• Journal of the Korean Society for Heat Treatment
• /
• v.12 no.3
• /
• pp.215-220
• /
• 1999

Rotary bending fatigue tests were carried out to investigate the artificial defect sensitivity of fatigue limit in annealed and austempered ductile irons. Artificial defect(hole, diameter${\leq}0.4mm$) machined on specimen surface did not bring about an obvious reduction of fatigue limit in austempered ductile iron as compared with annealed. As a result of investigation on $\sqrt{area}$ c which is the critical artificial defect size. $\sqrt{area}$ c of austempered ductile iron is larger than that of annealed. This means that the crack initiation at artificial defect in austempered ductile iron is more difficult in comparison with annealed. In case that the $\sqrt{area}$ c of artificial defect and graphite nodule are same, the rate of crack initiation for graphite nodule is higher than that of artificial defect.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.23 no.11 s.170
• /
• pp.1922-1928
• /
• 1999

Rotary bending fatigue tests were carried out to investigate the influence of artificial defects on fatigue limit in annealed and austempered ductile iron. Obtained main results are as follows : (1) Artificial defect(micro hole type, dia.<0.4 mm) on specimen surface did not bring about a obvious reduction of fatigue limit in austempered ductile iron(ADI) as compared with annealed ductile iron. (2) According to the investigation of $\sqrt{area}_c$ which is the critical defect size to crack initiation at artificial defect, $\sqrt{area}_c$ of ADI is larger than that of annealed ductile iron. This shows that the situation of crack initiation at artificial defect in ADI is more difficult in comparison with annealed ductile iron. (3) One of the reasons for the low rate of crack initiation from artificial defect in ADI is that the resistance of matrix to crack initiation is higher than that of annealed ductile iron. (4) In case that the $\sqrt{area}$ of artificial defect and graphite nodule is the same, the rate of crack initiation from graphite nodule is higher than that from artificial defect. This reason is that the serious ruggedness around graphite nodule is formed by austempering treatment.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.7 no.5
• /
• pp.221-229
• /
• 1999

We examined the governing factors of fatigue limit in annealed and austempered ductile iron specimens machined micro hole(dia.<0.4mm) in rotary bending fatigue test. Also, the quantitative relationship between fatigue limit and maximum defect size in specimens was investigated. Artificial defect(micro-pit type, dia.<0.4mm) on specimen surface did not bring about an obvious reduction of fatigue limit in austempered ductile iton(ADI) as compared with annealed ductile iron. According to the investigation of ${\sqrt{area}}_c$ which is the critical defect size to crack initiation at artificial defect, ${\sqrt{area}}_c$ of ADI was larger than that of annealed ductile iron. This shows that the situation of crack initiation at artificial defect in ADI is more difficult in comparison with annealed ductile iron. Maximum defect size is one of the important parameters to predict fatigue limit. And, the quantitative relationship, between the fatigue limit ${\sigma}_{\omega}$ and the maximum defect size ${\sqrt{area}}_{max}$ can be expressed to ${\sigma}_{\omega}^n{\cdot}{\sqrt{area}}_{max}=C_2$ where, $C_2$ are constant. Moreover, it is possible to explain the difference in fatigue limit between, austempered and annealed ductile iron by introducing the parameter ${\delta}(=N_{sg}/N_{total})$in a plain spectimen.

• Journal of Ocean Engineering and Technology
• /
• v.3 no.2
• /
• pp.601-601
• /
• 1989

The behavior of fatigue was studied by using low carbon steel bar with microhole(artificial small defect) under the condition of rotary bending stress which is made artificially at smooth surface and round notch root. The results obtained can be summerized; The behavior of non-propagating cracks which are produced at both tips of small defect occurred to dissymmetry, and it is found to be double size of small defect. For the range of l>lc, threshold stress intensity is constant. However, for the range of l

• Journal of Ocean Engineering and Technology
• /
• v.3 no.2
• /
• pp.101-107
• /
• 1989

The behavior of fatigue was studied by using low carbon steel bar with microhole(artificial small defect) under the condition of rotary bending stress which is made artificially at smooth surface and round notch root. The results obtained can be summerized; The behavior of non-propagating cracks which are produced at both tips of small defect occurred to dissymmetry, and it is found to be double size of small defect. For the range of l>lc, threshold stress intensity is constant. However, for the range of l

• Journal of the Korean Ceramic Society
• /
• v.41 no.5
• /
• pp.406-409
• /
• 2004

A blue phosphor(ZnS:Cu) is manufactured by solid state reaction for ACPEL(AC powder EL). The effect of artificial defect on phosphor surface on the ZnO phase conversion and resulting luminescence have been studied. It was found that ZnS:Cu could converse to cubic phase more easily due to the formation of artificial defect on 1st fired phosphor by ball-milling process, resulting in improvement of luminescence of phosphor phosphors under the driven EL condition. We found out an optimized ball-mill condition through considering effect of each ball-mill conditions such as milling time and milling rpm on defect. Also we determined relationship between emission luminescence and phase of phosphor based on analyses of crystal structures of phosphors. A significant improvement above 30% was observed in electroluminescence by the artificial defect on ZnS:Cu phosphors compared to non-treated phosphors.

• Proceedings of the Korean Society of Propulsion Engineers Conference
• /
• 2006.05a
• /
• pp.209-212
• /
• 2006

In this study, Support Vector Machine(SVM) and Artificial Neural Network(ANN) are used for developing the defect diagnostic algorithm of the aircraft turbo-shaft engine. Effect of altitude variation on the Defect Diagnostics algorithm has been included and evaluated. Separate learning Algorithm(SLA) suggested with ANN to loam the performance data selectively after classifying the position of defects by SVM improves the classification speed and accuracy.

• Journal of the Korean Society of Propulsion Engineers
• /
• v.11 no.1
• /
• pp.43-50
• /
• 2007

In this study, Hybrid Separate Learning Algorithm(SLA) consisting of Support Vector Machine(SVM) and Artificial Neural Network(ANN) has been used for developing the defect diagnostic algorithm of the aircraft turbo-shaft engine in the off-design range considering altitude variation. Although the number of teaming data and test data highly increases more than 6 times compared with those required for the design condition, the proposed defect diagnostics of gas turbine engine using SLA was verified to give the high defect classification accuracy in the off-design range considering altitude variation.

• Proceedings of the Korean Society of Propulsion Engineers Conference
• /
• 2008.11a
• /
• pp.23-27
• /
• 2008

In this study, Real Coded Genetic Algorithm(RCGA) and Artificial Neural Network(ANN) are used for developing the defect diagnostics of the aircraft turbo-shaft engine. ANN accompanied with large amount data has a most serious problem to fall in the local minima. Because of this weak point, it becomes very difficult to obtain good convergence ratio and high accuracy. To solve this problem, GA based ANN has been suggested. GA is able to search the global minima better than ANN. GA based ANN has shown the RMS defect error of 5% less in single and dual defect cases.

• Journal of the Semiconductor & Display Technology
• /
• v.22 no.2
• /
• pp.40-44
• /
• 2023

The defect detection based on deep learning requires minimal loss and high accuracy to pinpoint product defects. In this paper, we confirm the loss rate of deep learning training based on disc-shaped artificial scaffold images. It is intended to compare the performance of Cross-Entropy functions used in object detection algorithms. The model was constructed using normal, defective artificial scaffold images and category cross entropy and sparse category cross entropy. The data was repeatedly learned five times using each loss function. The average loss rate, average accuracy, final loss rate, and final accuracy according to the loss function were confirmed.