• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 2012년도 추계학술대회 논문집
• /
• pp.67-68
• /
• 2012

• 한국정밀공학회지
• /
• 제23권10호
• /
• pp.7-13
• /
• 2006

• 한국레이저가공학회지
• /
• 제13권3호
• /
• pp.1-6
• /
• 2010

The in-process monitoring of $CO_2$ welding of Zn-coated steel plates has been studied and compared with that of conventional thin plates. Relationships between weld defects and plasma emission signals were evaluated in laser lap joint of thick Zn-coated steel. According to the study, weld defects were found to increase with Zn content. As a result, measured plasma emission signals also decreased. In case of plate with $15{\mu}m$-thick Zn-coated layer, defects caused by evaporation of Zn could, therfore, controled by gap of 0.1mm, resulting in a stable emission signals. However, the amplitude of signals fluctuated very widely. Variation of amplitude sould be limited in 3-8V by FFT smoothing.

• 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.

• 한국안전학회지
• /
• 제18권1호
• /
• pp.8-13
• /
• 2003

This study proposes integrity evaluation method of weld zone in rails using high precision distance amplitude characteristics curve(DACC) and ultrasonic signals. For these purposes, the ultrasonic signals for defects(porosity and crack) of weld zone in rails are acquired in the type of time series data and echo strength. 6 lines in the DACC indicated damage evaluation standard of weld zone in rails. The aquired ultrasonic signals agree fairly well with the mesured results of reference block and sensitivity block(defect location, beam propagation distance, echo strength, etc). The proposed high precision DACC in this study can be used for integrity evaluation of weld zone in rails.

• 한국기계가공학회지
• /
• 제11권5호
• /
• pp.129-136
• /
• 2012

On this study, $CO_2$ gas, net of Ar gas, and mixed gas in solid wire(AWS ER 70S-6) and flux cored wire(AWS E71T-1) were used to weld on Mild steel(SS400). After the progress, the status changes of the welds in Mild steel(SS400) were investigated with compositional changes. For stable experiments, welding was conducted using the automatic feeder. Radiation testing, hardness testing, chemical composition analysis and penetrated cross-section were measured. Through these experiments, shapes of penetrated cross-section, chemical composition changes, and weld defects according to the variation of welding gas were known. Weld defects and weld cross-sectional shapes by the variation of the welding voltage were also detected.

• 한국안전학회지
• /
• 제26권5호
• /
• pp.17-22
• /
• 2011

This study proposes feature extraction method of pattern recognition by evaluation of weld defects in weld zone of titanium. For this purpose, analysis objectives in this study are features of attractor quadrant and fractal dimension. Trajectory changes in the attractor indicated a substantial difference in fractal characteristics resulting from distance shifts such as porosity of weld zone. These differences in characteristics of weld defects enables the evaluation of unique characteristics of defects in the weld zone. In quantitative fractal feature extraction, feature values of 0.87 and 1.00 in the case of part of 0.5 skip distance and 0.72 and 0.93 in the case of part of 1.0 skip distance were proposed on the basis of fractal dimensions. Attractor quadrant point, feature values of 1.322 and 1.172 in the case of ${\phi}1{\times}3mm$ porosity and 2.264 and 307 in the case of ${\phi}3{\times}3mm$ porosity were proposed on the basis of distribution value. The Proposed feature extraction of pattern recognition in this study can be used for safety evaluation of weld zone in titanium.

• 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.

• 한국소성가공학회:학술대회논문집
• /
• 한국소성가공학회 2007년도 추계학술대회 논문집
• /
• pp.364-367
• /
• 2007

In nano-imprint lithography (NIL) process, which has shown to be a good method to fabricate polymeric patterns, several kinds of pattern defects due to thermal effects during polymer flow and mold release operation have been reported. A typical defect in NIL process with high aspect ratio and low resist thickness pattern is a resist fracture during the mold release operation. It seems due to interfacial adhesion between polymer and mold. However, in the present investigation, FEM simulation of NIL molding process was carried out to predict the defects of the polymer pattern and to optimize the process by FEA. The embossing operation in NIL process was investigated in detail by FEM. From the analytical results, it was found that the lateral flow of polymer resin and the applied pressure in the embossing operation induce the weld line and the drastic lateral strain at the edge of pattern. It was also shown that the low polymer-thickness result in the delamination of polymer from the substrate. It seems that the above phenomena cause the defects of the final polymer pattern. To reduce the defect, it is important to check the initial resin thickness.

• International Journal of Korean Welding Society
• /
• 제1권2호
• /
• pp.36-44
• /
• 2001

To get the appropriate welding process variables, mathematical modeling in conjunction with many experiments is necessary to predict the magnitude of weld bead shape. Even though the experimental results are reliable, it has a difficulty in accurately predicting welding process variables for the desired weld bead shape because of nonlinear and complex characteristics of welding processes. The welding condition determined for the desired weld bead shape may cause the weld defect if the welding current/voltage/speed combination is improperly selected. In this study, the $2^{n-1}$ fractional factorial design method and correlation parameter were used to investigate the effect of the welding process variables on the fillet joint shape, and the multiple non-linear regression analysis was used for modeling the gas metal arc welding(GMAW）parameters of the fillet joint. Finally, a fuzzy rule-based method and a neural network method were proposed so that the complexity and non-linearity of arc welding phenomena could be effectively overcome. The performance of the proposed neuro-fuzzy system was evaluated through various experiments. The experimental results showed that the proposed neuro-fuzzy system could effectively check the welding conditions as to whether or not weld defects would occur, and also adjust the welding conditions to avoid these weld defects.