• Journal of the Semiconductor & Display Technology
• /
• v.23 no.2
• /
• pp.135-142
• /
• 2024

Cu-Cu bonding, one of the key technologies in advanced packaging, enhances semiconductor chip performance, miniaturization, and energy efficiency by facilitating rapid data transfer and low power consumption. However, the quality of the interface bonding can significantly impact overall bond quality, necessitating strategies to quickly detect and classify in-process defects. This study presents a methodology for detecting defects in wafer junction areas from Scanning Acoustic Microscopy images using a ResNet-50 based deep learning model. Additionally, the use of the defect map is proposed to rapidly inspect and categorize defects occurring during the Cu-Cu bonding process, thereby improving yield and productivity in semiconductor manufacturing.

• Journal of Korea Multimedia Society
• /
• v.13 no.8
• /
• pp.1115-1127
• /
• 2010

In order to increase the productivity in manufacturing TFT-LCD(thin film transistor-liquid crystal display), it is essential to classify defects that occur during the production and make an appropriate decision on whether the product with defects is scrapped or not. The decision mainly depends on classifying the defects accurately. In this paper, we present an effective classification method for film defects acquired in the panel production line by analyzing the intensity distribution and shape feature of the defects. We first generate a binary image for each defect by separating defect regions from background (non-defect) regions. Then, we extract various features from the defect regions such as the linearity of the defect, the intensity distribution, and the shape characteristics considering intensity, and construct a referential image database that stores those feature values. Finally, we determine the type of a defect by matching a defect image with a referential image in the database through the matching cost function between the two images. To verify the effectiveness of our method, we conducted a classification experiment using defect images acquired from real TFT-LCD production lines. Experimental results show that our method has achieved highly effective classification enough to be used in the production line.

• Journal of the Semiconductor & Display Technology
• /
• v.20 no.1
• /
• pp.99-103
• /
• 2021

Warpage defect detecting of scaffold is very important in biosensor production. Because warpaged scaffold cause problem in cell culture. Currently, there is no detection equipment to warpaged scaffold. In this paper, we produced detection model for shape warpage detection using deep learning based CNN. We confirmed the shape of the scaffold that is widely used in cell culture. We produced scaffold specimens, which are widely used in biosensor fabrications. Then, the scaffold specimens were photographed to collect image data necessary for model manufacturing. We produced the detecting model of scaffold warpage defect using Densenet among CNN models. We evaluated the accuracy of the defect detection model with mAP, which evaluates the detection accuracy of deep learning. As a result of model evaluating, it was confirmed that the defect detection accuracy of the scaffold was more than 95%.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.46 no.2
• /
• pp.1-12
• /
• 2023

To make semiconductor chips, a number of complex semiconductor manufacturing processes are required. Semiconductor chips that have undergone complex processes are subjected to EDS(Electrical Die Sorting) tests to check product quality, and a wafer bin map reflecting the information about the normal and defective chips is created. Defective chips found in the wafer bin map form various patterns, which are called defective patterns, and the defective patterns are a very important clue in determining the cause of defects in the process and design of semiconductors. Therefore, it is desired to automatically and quickly detect defective patterns in the field, and various methods have been proposed to detect defective patterns. Existing methods have considered simple, complex, and new defect patterns, but they had the disadvantage of being unable to provide field engineers the evidence of classification results through deep learning. It is necessary to supplement this and provide detailed information on the size, location, and patterns of the defects. In this paper, we propose an anomaly detection framework that can be explained through FCDD(Fully Convolutional Data Description) trained only with normal data to provide field engineers with details such as detection results of abnormal defect patterns, defect size, and location of defect patterns on wafer bin map. The results are analyzed using open dataset, providing prominent results of the proposed anomaly detection framework.

• Journal of Korea Foundry Society
• /
• v.37 no.6
• /
• pp.181-185
• /
• 2017

In the present study, the effect of cooling rate on the formation of the porosity in the thick aluminum sand casting was investigated. Nowadays, due to considerations of weight and cost reduction, large scale thick aluminum casting has replaces steel frames for vacuum chambers for semiconductor production. Several thick aluminum castings were manufactured using chill with temperature measurements. The castings were inspected using 3D computed tomography in order to quantify the porosity defect density in the castings. Effects of the thickness of the chill on the porosity defect density were discussed.

• Journal of the Korean Society of Manufacturing Technology Engineers
• /
• v.6 no.4
• /
• pp.46-53
• /
• 1997

This paper presents a method of detection localized defects on tapered roller bearing in main spindle of machine tool system. The feature vectors, i.e. statistical parameters, in time-domain analysis technique have been calculated to extract useful features from acoustic emission signals. These feature vectors are used as the input feature of an neural network to classify and detect bearing defects. As a results, the detection of bearing defect conditions could be sucessfully performed by using an neural network with statistical parameters of acoustic emission signals.

• Journal of Korean Society for Quality Management
• /
• v.30 no.3
• /
• pp.150-167
• /
• 2002

Normative theory suggests that control systems should be designed to complement management's objectives and strategies. However, few empirical studies have focused on how control systems have been modified to complement new manufacturing techniques, such as zero-defect strategy. The major purpose of this study is to examine the effects of the attributes of quality strategy and control system on performance. The previous studies have subdivided quality strategy into the ECL(economic conformance level) and ZD(zero-defect) strategy. To accomplish the purpose, this study empirically analysed the data based on the questionnaires from manufacturing department personnel of 67 Korean companies. The major results are as follows. The companies that had implemented the ZD strategy and its control system outperformed the companies that had implemented ECL strategy. Also, the ZD strategy differs from ECL strategy in control system, the criteria of performance evaluation and feedback frequence variable. There is no difference in quality performance monitoring and communication variable. From this results, although many companies have strived for continuous improvement of quality, it was restricted in improvement activities that dont's required much investment cost, quality performance monitoring and communication.

• Tribology and Lubricants
• /
• v.23 no.4
• /
• pp.143-148
• /
• 2007

The surface defects of an aluminum tube for an OPC drum have been analyzed using a scanning microscopy(SEM) and an energy dispersive X-ray analyze.(EDX). The SEM/EDX system, which may provide good information on the surface defects and their distributions, provides an optical diameter of an impurity and a chemical composition. These are strongly related on the coated film thickness and quality of an OPC drum, which is a key element of a toner cartridge for a laser printer. The experimental results show that the local deformations, scratch wear, and flaws are produce the non-uniform coating layers, which may be removed by a manufacturing process of an aluminum tube. The major parameters on the coating quality of an OPC drum are the impurities of an aluminum tube such as silicon, oxygen, calcium, carbon, sulphur, chlorine, and others. These impurities may be removed by an ingot molding, extrusion and drawing, quality control, and packing processes with a strict manufacturing technology.

• Journal of the Korean Society of Manufacturing Process Engineers
• /
• v.11 no.1
• /
• pp.7-12
• /
• 2012

Chemical mechanical polishing(CMP) technology is faced with the challenge of processing new electronic materials. This paper focuses on the balance between chemical and mechanical reactions in the CMP process that is required to cope with a variety of electronic materials. The material properties were classified into the following categories: easy to abrade(ETA), difficult to abrade(DTA), easy to react(ETR) and difficult to react(DTR). The chemical and mechanical balance for the representative ETA-ETR, DTA-ETR, ETA-DTR and DTA-DTR materials was considered for defect-free surfaces. This paper suggests the suitable polishing methods and examples for each electronic material.

• Journal of the Korean Society of Manufacturing Technology Engineers
• /
• v.20 no.5
• /
• pp.666-672
• /
• 2011

In this paper, we describes the development of automatic inspection system for detecting the defects on photovoltaic wafer by using machine vision. Until now, The defect inspection process was manually performed by operators. So these processes caused the produce of poorly-made articles and inaccuracy results. To improve the inspection accuracy, the inspection system is not only configured, but the image processing algorithm is also developed. The inspection system includes dimensional verification and pattern matching which compares a 2-D image of an object to a pattern image the method proves to be computationally efficient and accurate for real time application and we confirmed the applicability of the proposed method though the experience in a complex environment.