• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.66 no.7
• /
• pp.1100-1104
• /
• 2017

A detector-based approach shows the limited performances for the defect inspections such as shallow fine cracks and indistinguishable defects from background. Deep learning technique is widely used for object recognition and it's applications to detect defects have been gradually attempted. Deep learning requires huge scale of learning data, but acquisition of data can be limited in some industrial application. The possibility of applying CNN which is one of the deep learning approaches for surface defect inspection is investigated for industrial parts whose detection difficulty is challenging and learning data is not sufficient. VOV is adopted for pre-processing and to obtain a resonable number of ROIs for a data augmentation. Then CNN method is applied for the classification. Three CNN networks, AlexNet, VGGNet, and mofified VGGNet are compared for experiments of defects detection.

• Journal of Korea Water Resources Association
• /
• v.55 no.spc1
• /
• pp.1177-1185
• /
• 2022

The water and sewage system is an infrastructure that provides safe and clean water to people. In particular, since the water and sewage pipelines are buried underground, it is very difficult to detect system defects. For this reason, the diagnosis of pipelines is limited to post-defect detection, such as system diagnosis based on the images taken after taking pictures and videos with cameras and drones inside the pipelines. Therefore, real-time detection technology of pipelines is required. Recently, pipeline diagnosis technology using advanced equipment and artificial intelligence techniques is being developed, but AI-based defect detection technology requires a variety of learning data because the types and numbers of defect data affect the detection performance. Therefore, in this study, various defect scenarios are implemented using 3D printing model to improve the detection performance when detecting defects in pipelines. Afterwards, the collected images are performed to pre-processing such as classification according to the degree of risk and labeling of objects, and real-time defect detection is performed. The proposed technique can provide real-time feedback in the pipeline defect detection process, and it would be minimizing the possibility of missing diagnoses and improve the existing water and sewerage pipe diagnosis processing capability.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.33 no.11
• /
• pp.1256-1261
• /
• 2009

Today, implementation of the defect detection in laser welding has been researched for a long time, but most studies have been made around thin plate within $1{\sim}3mm^t$. Therefore, this study was measured and analyzed light emission signals of the induced plasma in $CO_2$ laser lap welding of $6mm^t$ Zn primer-coated steel, and based on this analysis, research made an investigation into possibility of monitoring in thick plate welding. It was been analyzing the measured signals by RMS and FFT processing, as a results, we were able to confirm definite difference of two signals between humping bead and sound bead. Thus, possibility of real time monitoring in $CO_2$ laser lap welding verified experimentally.

• Proceedings of the Computational Structural Engineering Institute Conference
• /
• 1998.10a
• /
• pp.61-68
• /
• 1998

It has become important to evaluate the qualitive reliability and condition assessment of existing structural systems in order to establish a rational program for repair and maintenance. Since most of if existing structural system may suffer from defect corrosion and damage, it is necessary to account for their effects in fuzzy reliability analysis, In this paper, an attempt is made to develope a reliability analysis for damaged structural systems using failure possibility theory. Damage state is specified in terms of linguistic valiables using natural language information and numerical information, which are defined by fuzzy sets. Using a subjective condition index of failure possibility and information of the damage state is introduced into the calculation of failure probability. The subjective condition index of quantitative and qualitative analysis method is newly proposed based on the fuzzy set operations, namely logical product, drastic product, logical sum and drastic sum

• The Journal of the Korean dental association
• /
• v.36 no.4 s.347
• /
• pp.289-295
• /
• 1998

Toothash and Plaster of Paris(Calcium sulfate) mixture have been studied for development of new biomaterial since 1992. I have performed the experimental and clinical study for evaluation of biocompatibility and possibility of bony defect reconstruction and clinical application. These materials are biocompatible, osteoconductive and resorbable. Main component of toothash is hydroxylapatite. In the future, I will perform the systematic construction of material and additional research.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 1996.04a
• /
• pp.242-246
• /
• 1996

Accurate measurements of burr profile and burr size are very important for the automation of deburring. In this paper, a new burr measurement system using capacitance sensor is proposed. Ultra precision milling machine was used as a sensor positioning system. The possibility and limitation of employing a capacitance sensor to defect burrs are also investigated. The proposed system is proven to be relatively accurate, easy to setup and lower cost. This system will be applicable to a fully automated deburring system with minor modifications.

• Journal of the Korean Ceramic Society
• /
• v.37 no.7
• /
• pp.726-729
• /
• 2000

The entitled report revealed that ZnO phosphor samples treated at different temperatures under a given reduction atmosphere show the radiation brightness increase with increase of temperature up to about 900$^{\circ}C$ but become decreasing beyond the temperature. The brightness deterioration with curing temperature at higher temperatures was explained by the decrease of excess zinc ions resulted from their evaporation. The comments will open possibility for different discussions on the experimental result by introducing numerical relationships between the concentration of the native defects and the curing condition.

• The Journal of Korean Academy of Prosthodontics
• /
• v.43 no.6
• /
• pp.736-744
• /
• 2005

Statement of problem. Initial stability of implant is an important factor for predicting osseointegration. It requires a rapid, non-invasive, user-friendly technique to frequently assess the implant stability and the degree of osseointegration. Purpose. The aim of this study was to evaluate the correlation between the resonance frequency analysis (RFA) and the radiographic method for peri-implant bone change under in vitro conditions. Material and Method. Twenty implants of 3.75 mm in diameter(Neoplant, Neobiotech, Korea) were used. To simulate peri-implant bone change, 2 mm-deep $45^{\circ}$ range horizontal defect and 2 mm-deep $90^{\circ}$ range horizontal defect area were serially prepared perpendicular to the X-ray beam after conventional implant insertion. Customized film holding device was fabricated to standardize the projection geometry for serial radiographs of implants and direct digital image was obtained. ISQ values and gray values inside threads were measured before and after peri-implant bone defect preparation. Results. Within a limitation of this study, ISQ value of resonance frequency analysis was changed according to peri-implant bone change (p<0.05) and gray value of radiographic method was changed according to peri-implant bone change (p<0.05). There was no correlation between the ISQ value and the gray value for peri-implant bone change (p>0.05). But, in horizontal defect condition, relatively positive correlation were between ISQ and gray values(r=0.663). Conclusion. This results provided a possibility that peri-implant bone change may be evaluated by both RFA and radiographic method.

• Journal of the Korea Institute of Building Construction
• /
• v.17 no.4
• /
• pp.385-391
• /
• 2017

The warranty liability period for defects in apartment buildings by work type is not based on scientific analysis, making the appropriateness of the term a culprit behind the lawsuits. Therefore, this research aims to evaluate the appropriateness of the warranty liability term of apartment buildings by identifying the current status of defects, in particular, caused by finishing works. That is because the number of defects, caused during the finishing works, accounted for the largest portion of the total defect cases of apartment buildings reported to the Apartment Defect Dispute Mediation Committee under the Ministry of Land, Infrastructure, and Transport of Korea between 2010 and 2011. The result from analyzing claims for defect repairs of the finishing works showed that most cases by work type continued to be made after two years, and only about 60% were charged within the warranty period. And, defects by work type have correlation, which needs to be considered for a better construction technique. Considering a low correlation between the possibility of defects and the construction performance rankings, which are highly relevant to the apartment preference. It is believed that there needs to be a qualification process for agencies that actually performs finishing works.

• Journal of Applied Reliability
• /
• v.18 no.1
• /
• pp.87-94
• /
• 2018

Purpose: In this study, the defect quantification of thin metal plate was evaluated by using lock-in infrared thermography. Methods: A STS304 standard specimens, which had the artificial-defects of different size, were used. The focal distance between the infrared camera and the specimen was set to 500mm, and the distance between the lump and the specimen was set to 200mm. One halogen lamp with a maximum capacity of 1kW was used, and phase-lock infrared thermal images with a frequency of 1Hz were captured and analyzed. Result: Objectively quantified data values were obtained by analyzing the contrast ratio and signal-to-noise ratio. Conclusion: The possibility of defect diagnosis for thin metal plate was confirmed by using the lock-in infrared thermography technique.