• 한국공작기계학회논문집
• /
• 제12권2호
• /
• pp.65-70
• /
• 2003

In this study, researchers developed the estimative algorithm for artificial defect in semiconductor packages and performed it by pattern recognition technology. For this purpose, the estimative algorithm was included that researchers made software with MATLAB. The software consists of some procedures including ultrasonic image acquisition, equalization filtering, Self-Organizing Map and Backpropagation Neural Network. Self-organizing Map and Backpropagation Neural Network are belong to methods of Neural Networks. And the pattern recognition technology has applied to classify three kinds of detective patterns in semiconductor packages : Crack, Delamination and Normal. According to the results, we were confirmed that estimative algerian was provided the recognition rates of 75.7% (for Crack) and 83.4% (for Delamination) and 87.2 % (for Normal).

• KIEE International Transactions on Electrophysics and Applications
• /
• 제5C권2호
• /
• pp.63-66
• /
• 2005

This paper describes analysis and pattern recognition techniques for Partial Discharge(PD) signals in Gas Insulated Switchgears (GIS). Detection of PD signals is one of the most important factors in the predictive maintenance of GIS. One of the methods of detection is electro magnetic wave detection within the Ultra High Frequency (UHF) band (300MHz $\~$ 3GHz). In this paper, PD activity simulation is generated using three types of artificial defects, which were detected by a UHF PD sensor installed in the GIS. The detected PD signals were performed on three-dimensional phi-q-n analysis. Finally, parameters were calculated and an Artificial Neural Network (ANN) was applied for PD pattern recognition. As a result, it was possible to discriminate and classify the defects.

• 제어로봇시스템학회논문지
• /
• 제14권5호
• /
• pp.444-452
• /
• 2008

This paper presents an overall image processing approach of defect inspection of patterned TFT-LCD panels for the real manufacturing process. A prototype of AOI(Automatic Optical Inspection) system which is composed of air floating stage and multi line scan cameras is developed. Adjacent pattern comparison algorithm is enhanced and used for pattern elimination to extract defects in the patterned image of TFT-LCD panels. New region merging algorithm which is based on border expansion is proposed to identify defects from the pattern eliminated defect image. Experimental results show that a developed AOI system has acceptable performance and the proposed algorithm reduces environmental effects and processing time effectively for applying to the real manufacturing process.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 2002년도 추계학술대회 논문집
• /
• pp.345-350
• /
• 2002

In this study, researchers classifying the artificial flaws in semiconductor packages are performed by pattern recognition technology. For this purposes, image pattern recognition package including the user made software was developed and total procedure including ultrasonic image acquisition, equalization filtration, binary process, edge detection and classifier design is treated by Backpropagation Neural Network. Specially, it is compared with various weights of Backpropagation Neural Network and it is compared with threshold level of edge detection in preprocessing method fur entrance into Multi-Layer Perceptron(Backpropagation Neural network). Also, the pattern recognition techniques is applied to the classification problem of defects in semiconductor packages as normal, crack, delamination. According to this results, it is possible to acquire the recognition rate of 100% for Backpropagation Neural Network.

• Nuclear Engineering and Technology
• /
• 제36권3호
• /
• pp.219-228
• /
• 2004

[1] and [2] present an approach to diagnosing possible defects in the mechanical systems of a nuclear power plant. In this paper, by using a fault library as a database and training data, we develop a diagnostic algorithm 1) to decide whether an Air Operated Valve system is sound or not and 2) to identify the defect from which an Air-Operated Valve system suffers, if any. This algorithm is composed of three stages: a neural net stage, a non-neural net stage, and an integration stage. The neural net stage is a simple perceptron, a pattern-recognition module, using a neural net. The non-neural net stage is a simple pattern-matching algorithm, which translates the degree of matching into a corresponding number. The integration stage collects each output and makes a decision. We present a simulation result and confirm that the developed algorithm works accurately, if the input matches one in the database.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 2005년도 추계학술대회 논문집
• /
• pp.721-726
• /
• 2005

In this study, researchers classifying the artificial flaws in semiconductor. packages are performed by pattern recognition technology. For this purposes, image pattern recognition package including the user made software was developed and total procedure including ultrasonic image acquisition, equalization filtration, binary process, edge detection and classifier design is treated by Backpropagation Neural Network. Specially, it is compared with various weights of Backpropagation Neural Network and it is compared with threshold level of edge detection in preprocessing method for entrance into Multi-Layer Perceptron(Backpropagation Neural network). Also, the pattern recognition techniques is applied to the classification problem of defects in semiconductor packages as normal, crack, delamination. According to this results, it is possible to acquire the recognition rate of 100% for Backpropagation Neural Network.

• 한국레이저가공학회지
• /
• 제2권3호
• /
• pp.19-31
• /
• 1999

This paper introduces the monitoring scheme of laser welding quality using neural network. The developed monitoring scheme detects light signal emitting from plasma formed above the weld pool with optic sensor and DSP-based signal processor, and analyzes to give a guidance about the weld quality. It can automatically detect defects of laser weld and further give an information about what kind of defects it is, specially partial penetration and porosity among the interior defects. Those could be detected only by naked eyes or X-ray after welding, which needs more processes and costs in mass production. The monitoring scheme extracts four feature vectors from signal processing results of optical measuring data. In order to classify pattern for extracted feature vectors and to decide defects, it uses single-layer neural network with perceptron learning. The monitoring result using only the first feature vector shows confidence rate in recognition of 90%($\pm$5) and decides whether normal status or defects status in real time.

• Nuclear Engineering and Technology
• /
• 제45권3호
• /
• pp.361-366
• /
• 2013

An imaging technique to visualize the internal defects in a plate-type nuclear fuel specimen was developed by using an active optical interferometer for a nondestructive quality inspection. A periodic thermal wave having a sinusoidal intensity pattern induced a periodical strain variation for the specimen. The varying strain image was acquired using an optical laser interferometer. The strain distribution over the internal defects will be distorted in an acquired strain image because a part of the thermal wave will be reflected from these defects during propagation. In this paper, internal defects were efficiently visualized by sequentially accumulating the extracted defect components. The experimental results confirmed that the developed visualization system can be a valuable tool to detect the internal defects in plate-type nuclear fuel.

• KIEE International Transactions on Electrophysics and Applications
• /
• 제2C권5호
• /
• pp.239-245
• /
• 2002

In this work, in order to realize the possible defects at the cable joint interface, four different types of artificial defects are provided : conducting, insulating substances, void and scratches. The analysis related to the PD patterns has been performed by means of conventional Phase Resolved Partial Discharge Analysis (PRPDA) and Chaotic Analysis of Partial Discharge (CAPD) as well which was proposed by our previous communication. As a result, it could be pointed out that each defect has shown particular characteristics in its pattern respectively and that the nature of defect causing partial discharge could be identified more distinctively when the CAPD is combined with the conventional statistic method, PRPDA.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 2001년도 춘계학술대회 논문집
• /
• pp.140-143
• /
• 2001

Digital shearography, a speckle pattern method is based on the superposition of two laterally sheared images. Therefore, object points which are positioned in some distance from each other are superposed in the image plane. This shearography, one of NDT methods without contact, is able to inspect defects in pipelines and pressure vessels that are used in nuclear power plants. This is can inspect whole fields and has a low sensitivity to environmental noise. Because optical setting is very simple, it has a little exhaustion of time, cost and man power. And also it can find a defect position through real time monitoring of a part. This paper, finds out the relationship among shearing quantity image quality and defect size with this method.