• Journal of Welding and Joining
• /
• 제16권5호
• /
• pp.108-118
• /
• 1998

This study proposes th analysis and evaluation method of time series ultrasonic signal using the chaos feature extraction for ultrasonic pattern recognition. Features extracted from time series data using the chaos time series signal analyze quantitatively weld 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 chaosity resulting from distance shifts such as 0.5 and 1.0 skip distance. Such differences in chaosity enables the evaluation of unique features of defects in the weld zone. In quantitative chaos feature extraction, feature values of 4.511 and 0.091 in the case of side hole and 4.539 and 0.115 in the case of vertical hole were proposed on the basis of fractal dimension and Lyapunov exponent. Proposed chaos feature extraction in this study can enhances ultrasonic pattern recognition results from defect signals of weld zone such as side hole and vertical hole.

• 한국정밀공학회지
• /
• 제15권7호
• /
• pp.149-159
• /
• 1998

The importance of soundness and safety evaluation in weld zone using by the ultrasonic wave has been recently increased rapidly because of the collapses of huge structures and safety accidents. Especially, the ultrasonic method that has been often used for a major non-destructive testing(NDT) technique in many engineering fields plays an important role as a volume test method. Hence, the defecting any defects of weld Bone in austenitic stainless steel type 304 using by ultrasonic wave and neural network is explored in this paper. In order to detect defects, a distance amplitude curve on standard scan sensitivity and preliminary scan sensitivity represented of the relation between ultrasonic probe, instrument, and materials was drawn based on a quantitative standard. Also, a total of 93％ of defect types by testing 30 defect patterns after organizing neural network system, which is learned with an accuracy of 99％, based on ultrasonic evaluation is distinguished in order to classify defects such as holes or notches in experimental results. Thus, the proposed ultrasonic wave and neural network is useful for defect detection and Ultrasonic Non-Destructive Evaluation(UNDE) of weld zone in austenitic stainless steel 304.

• 한국정밀공학회지
• /
• 제15권11호
• /
• pp.152-165
• /
• 1998

This study proposes the analysis and evaluation method of time series ultrasonic signal using the chaoral post-process system for precision rate enhancement of ultrasonic pattern recognition. Chaos features extracted from time series data for analysis quantitatively weld defects For this purpose, feature extraction objectives in this study are fractal dimension, Lyapunov exponent, shape of strange attrator. Trajectory changes in the strange attractor indicated that even same type of defects carried substantial difference in chaoticity resulting from distance shifts such as nearby 0.5, 1.0 skip distance. Such difference in chaoticity enables the evaluation of unique features of defects in the weld zone. In quantitative chaos fenture extraction, feature values of 0.835 and 0.823 in the case of slag inclusion and 0.609 and 0.573 in the case of crack were suggested on the basis of fractal dimension and Lyapunov exponent. Proposed chaoral post-process system in this study can enhances precision rate of ultrasonic pattern recognition results from defect signals of weld zone, such as slag inclusion and crack.

• 한국신재생에너지학회:학술대회논문집
• /
• 한국신재생에너지학회 2009년도 추계학술대회 논문집
• /
• pp.135-138
• /
• 2009

Quality evaluation of laser welded MCFC separator panels with large active area was performed. Lap joint was applied to produce stable air-tight seam weld by employing Nd:YAG laser. Results showed that surface contamination played a key role to form weld defects at the joint interface. However, there was no evidence that weld width at the lap joint changed after the stack operation time of 2,890h. Test results also revealed that the reinforcement values which were measured on the weld line after long time operation, were stable.

• 대한기계학회:학술대회논문집
• /
• 대한기계학회 2000년도 춘계학술대회논문집A
• /
• pp.200-205
• /
• 2000

Fatigue failure modes of load-carrying cruciform weld joints are dependent on the characteristics of the fatigue crack initiation and propagation from the weld toe or the weld root. In this study, constant amplitude fatigue tests on load-carrying fillet welded specimen carried out, and fatigue strengths were evaluated. Also, an attempt is made to develop a new analytical model with more accuracy to predict the fatigue crack propagation life of fillet welded cruciform joints of SWS 490B steels containing lack of penetration defects. From the result of this study, fatigue crack growth characteristics of load-carrying fillet welded cruciform joints, containing lack of penetration defects are found to be affected by the weld geometry, stress range and microstructures of the weld zone.

• 제어로봇시스템학회논문지
• /
• 제6권2호
• /
• pp.207-216
• /
• 2000

This paper introduces an effective system design method to develop a customer oriented product using a design optimization process and to select a set of critical design paramenters,. The process results in the development of a successful product satisfying customer needs and reducing development risk. The proposed scheme adopted a five step QFD(Quality Function Deployment) in order to extract design parameters from customer needs and evaluated their priority using risk factors for extracted design parameters. In this process we determine critical design parameters and allocate them to subsystem designers. Subsequently design engineers develop and test the product based on these parameters. These design parameters capture the characteristics of customer needs in terms of performance cost and schedule in the process of QFD, The subsequent risk management task ensures the minimum risk approach in the presence of design parameter uncertainty. An application of this approach was demonstrated in the development of weld quality monitoring system. Dominant design parameters affect linearity characteristics of weld defect feature vectors. Therefore it simplifies the algorithm for adopting pattern classification of feature vectors and improves the accuracy of recognition rate of weld defect and the real time response of the defect detection in the performance. Additionally the development cost decreases by using DSP board for low speed because of reducing CPU's load adopting algorithm in classifying weld defects. It also reduces the cost by using the single sensor to measure weld defects. Furthermore the synergy effect derived from the critical design parameters improves the detection rate of weld defects by 15% when compared with the implementation using the non-critical design parameters. It also result in 30% saving in development cost./ The overall results are close to 95% customer level showing the effectiveness of the proposed development approach.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 1995년도 추계학술대회 논문집
• /
• pp.1101-1104
• /
• 1995

Through welding fabrication, user can feel an surficaial and capable unsatisfaction because of welded defects, Generally speaking, these are called weld defects. For checking these defects effectively without time loss effectively, weldability estimation system setup isan urgent thing for detecting whole specimen quality. In this study, by laser vision camera, catching a rawdata on welded specimen profiles, treating vision processing with these data, qualititative defects are estimated from getting these information at first. At the same time, for detecting quantitative defects, whole specimen weldability estimation is pursued by multifeature pattern recognition, which is a kind of fuzzy pattern recognition. For user friendly, by weldability estimation results are shown each profiles, final reports and visual graphics method, user can easily determined weldability. By applying these system to welding fabrication, these technologies are contribution to on-line weldability estimation.

• 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.

• 한국압력기기공학회 논문집
• /
• 제10권1호
• /
• pp.15-19
• /
• 2014

A Failure or degradation of reactor upper head penetration is a recurring problem due to long term operation at nuclear power plants. And a flaw in the reactor upper head penetration has caused unplanned plant shutdown for repair as well as high economic impact on the plants. Consequently, a detection of flaws is of the utmost importance. Prior to the replacement of reactor upper head penetration, some utilities have repaired the flaws of reactor upper head penetration generated by overlay weld. Until now, only the base metal in reactor upper head penetration has been inspected according to 10 CFR 50.55a and ASME code case N-729-1. Accordingly, it is difficult to detect manufacturing defects and repair defects in overlay weld. This paper presents a case study on the application of Time of Flight Diffraction technique for reactor head penetration mockup with artificial flaws in overlay weld. This study offers a way to understand the flaws detected in reactor upper head penetration overlay weld.

• Journal of Welding and Joining
• /
• 제34권6호
• /
• pp.62-68
• /
• 2016

Laser welding has superior characteristic such as low distortion, high welding speed, easy automation and real time control. But it is easy to occur weld defects such as porosity, crater, humping bead in the area of welding start and end. These weld defects can be suppressed by applying the wave shape control. In this study CW fiber laser was used for welding of $0.5mm^t$ pure titanium. Penetration properties were evaluated with the time of slope up and down. After then the bead shape was observed, and the maximum depth and the area of crater were measured. The bead shape of welding start area changed to be sharp with increase of slope up time and non-weld area of welding start increased. The crater and humping bead were suppressed with slope down time. The cooling rate of crater area was understood through measure of the hardness. Also, The distribution tendency of alloying elements was observed by EPMA and EDS. When wave shape control didn't applied to weld, the hardness of end weld increased due to rapid cooling rate and the hardness of rear part in the crater was higher than that of fore part. On the other hand, when the wave shape control was used for end weld, the increase of hardness in the end weld couldn't be found due to gradual cooling rate.