extraction with the classification accuracy reaching 96.5%, which is 6.6% higher than the classification accuracy of other existing fine-tuned models, and even improves the classification accuracy compared with the traditional image processing methods, and also proves that the model trained from scratch also has a good performance on small-scale data sets. Our proposed method can assist the evaluators in classifying pipeline welding defects.

• 대한용접접합학회:학술대회논문집
• /
• 대한용접접합학회 2009년 추계학술발표대회
• /
• pp.32-32
• /
• 2009

Electric Resistance Welding (ERW) process is the most efficient process to manufacture the linepipe. To develop the high performance ERW linepipe using the high strength and the high alloy steels, the modulation of input power waveform such as sinusoidal waveform is introduced because the conventional ERW technology is not sufficient enough to produce the high quality linepipe due to its strength and high alloy contents (high Ceq). In this article, the material used for the experiment was API X60 with 8.2mm thickness, and ERW simulator at POSCO was used to develop a waveform control system for the power modulation. The frequency of power modulation was varied from 50Hz to 150Hz with the fixed amplitude of ${\pm}2%$ power. The non-modulated power input and the modulated power input cases are conducted to demonstrate the variation of the narrow gap length and the arcing frequency due to power modulation. From results of the non-modulated power input case, the excessive power causes the longer narrow gap length and the low arcing frequency due to the large heat input and the strong electro magnetic force that increase the weld defect. On the contrary, the small narrow gap length and the high arcing frequency reduce the weld defect. After modulating the power input with 50Hz and 100Hz at the fixed power, the arcing frequency increases, but the narrow gap length does not change much. The high arcing frequency prevents the formation of weld defect because the sweeping frequently cleans the oxides on the narrow gap edges. As a result, the manufacturing window can be expanded by the power modulation that provides the stable ERW process for the quality improvement of the linepipe made from the high strength/high alloy steels.

• 비파괴검사학회지
• /
• 제28권4호
• /
• pp.323-330
• /
• 2008

소구경 배관 소켓 용접부의 고주기 피로특성윽 평가하고 피로 균열의 발생을 음향방출법을 이용하여 실시간 모니터링 하였다. 스테인리스 316L강 시험편은 가스텅스텐아크용접 공정으로 루트부에 결함이 없는 시험편과 용입불량 결함이 있는 시험편으로 준비하였다. 피로파단은 고응력 일때는 토우부, 상대적으로 저응력일 때는 루트부에서 일어났다. 피로시험동안 음향방출 카운트가 급격히 증가하는 시점을 균열의 발생 싸이클 ($N_i$)로 정의하였고 방사선투과법과 전자현미경을 이용하여 피로균열 생성 싸이클 전과 후에서 균열을 확인하였다. 소켓용접배관의 굽힘피로 손상 진단 및 감시를 위해 균열의 존재와 파괴모드 그리고 균열의 발생 싸이클에 관한 연구를 수행하였다.

• 한국산업정보학회논문지
• /
• 제29권1호
• /
• pp.107-116
• /
• 2024

Copper Filter Dryer(CFD)는 냉동 및 냉방 시스템에서 냉매의 순환 시 불순물을 제거하여 깨끗한 냉매를 유지하는 역할을 하며, CFD의 결함은 냉동 및 냉방 시스템의 누수, 수명 저하 등 제품의 결함으로 이어질 수 있어 품질보증이 필수적이다. 기존에는 품질 검사 단계에서 작업자가 검사하고 결함을 판단하는 방법이 주로 사용되었으나, 이러한 방법은 주관적으로 판단하기 때문에 정확하지 못하다. 본 논문에서는 CFD 축관 및 용접 공정 과정에서 발생하는 결함을 검출하고 기존의 품질 검사를 대체하기 위해 YOLOv7 객체 감지 알고리즘을 사용하여 결함을 검출했고, F1-Score 0.954, 0.895의 검출 성능을 확인하였다. 또한, 결함 이미지의 Timestamp에 해당하는 센서 데이터 분석을 통해 용접 과정 중 발생하는 결함의 원인을 분석하였다. 본 논문은 CFD 공정 중 발생하는 결함을 검출하고 원인을 분석함으로써 제조 품질보증과 개선 방안을 제시한다.

• 한국생산제조학회지
• /
• 제9권5호
• /
• pp.135-143
• /
• 2000

The vision system is easy to use the exclusive use as a independent computer system but it is not much popularization by reason of expensive and difficult to adapt to the various fields, because it is easy to the existed computer system, the price is cheap and also it can use to the various measurement purpose which user wanted and programed. The measurement method of the vehicle axle casing nut welding part is that measure the value of the welding part to adapt the actual operation program from using the ratio between the actual length of the standard specimen and the length of image, to measure the ratio between the actual product and the camera image. A defect is found by the assembled visual inspection system. The inspection algorithm which estimates the quality of welded product is developed and also, the software program which processes the automatic test function of the inspection system. We make the foundation of the inspection automatic system and we will help to apply other welding machine.

• 한국정보통신학회:학술대회논문집
• /
• 한국해양정보통신학회 1999년도 춘계종합학술대회
• /
• pp.425-431
• /
• 1999

본 연구에서는 플라즈마 감시에 의한 용접성 평가방식을 채택한다. 플라즈마에서 발생하는 자외선신호를 반도체 광센서를 사용하여 검출하고, 감시장치로 쓰이는 개인용 컴퓨터에 고속으로 전달, 저장하는 장치를 개발한다. 이 장치를 사용하여 용접 데이터베이스를 구축하고, 용접성과 플라즈마 신호와의 관계를 평가하고, 분석할 것이다. 이 분야에 대한 연구동향을 하면 표2와 같다. 그러나 이 연구들은 모두 사용한 장치의 특성, 플라즈마발생원에 대한 센서의 상대적 위치 및 자세와 획득 신호와의 관계, 용접할 때 발생하는 열의 센서에 대한 영향, 잡음이 취득된 신호에 미치는 영향 및 회피방법 둥에 대한 언급이 없다. 따라서 논문에 실린 신호의 파형은 대부분 일관성이 없으며, 참고가 어렵다. 본 연구에서는 이러한 관계를 도출하고, 특히 잡음의 영향을 최소화하는 장치화에 주안점을 둔다.