• Journal of the Korean Society of Manufacturing Technology Engineers
• /
• v.9 no.1
• /
• pp.119-127
• /
• 2000

In this study the classified researches the artificial and natural flaws in welding parts are performed using the pattern recognition technology. For this purpose the signal pattern recognition package including the user defined function was developed and the total procedure including the digital signal processing feature extraction feature selection and classifi-er selection is teated by bulk,. Specially it is composed with and discussed using the statistical classifier such as the linear discriminant function the empirical Bayesian classifier. Also the pattern recognition technology is applied to classifica-tion problem of natural flaw(i.e multiple classification problem-crack lack of penetration lack of fusion porosity and slag inclusion the planar and volumetric flaw classification problem), According to this result it is possible to acquire the recognition rate of 83% above even through it is different a little according to domain extracting the feature and the classifier.

• Journal of the Korean Society for Precision Engineering
• /
• v.19 no.1
• /
• pp.158-164
• /
• 2002

This paper proposes the optimization of ultrasonic signal recognition in ferrite carbon steel weld zone using neural networks. For these purposes, the ultrasonic signals for defects as porosity, incomplete penetration and slag inclusion in the weld zone are acquired in the type of time series data. And then their applications evaluated feature extraction based on the time-frequency-attractor domain(peak to peak, rise time, rise slope, fall time, fall slope, pulse duration, power spectrum, and bandwidth) and attractor characteristics (fractal dimension and attractor quadrant) etc. The proposed neural networks system in this study can enhances performance of ultrasonic signal recognition.

• Journal of Welding and Joining
• /
• v.2 no.2
• /
• pp.29-37
• /
• 1984

발전설비를 비롯한 산업설비, 각종 압력용기 및 철구조물 제작시 발생하는 여러가지의 용접불량 중에서 슬래그 혼입이 차지하는 비율이 전체 불량의 절반 이상을 차지하고 있다. 특히 여타의 용접법에 비해 SMAW에 의한 슬래그 혼입의 발생이 가장 많으므로 이에 대한 결함 발생의 경향을 조사하고 그 방지대책을 설정하기 위하여 이번 실험을 실시하게 되었다. 수동 용접봉의 피복제 중 가스 발생 원인은 아아크 분위기를 생성하고 기타 부분은 슬래그가 되어 용융금속을 둘러싸서 이것을 보호하면서 용융지로 이행한다. 슬래그는 용융지 내에서 비이드 표면으로 부상하면서 탈산반응이나 불순물을 제거하는 정련작용을 한다. 또한 적당한 합금 원소의 보충, 용융금속의 유동성 증가 등에 의하여 양호한 용착금속의 생성을 돕는다. 한편, 슬래그는 고온금속을 덮어 이것을 보호함과 동시에 급냉을 완화하는 작용을 한다. 그러나 이러한 슬래그가 응고하는 용착금속 사이에 혼입된다면 용착금속의 기계적 성질을 저하시키는 중요한 요인이 된다. 슬래그 혼입에 대하여 간단하고 일반적인 방지대책은 많이 언급되어 있으나 슬래그 혼입의 방지대책에 대해 깊이 있는 연구가 거의 없다. 이번 실험에서는 광범위한 요인의 선제, 싯수의 제안으로 인하여 새로운 슬래그 혼입 기구의 설정이나 특정한 요인의 영향에 대한 정확한 한계치의 설정보다는 각 요인에 대한 정성적인 영향을 분석하였다.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.20 no.4
• /
• pp.1309-1319
• /
• 1996

The research for the classification of the natural defects in welding zone is performd using the neuro-pattern recognition technology. The signal pattern recognition package including the user's defined function is developed to perform the digital signal processing, feature extraction, feature selection and classifier selection, The neural network classifier and the statistical classifiers such as the linear discriminant function classifier and the empirical Bayesian calssifier are compared and discussed. The neuro-pattern recognition technique is applied to the classificaiton of such natural defects as root crack, incomplete penetration, lack of fusion, slag inclusion, porosity, etc. If appropriately learned, the neural network classifier is concluded to be better than the statistical classifiers in the classification of the natural welding defects.

• Resources Recycling
• /
• v.30 no.1
• /
• pp.14-25
• /
• 2021

As a demand of high-end steel raises, the importance of secondary refinement process also increases. However, the content of each component in molten steel, slag and inclusions change with the time, meaning the secondary refinement process is not an equilibrium state. Furthermore, many reactions occur between molten steel, slag, inclusion, refractory and alloying element during secondary refinement process. In order to consider the above complex reactions with non-equilibrium state, a few researchers developed kinetic models in secondary refinement process based on the experimental numerical equations. It is important to analyze and review to the previously reported models to develop a precise model. Therefore, in present study, the complex reaction models based on kinetic in secondary refinement process were analyzed, reviewed, and introduced. Moreover, the single reaction models also introduced which would be applied to the complex reaction models.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 1995.10a
• /
• pp.393-396
• /
• 1995

In this syudy, the researches classifying the artificial and natural flaws in welding parts are performed using the smart pattern recognition technology. For this purpose the smart signal pattern recognition package including the user defined function was developed and the total procedure including the digital signal processing,feature extraction , feature selection and classifier selection is treated by bulk. Specially it is composed with and discussed using the statistical classifier such as the linear disciminant function classifier, the empirical Bayesian classifier. Also, the smart pattern recognition technology is applied to classification problem of natural flaw(i.e multiple classification problem-crack,lack of penetration,lack of fusion,porosity,and slag inclusion, the planar and volumetric flaw classification problem). According to this results, if appropriately learned the neural network classifier is better than ststistical classifier in the classification problem of natural flaw. And it is possible to acquire the recognition rate of 80% above through it is different a little according to domain extracting the feature and the classifier.

• Journal of Welding and Joining
• /
• v.16 no.5
• /
• 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.

• Advances in concrete construction
• /
• v.6 no.1
• /
• pp.29-45
• /
• 2018

This paper investigates the effect of inclusion of glass fibers on mechanical and fracture properties of binary blend geopolymer concrete produced by using fly ash and ground granulated blast furnace slag. To study the effect of glass fibers, the mix design parameters like binder content, alkaline solution/binder ratio, sodium hydroxide concentration and aggregate grading were kept constant. Four different volume fractions (0.1%, 0.2%, 0.3% and 0.4%) and two different lengths (6 mm, 13 mm) of glass fibers were considered in the present study. Three different notch-depth ratios (0.1, 0.2, and 0.3) were considered for determining the fracture properties. The test results indicated that the addition of glass fibers improved the flexural strength, split tensile strength, fracture energy, critical stress intensity factor and critical crack mouth opening displacement of geopolymer concrete. 13 mm fibers are found to be more effective than 6 mm fibers and the optimum dosage of glass fibers was found to be 0.3% (by volume of concrete). The study shows the enormous potential of glass fiber reinforced geopolymer concrete in structural applications.

• Journal of Advanced Marine Engineering and Technology
• /
• v.23 no.3
• /
• pp.331-337
• /
• 1999

Cracks on the cylinder block of diesel engines will often happen due to cyclic load and thermal stress. According to the Classification Societies' rules welding reparis of cylinder block made of cast irons are generally not permitted. However such welding repairs became inevitable taking enormous cost and time for their renewal into consideration. In this study repair welding methods for the clinder blocks made of gray cast irons were reviewed and the tests of their welds were carried out in order to purpose the repair welding meth-ods of packing seat and o-ring seat of cylinder block and apply them to the practice. The following conclusions are botained :1 The tensile strength of weld of cast iron more than that of base metal can be obtained by means of preheating keeping temperature above $100^{\circ}C$ between welding pass-es preventing slag inclusion peening and cramping weld metal by studs. 2. The suspected crack by a magnetic particle test due to different magnetic permeability can be identified which are not associated with a mechanical discotinuity.

• Advances in concrete construction
• /
• v.8 no.4
• /
• pp.305-309
• /
• 2019

Pervious concrete pavements are the need of the day to avoid urban flooding and to facilitate ground water recharge. However, the strength of pervious or porous concrete is considerably less compared to conventional concrete. In this experimental investigation, an effort is made to improve the strength of pervious concrete by adopting fibres and a small amount of fine aggregate. A porous concrete with cement to aggregate ratio of 1:5 and a water-powder ratio of 0.4 is adopted. 30% of the cement is replaced by cementitious material ground granulated blast furnace slag (GGBS) for better strength and workability. Recron fibres at a dosage of 0.5, 1.0 and 1.5% by weight of cement were included to improve the impact strength. Since concrete pavements are subjected to impact loads, the impact strength was also calculated by "Drop ball method" in addition to compressive strength. The effect of fine aggregate and recron fibres on workability, porosity, compressive and impact strength was studied. The investigations have shown that 20% inclusion of fine aggregate and 1.5% recron fibres by weight of cement give better strength with an acceptable range of porosity.