• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.45 no.4
• /
• pp.86-98
• /
• 2022

Recently, many studies have been conducted to improve quality by applying machine learning models to semiconductor manufacturing process data. However, in the semiconductor manufacturing process, the ratio of good products is much higher than that of defective products, so the problem of data imbalance is serious in terms of machine learning. In addition, since the number of features of data used in machine learning is very large, it is very important to perform machine learning by extracting only important features from among them to increase accuracy and utilization. This study proposes an anomaly detection methodology that can learn excellently despite data imbalance and high-dimensional characteristics of semiconductor process data. The anomaly detection methodology applies the LIME algorithm after applying the SMOTE method and the RFECV method. The proposed methodology analyzes the classification result of the anomaly classification model, detects the cause of the anomaly, and derives a semiconductor process requiring action. The proposed methodology confirmed applicability and feasibility through application of cases.

• Journal of the Korea Safety Management & Science
• /
• v.16 no.3
• /
• pp.351-362
• /
• 2014

A prerequisite for improving the quality of a product is to enhance the quality of its parts supplied from outsourced enterprises. An enterprise certified by ISO 9001 Quality Management System is expected to develop their effective quality assurance system and maintain it through continuous control and improvement, thereby ensuring the good quality of products that they produce. However, it is reported that small and medium-sized enterprises certified by ISO 9001 have difficulty establishing an effective quality assurance system. This study aims to propose a new method of improving a quality assurance system that can be more effective in small and medium-sized enterprises. This study collectively considered requirements specified in several international standards on quality system and the results of expert group brainstorming to identify evaluation areas and items for assessing a quality assurance system. Based on these evaluation areas and items, a set of checklists for diagnosing and improving a quality assurance system was developed. In order to demonstrate the usefulness of the proposed method, this study applied it to ten small and medium-sized enterprises and could identify four approaches for improving their current quality assurance system. The presented improvement method, which consists of establishment of quality goals and quality innovation plan, defective products corrective activities, 4M and design change process, improvement of customer quality information management, is expected to be utilized as a useful tool for the enhancement of the quality assurance system of small and medium-sized enterprises.

• Information Systems Review
• /
• v.22 no.1
• /
• pp.113-124
• /
• 2020

In the operation of farms, it is very important to evaluate the quality of harvested crops and to classify defective products. However, farmers have difficulty coping with the cost and time required for quality assessment due to insufficient capital and manpower. This study thus aims to detect defects by analyzing the epidermis of fruit using deep learning algorithm. We developed a model that can analyze the epidermis by applying YOLOv3 algorithm based on Region Convolutional Neural Network to video images of peach. A total of four classes were selected and trained. Through 97,600 epochs, a high performance detection model was obtained. The crop failure detection model proposed in this study can be used to automate the process of data collection, quality evaluation through analyzed data, and defect detection. In particular, we have developed an analytical model for peach, which is the most vulnerable to external wounds among crops, so it is expected to be applicable to other crops in farming.

• 한국벤처창업학회:학술대회논문집
• /
• 2008.11a
• /
• pp.285-334
• /
• 2008

The manager of manufacturing industry just not to have known to do related to the law of Product Liability that was put into operation in July 2002. The law of PL is a public law about defective product, which was established in order to compensate consumer's damages of property and body caused by product, to make sound society by the safety products and to take international competitiveness. The economic effects by the law of Product Liability are the increase of consumers relief production cost by the lawsuits. Product liability as a process has developed significantly in the United Kingdom and the United States of America. The rapid introduction of product liability has recently been a prevalent phenomenon, as global changes arising from rapid development in science and the economy have resulted in a highly interconnected world economy. This thesis was established, based on current literature and business consulting cases in the position of companies, and is one of the operating subjects in a system for legal responsibility in manufactured products. However, there are limitations in the fact that research theories are only able to present a theoretical model and directions. In this context, managers and personnel of multiple companies cannot adequately respond to the recently enforced Product Liability Act. The major findings are summarized as Product Liability Management Activity are positively Correlation of Enterprise Value.

• Journal of the Korea Society of Computer and Information
• /
• v.25 no.11
• /
• pp.115-122
• /
• 2020

In this paper, we propose an MES system based on real-time process capability management and how to manage the manufacturing process using the system. The current MES system presents a KPI report that makes it easy to recognize the manufacturing site, but has not been able to derive an improvement method to improve the actual manufacturing site KPI. In other words, it is difficult to extract the cause of the increase in defective rate, decrease in yield, and increase in production lead-time, and to draw an improvement plan and apply it to the manufacturing site. The purpose of the MES system based on real-time process capability management proposed in this paper is to establish an manufacturing operation management system that overcomes the limitations of the existing MES by managing the distribution of major factors of the equipment that determines the process capability. In addition, by presenting a speed improvement method for real-time large-capacity data processing, it is intended to be applied so that the system can operate well.

• Journal of Korean Society of Water and Wastewater
• /
• v.29 no.3
• /
• pp.395-406
• /
• 2015

This research carried out an analysis on input cost and leakage reduction effect by leakage reduction method, focusing on the project for establishing an optimal water pipe network management system in the Taebaek region, which has been executed annually since 2009. Based on the result, optimal cost-benefit analysis models for water distribution network rehabilitation project were developed using DEA(data envelopment analysis) and multiple regression analysis, which have been widely utilized for efficiency analysis in public and other projects. DEA and multiple regression analysis were carried out by applying 4 analytical methods involving different ratios and costs. The result showed that the models involving the analytical methods 2 and 4 were of low significance (which therefore were excluded), and only the models involving the analytical methods 1 and 3 were suitable. From the result it was judged that the leakage management method to be executed with the highest priority for the improvement of revenue water ratio was installation of pressure reduction valve, followed by replacement of water distribution pipe, replacement of water supply pipe, and then leakage detection and repair; and that the execution of leakage management methods in this order would be most economical. In addition, replacement of water meter was also shown to be necessary in case there were a large number of defective water meters.

• Asia-Pacific Journal of Business Venturing and Entrepreneurship
• /
• v.3 no.3
• /
• pp.17-65
• /
• 2008

The manager of manufacturing industry just not to have known to do related to the law of Product Liability that was put into operation in July 2002. The law of PL is a public law about defective product, which was established in order to compensate consumer's damages of property and body caused by product, to make sound society by the safety products and to take international competitiveness. The economic effects by the law of Product Liability are the increase of consumers relief production cost by the lawsuits. Product liability as a process has developed significantly in the United Kingdom and the United States of America. The rapid introduction of product liability has recently been a prevalent phenomenon, as global changes arising from rapid development in science and the economy have resulted in a highly interconnected world economy. This thesis was established, based on current literature and business consulting cases in the position of companies, and is one of the operating subjects in a system for legal responsibility in manufactured products. However, there are limitations in the fact that research theories are only able to present a theoretical model and directions. In this context, managers and personnel of multiple companies cannot adequately respond to the recently enforced Product Liability Act. The major findings are summarized as Product Liability Management Activity are positively Correlation of Enterprise Value.

• Journal of Korean Society for Quality Management
• /
• v.51 no.2
• /
• pp.283-296
• /
• 2023

Purpose: The purpose of this study is to actually implement and verify whether welding defects can be detected in real time by utilizing deep learning AI solutions in the welding process of electric vehicle hairpin winding motors. Methods: AI's function and technological elements using synthetic neural network were applied to existing electric vehicle hairpin winding motor laser welding process by making special hardware for detecting electric vehicle hairpin motor laser welding defect. Results: As a result of the test applied to the welding process of the electric vehicle hairpin winding motor, it was confirmed that defects in the welding part were detected in real time. The accuracy of detection of welds was achieved at 0.99 based on mAP@95, and the accuracy of detection of defective parts was 1.18 based on FB-Score 1.5, which fell short of the target, so it will be supplemented by introducing additional lighting and camera settings and enhancement techniques in the future. Conclusion: This study is significant in that it improves the welding quality of hairpin winding motors of electric vehicles by applying domestic artificial intelligence solutions to laser welding operations of hairpin winding motors of electric vehicles. Defects of a manufacturing line can be corrected immediately through automatic welding inspection after laser welding of an electric vehicle hairpin winding motor, thus reducing waste throughput caused by welding failure in the final stage, reducing input costs and increasing product production.

• Journal of Korean Society for Quality Management
• /
• v.45 no.2
• /
• pp.227-246
• /
• 2017

Purpose: This study proposes a Shiny-Sigma Methods that combines the advantages of Six Sigma method and Shainin method in order to solve field defect. Each technique has advantages and disadvantages. Methods: This study proposed Shiny-Sigma by combining Six Sigma has the logical advantage of the problem solving road map and Shiny has the merits of finding the root problem from the defective phenomenon. The Six Sigma method has the disadvantage that it is difficult to solve if the number of data is small, but the Shiny method has the advantage of finding the root cause with a small number of data. Results: As a result of applying Shiny-Sigma method to the field, it has advantages of solving the problem easily and quickly than the existing Six Sigma method. It does not require a lot of statistical knowledge, which helps field workers to use it. Based on these successes L Co. company has obtained the effect of improving the production quality by applying the Shiny-Sigma method. Conclusion: The Shiny-Sigma method proved to be suitable for the production site as a result of field application. It is suitable for field workers with low statistical knowledge and is suitable for field where data is difficult to obtain. This method is not a method to solve all the problems because there are problems that can be solved according to the field problems. We hope that this method will spread to many industrial sites and this method will have a great effect on the improvement of field production quality.

• The KIPS Transactions:PartD
• /
• v.11D no.4
• /
• pp.975-982
• /
• 2004

In current P2P concept, pure P2P and Hybrid P2P structures are used commonly. Gnutella and Ktella are forms of pure P2P. and forms of Hybrid P2P are innumerable. File searching models exist in these models. These models provide group management for file sharing, searching and indexing. The general file sharing model is good at maintaining connectivity. However, it is defective in group management. Therefore, this study approaches hierarchical structure in file sharing models through routing technique and backup system. This system was designed so that the user was able to maintain group efficiency and connection reliability in large-scale network.