• Journal of the Korean Society for Precision Engineering
• /
• v.29 no.1
• /
• pp.48-55
• /
• 2012

Pressure vessels in vehicle industries, power plants, and chemical industries are often affected by flaw and defect generated inside the pressure vessels due to production processes or being used. It is very important to detect such internal defects of pressure vessel because they sometimes bring out serious problems. In this paper, an optical defect detection method using digital shearography is used. This method has advantages that the inspection can be performed at a real time measurement and is less sensitive to environmental noise. Shearography is a laser-based technique for full-field, non-contacting measurement of surface deformation (displacement or strain). The ultimate goal of this paper is to detect flaws in pressure vessels and to measure the lengths of the flaws by using unwrapping, phase images which are only obtained by Phase map. Through this method, we could decrease post-processing (next processing). Real length of a pixel can be calculated by comparing minimum and maximum unwrapping images with shearing angle. Through measuring several specimen defects which have different lengths and depths of defect, it can be possible to interpret quantitatively by calculating gray level.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.21 no.11
• /
• pp.2121-2127
• /
• 2017

In this paper, we propose a computer vision based automatic defect detection method from ceramic image for non-destructive testing. From region of interest of the image, we apply brightness enhancing stretching algorithm first. One of the strength of our method is that it is designed to detect defects of images obtained from various thicknesses, that is, 8, 10, 11, 16, and 22 mm. In other cases we apply histogram based binarization algorithm. However, for 8 mm case, it may have false positive cases due to weak brightness contrast between defect and noise. Thus, we apply modified fuzzy binarization algorithm for 8 mm case. From the experiment, we verify that the proposed method shows stronger result than our previous study that used Blob labelling for all five thickness cases as expected.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.17 no.8
• /
• pp.1899-1907
• /
• 2013

This paper presents an efficient defect detection and classification system based on reference image for COF (Chip-on-Film) which encounters fatal defects after ultra fine pattern fabrication. These defects include typical ones such as open, mouse bite (near open), hard short and soft short. In order to detect these defects, conventionally it needs visual examination or electric circuits. However, these methods requires huge amount of time and money. In this paper, based on reference image, the proposed system detects fatal defect and efficiently classifies it to one of 4 types. The proposed system includes the preprocessing of the test image, the extraction of ROI, the analysis of local binary pattern and classification. Through simulations with lots of sample images, it is shown that the proposed system is very efficient in reducing huge amount of time and money for detecting the defects of ultra fine pattern COF.

• Journal of the Korea Institute of Building Construction
• /
• v.11 no.5
• /
• pp.459-467
• /
• 2011

The work of constructing apartment housing involves various fields of industry that are linked to each other, and is based on a design document prepared by multiple technicians and architects. Consequently, design errors, material flaws or faulty construction works can cause defects, which sometimes overlap with each other. Construction companies should repair any defects found in a completed building within a specified period of time, and to do this, should establish a business plan by efficiently predicting the cost of defect repair. As it is very difficult for companies to accurately predict the occurrence of defects, historical performance data is used as a base. For domestic apartment housing units, data on the cost of defect repair is insufficient, so there are hardly any methods that can be used to make precise predictions. Therefore, the intent of this study is to develop a model that can predict the cost of defect repair by supply type and area, based on historical performance data with ten years worth of post-completion.

• Journal of the Korean Institute of Electrical and Electronic Material Engineers
• /
• v.27 no.12
• /
• pp.831-836
• /
• 2014

One-dimensional (1D) photonic crystals (PCs) were prepared by $TeO_x(2<x<3)/SiO_2$ with the difference refractive index, and fabricated by sputtering technique from a $TeO_2$ and $SiO_2$ target. The $TeO_x$(2$Ar:O_2=40:10$). A 10-pair $TeO_x(2<x<3)/SiO_2$ 1D PCs were fabricated with the structure parameters of filling factor=0.5185, and period=410 nm. The properties of 1D PCs with and without a defect layer were evaluated by UV-VIS-NIR. A normal mode 1D PC have a photonic band gap (PBG) in the near infrared (NIR) region from 1,203 to 1,421 nm. In the case of 1D PC containing a defect layer, a defect level appears at 1,291 nm. The measured transmittance (T) spectra are nearly corresponding to calculated results. After He-Cd laser exposure, the defect level is shifted from 1,291 nm to 1,304 nm.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.46 no.3
• /
• pp.139-147
• /
• 2023

The metal bush assembling process is a process of inserting and compressing a metal bush that serves to reduce the occurrence of noise and stable compression in the rotating section. In the metal bush assembly process, the head diameter defect and placement defect of the metal bush occur due to metal bush omission, non-pressing, and poor press-fitting. Among these causes of defects, it is intended to prevent defects due to omission of the metal bush by using signals from sensors attached to the facility. In particular, a metal bush omission is predicted through various data mining techniques using left load cell value, right load cell value, current, and voltage as independent variables. In the case of metal bush omission defect, it is difficult to get defect data, resulting in data imbalance. Data imbalance refers to a case where there is a large difference in the number of data belonging to each class, which can be a problem when performing classification prediction. In order to solve the problem caused by data imbalance, oversampling and composite sampling techniques were applied in this study. In addition, simulated annealing was applied for optimization of parameters related to sampling and hyper-parameters of data mining techniques used for bush omission prediction. In this study, the metal bush omission was predicted using the actual data of M manufacturing company, and the classification performance was examined. All applied techniques showed excellent results, and in particular, the proposed methods, the method of mixing Random Forest and SA, and the method of mixing MLP and SA, showed better results.

• Archives of Plastic Surgery
• /
• v.32 no.4
• /
• pp.467-473
• /
• 2005

Calvarial bone grafting in craniomaxillofacial trauma and facial reconstructive surgery is now widely recognized and accepted as a standard procedure. One of the commonly reported problems of calvarial bone graft is the contour defect caused by partial resorption of the graft. But, there are few reports that discuss the fate of the calvarial bone graft based on the quantitative data. In this article, the changes of grafted calvarial bone were evaluated using 3-dimensional computed tomography(CT). 9 patients were observed with the CT scans at 2mm thickness immediately after operation and at the time of last follow-up. The area of the bone defect was segmented on the 3-dimensional CT image and calculated by AnalyzeDirect 5.0 software. The immediate postoperative bone defect area of the recipient site and the donor site were $612.9mm^2$ and $441.5mm^2$, respectively, which became $1028.1mm^2$ and $268.8mm^2$, respectively at the last follow-up. In conclusion, the bone defect area was less increased on the donor site of calvarial bone graft than on the recipient site. And the CT scan is a valuable imaging method to assess and follow-up the clinical outcome of calvarial bone grafting.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.32 no.2C
• /
• pp.37-47
• /
• 2012

In this study, three centrifuge tests were performed to evaluate the feasibility of three physical quantities for detecting internal defect of earth core fill dam: pore water pressure, temperature, and electrical resistance. For this purpose, the measurement system for pore water pressure, temperature and electrical resistance on centrifuge model dams was established. Three centrifuge tests included a fill dam without internal defect and two other dams with artificial internal defect in the core. The effectiveness of seepage monitoring was examined during the centrifuge test. Test results showed the applicability of monitoring techniques to detect internal defect by monitoring pore water pressure, temperature, and electrical resistance.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.49 no.1
• /
• pp.8-11
• /
• 2012

Automated Vision Inspection (AVI) systems automatically detect any defect feature in a surface image. The performance of the system can be measured under a special circumstances such as ultimate defect detection. In this situation, the defect signal level is similar to noise level and it becomes hard to make a solid decision with AVI systems. In this paper, we propose an effective preprocessing technique to enhance SNR (Signal to Noise Ratio). The method is motivated by some principles of HVS (Human Visual System) and RLC (Run Length Coding) techniques is used for this purpose. The proposed preprocessing technique enhances SNR under ultimate defect conditions and improves overall performance of AVI system.

• KIPS Transactions on Software and Data Engineering
• /
• v.10 no.9
• /
• pp.339-348
• /
• 2021

In recent software defect prediction research, defect prediction between cross projects and cross-version projects are actively studied. Cross-version defect prediction studies assume WP(Within-Project) so far. However, in the CV(Cross-Version) environment, the previous work does not consider the distribution difference between project versions is important. In this study, we propose an automated Bayesian optimization framework that considers distribution differences between different versions. Through this, it automatically selects whether to perform transfer learning according to the difference in distribution. This framework is a technique that optimizes the distribution difference between versions, transfer learning, and hyper-parameters of the classifier. We confirmed that the method of automatically selecting whether to perform transfer learning based on the distribution difference is effective through experiments. Moreover, we can see that using our optimization framework is effective in improving performance and, as a result, can reduce software inspection effort. This is expected to support practical quality assurance activities for new version projects in a cross-version project environment.