• Journal of Institute of Control, Robotics and Systems
• /
• v.2 no.4
• /
• pp.337-343
• /
• 1996

In this paper, we investigate the defect detection by making use of pre-made reference image data and classify the defects by using the artificial neural network. The approach is composed of three main parts. The first step consists of a proper generation of two reference image data by using a low level morphological technique. The second step proceeds by performing three times logical bit operations between two ready-made reference images and just captured image to be tested. This results in defects image only. In the third step, by extracting four features from each detected defect, followed by assigning them into the input nodes of an already trained artificial neural network we can obtain a defect class corresponding to the features. All of the image data are formed in a bit level for the reduction of data size as well as time saving. Experimental results show that proposed algorithms are found to be effective for flexible defect detection, robust classification, and high speed process by adopting a simple logic operation.

• Journal of Korean Foot and Ankle Society
• /
• v.9 no.2
• /
• pp.224-226
• /
• 2005

In diabetic foot with arterial occlusive disease, skin defect on heel was tried to treat with free flap or local flap, but couldn't be treated well. Therefore below knee amputation was perfomed mostly. But we treated a patient of large heel defect with using of artificial bypass graft and antero-lateral thigh perforator flap.

• Journal of the Korean Society of Manufacturing Technology Engineers
• /
• v.6 no.2
• /
• pp.76-82
• /
• 1997

The discrimination of flaw shape and sizing is very important subject in the material evaluation for semiconductor and new materials. The aim of this paper is to investigate the spectrum analysis of artificial defect signal captured from steel ball embedded in the resin. The results show that it can be evaluated quantitatively the size of artificial defect, from the amplitude variation of same frequency if the probe with same diameter and focal length is used. Comparing with the amplitude variation of the high frequency component and low frequency component obtained from the distance of defect center position, it can be estimated steel ball and flat bottm defect.

• Journal of Welding and Joining
• /
• v.16 no.3
• /
• pp.64-73
• /
• 1998

This paper is concerned with defects detection and evaluation of heat affected zone (HAZ) in austenitic stainless steel type 304 by ultrasonic wave and neural network. In experiment, the reflected ultrasonic defect signals from artificial defects (side hole, vertical hole, notch) of HAZ appears as beam distance of prove-defect, distance of probe-surface, depth of defect-surface on CRT. For defect classification simulation, neural network system was organized using total results of ultrasonic experiment. The organized neural network system was learned with the accuracy of 99%. Also it could be classified with the accuracy of 80% in side hole, and 100% in vertical hole, 90% in notch about ultrasonic pattern recognition. Simulation results of neural network agree fairly well with results of ultrasonic experiment. Thus were think that the constructed system (ultrasonic wave - neural network) in this work is useful for defects dection and classification such as holes and notches in HAZ of austenitic stainless steel 304.

• Journal of the korean Society of Automotive Engineers
• /
• v.11 no.1
• /
• pp.51-56
• /
• 1989

This study was performed to investigate the effect of defect on fatigue strength under the stress of rotary bending. The specimens were made of low carbon steel having artificial microholes, namely, single micro-hole and two adjacent micro-holes as natural defects, and the effects of the diameter of hole and the distance between the holes on fatigue strength have been investigated. The obtained result can be summarized as follows: 1, The critical defect means the largest size of defect that does not affect fatigue limit, and correspondes to the size of defect leading to final fracture under fatigue limit of smooth specimen. The size of defect which has an effect on fatigue limit is larger than that of critical defect. 2, The defect larger than the critical defect affects fatigue strength for as a kind of size effect, and the physical meaning of size effect of defect is considered same as the one of notch effect.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.6
• /
• pp.834-841
• /
• 2022

Recently, applying artificial intelligence technologies in various fields of production has drawn an upsurge of research interest due to the increase for smart factory and artificial intelligence technologies. A great deal of effort is being made to introduce artificial intelligence algorithms into the defect detection task. Particularly, detection of defects on the surface of metal has a higher level of research interest compared to other materials (wood, plastics, fibers, etc.). In this paper, we compare and analyze the speed and performance of defect classification by combining machine learning techniques (Support Vector Machine, Softmax Regression, Decision Tree) with dimensionality reduction algorithms (Principal Component Analysis, AutoEncoders) and two convolutional neural networks (proposed method, ResNet). To validate and compare the performance and speed of the algorithms, we have adopted two datasets ((i) public dataset, (ii) actual dataset), and on the basis of the results, the most efficient algorithm is determined.

• Proceedings of the Korean Society of Propulsion Engineers Conference
• /
• 2008.03a
• /
• pp.72-79
• /
• 2008

The weak point of the artificial neural network(ANN) is that it is easy to fall in local minima when it learns too much nonlinear data. Accordingly, the classification ratio must be low. To overcome this weakness, the hybrid method has been proposed. That is, the ANN learns data selectively after detecting the defect position by the support vector machine(SVM). First, the SVM has been used for determination of the defect position and then the magnitude of the defect has been measured by the ANN. In off-design condition, the operation region of the engine is wide and the nonlinearity of learning data increases. The module system, dividing the whole operating region into reasonably small-size sections, has been suggested to solve this problem. In this study, the proposed algorithm has diagnosed the defects of triple components as well as single and dual components of the gas turbine engine in off-design condition.

• Archives of Craniofacial Surgery
• /
• v.19 no.1
• /
• pp.35-40
• /
• 2018

Background: When a skin defect occurs, clinicians must work to restore the original skin quality as soon as possible. Accordingly, an artificial dermis can be used to supplement the wound and prevent severe scar contracture formation. The Terudermis is an artificial dermis that is simple and easy to use. We investigated the effectiveness of the Terudermis in the treatment of facial skin defects by analyzing previous relevant cases treated in our institution. Methods: We retrospectively examined 143 patients who were treated with the Terudermis graft in facial skin defect at Dong Kang General Hospital in 2015 and 2016. The patients' age, sex and location, wound size, complications were analyzed. In addition, the patients were asked to complete a self-satisfaction questionnaire after 18 months from the completion of treatment. The results were compared with that of autologous full-thickness skin graft (FTSG) and split-thickness skin graft (STSG) patients in same period. Results: The mean self-satisfaction scores evaluated by patients were $4.1{\pm}1.0$, $4.0{\pm}1.3$ and $3.5{\pm}1.8$ for the Terudermis graft, FTSG and STSG patients, respectively. With respect to complications, there were fewer incidences of hematoma, partial skin loss and complete skin loss in the Terudermis graft patients. Conclusion: In the present study, the Terudermis, when used to treat post-traumatic facial skin defects, is a good alternative option to obtain satisfactory aesthetic outcomes. Also, the Terudermis grafting is a simple and easy treatment method to perform.

• Journal of the Korean Institute of Gas
• /
• v.16 no.2
• /
• pp.18-24
• /
• 2012

This research seeks to evaluate damage on type II gas cylinder by an acoustic emission test when executing 20000 cycles fatigue test and thereafter burst test. Used gas cylinders in the experimental are three types as follows; one is sound cylinder, others are cylinders which contain longitudinal and transverse artificial defect. The size of artificial defect is a depth of 3 mm, width of 3 mm and length of 50 mm. In the case of the cylinder which artificial defect, unlike the expectation that it will burst in low pressure, the burst pressure of the cylinder did not differ much according to whether or not there were defects. However, when there was longitudinal defect, the location of burst was near the location of defect. This leads to the effect in which the thickness of the composite material becomes thinner according to the length of the longitudinal defect and this is judged to have an effect on the location of initiation and growth of crack in the liner. Also, for the acoustic emission signal, when there is longitudinal defect, the ratio of an event occurring at defect position among overall hits is more than 50 %, and the source location also accords very precisely with defect position.

• Journal of the Korean Society for Nondestructive Testing
• /
• v.15 no.2
• /
• pp.378-385
• /
• 1995

The ultrasonic non-destructive testing uses the directivity of the ultrasonic pulse wave which propagates in one direction. The directivity is expressed as the relationship between the propagate direction and its sound pressure. The directivity of ultrasonic wave is closely related to determination of probe arrangement, testing sensitivity, scanning pitch and defect location and characterization. The paper measured the directivity of shear wave, which reflected from artificial defect located in weld metal zone in butt welded joint similar model made of pyrex glass by using visualization method. 2 MHz and 4 MHz angle probes were used to measure the directivity of reflection wave at the artificial defect. The directivity of shear waves reflected from the defect was different according to the probe position and the shape of butt welded joint. The difference of directivity of reflection wave was existed between 2 MHz and 4 MHz angle probes. The angle of reflection wave became equal to angle of incidence as increase of the height of excess metal.