• Journal of the Semiconductor & Display Technology
• /
• v.21 no.4
• /
• pp.168-173
• /
• 2022

As the function of a product is advanced and the process is refined, the yield in the fine manufacturing process becomes an important variable that determines the cost and quality of the product. Since a fine manufacturing process generally produces a product through many steps, it is difficult to find which process or equipment has a defect, and thus it is practically difficult to ensure a high yield. This paper presents the system architecture of how to build a smart manufacturing system to analyze the big data of the manufacturing plant, and the equipment factor analysis methodology to increase the yield of products in the smart manufacturing system. In order to improve the yield of the product, it is necessary to analyze the defect factor that causes the low yield among the numerous factors of the equipment, and find and manage the equipment factor that affects the defect factor. This study analyzed the key factors of abnormal equipment that affect the yield of products in the manufacturing process using the data mining technique. Eventually, a methodology for finding key factors of abnormal equipment that directly affect the yield of products in smart manufacturing systems is presented. The methodology presented in this study was applied to the actual manufacturing plant to confirm the effect of key factors of important facilities on yield.

• IE interfaces
• /
• v.20 no.3
• /
• pp.288-297
• /
• 2007

Success of semiconductor/LCD industry depends on its yield and quality of product. For the purpose, FDC (Fault Detection and Classification) system is used to diagnose fault state in main manufacturing processes by monitoring time series data collected by equipment sensors which represent various conditions of the equipment. The data set is segmented at the start and end of each product lot processing by a trigger event module. However, in practice, segmented sensor data usually have the features of data asynchronization such as different start points, end points, and data lengths. Due to the asynchronization problem, false alarm (type I error) and missed alarm (type II error) occur frequently. In this paper, we propose a robust process fault detection system by integrating a process event detection method and a similarity measuring method based on dynamic time warping algorithm. An experiment shows that the proposed system is able to recognize abnormal condition correctly under the asynchronous data situation.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.3
• /
• pp.471-477
• /
• 2021

In the field of display, a smart factory means more efficient display manufacturing using AI/BIG DATA technology not only for job automation, but also for existing process management, moving facilities, process abnormalities, and defect classification. In the past, when defects appeared in the display manufacturing process, the classification of defects and coping with process abnormalities were different, a lot of time was consumed for this. However, in the field of display manufacturing, advanced process equipment must be used, and it can be said that the competitiveness of the display manufacturing industry is to quickly identify the cause of defects and increase the yield. In this paper, we will summarize the cases in which smart factory AI/BIG DATA technology is applied to domestic display manufacturing, and analyze what advantages can be derived compared to existing methods. This information can be used as prior knowledge for improved smart factory development in the field of display manufacturing using AI/BIG DATA.

• Journal of Korean Institute of Industrial Engineers
• /
• v.36 no.3
• /
• pp.154-163
• /
• 2010

Process monitoring of output variables affecting final performance have been mainly executed in semiconductor manufacturing process. However, even earlier detection of causes of output variation cannot completely prevent yield loss because a number of wafers after detecting them must be re-processed or cast away. Semiconductor manufacturers have put more attention toward monitoring process inputs to prevent yield loss by early detecting change-point of the process. In the paper, we propose the method to efficiently monitor functional input variables in multi-phase semiconductor manufacturing process. Measured input variables in the multi-phase process tend to be of functional structured form. After data pre-processing for these functional input data, change-point analysis is practiced to the pre-processed data set. If process variation occurs, key variables affecting process variation are selected using contribution plot for monitoring efficiency. To evaluate the propriety of proposed monitoring method, we used real data set in semiconductor manufacturing process. The experiment shows that the proposed method has better performance than previous output monitoring method in terms of fault detection and process monitoring.

• Journal of Platform Technology
• /
• v.9 no.1
• /
• pp.15-22
• /
• 2021

In a smart manufacturing environment, more and more devices are connected to the Internet so that a large volume of data can be obtained during all phases of the product life cycle. The large-scale industries, companies and organizations that have more operational units scattered among the various geographical locations face a huge resource consumption because of their unorganized structure of sharing resources among themselves that directly affects the supply chain of the corresponding concerns. Cloud-based smart manufacturing paradigm facilitates a new variety of applications and services to analyze a large volume of data and enable large-scale manufacturing collaboration. The manufacturing units include machinery that may be situated in different geological areas and process instances that are executed from different machinery data should be constantly managed by the super admin to coordinate the manufacturing process in the large-scale industries these environments make the manufacturing process a tedious work to maintain the efficiency of the production unit. The data from all these instances should be monitored to maintain the integrity of the manufacturing service system, all these data are computed in the cloud environment which leads to the latency in the performance of the smart manufacturing service system. Instead, validating data from the external device, we propose to validate the data at the front-end of each device. The validation process can be automated by script validation and then the processed data will be sent to the cloud processing and storing unit. Along with the end-device data validation we will implement the APM(Asset Performance Management) to enhance the productive functionality of the manufacturers. The manufacturing service system will be chunked into modules based on the functionalities of the machines and process instances corresponding to the time schedules of the respective machines. On breaking the whole system into chunks of modules and further divisions as required we can reduce the data loss or data mismatch due to the processing of data from the instances that may be down for maintenance or malfunction ties of the machinery. This will help the admin to trace the individual domains of the smart manufacturing service system that needs attention for error recovery among the various process instances from different machines that operate on the various conditions. This helps in reducing the latency, which in turn increases the efficiency of the whole system

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2006.05a
• /
• pp.611-612
• /
• 2006

Many data mining techniques have been proved useful in revealing important patterns from large data sets. Especially, data mining techniques play an important role in a customer data analysis in a financial industry and an electronic commerce. Also, there are many data mining related research papers in a semiconductor industry and an automotive industry. In addition, data mining techniques are applied to the bioinformatics area. To satisfy customers' various requirements, each industry should develop new processes with more accurate production criteria. Also, they spend more money to guarantee their products' quality. In this manner, we apply data mining techniques to the production-related data such as a test data, a field claim data, and POP (point of production) data in the automotive parts industry. Data collection and transformation techniques should be applied to enhance the analysis results. Also, we classify various types of manufacturing processes and proposed an analysis scheme according to the type of manufacturing process. As a result, we could find inter- or intra-process relationships and critical features to monitor the current status of the each process. Finally, it helps an industry to raise their profit and reduce their failure cost.

• International Journal of Contents
• /
• v.13 no.2
• /
• pp.21-28
• /
• 2017

Abnormal data in the manufacturing process makes it difficult to find useful information that can be applied in data management for the manufacturing industry. It causes various problems in the daily process of production. An issue from the abnormal data can be handled by our method that uses big data and visualization. Visualization is a new technology that transforms data representation into a two-dimensional representation. Nowadays, many newly developed technologies provide data analysis, algorithm, optimization, and high efficiency, and they meet user requirements. We propose combined production of the data visualization approach that uses integrative visualization of sources of abnormal pattern analysis results. The perceived idea of the proposed approach can solve the problem as it also works for big data. It can also improve the performance and understanding by using visualization and solving issues that occur in the manufacturing process with a calendar heat map.

• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 2001.10a
• /
• pp.411-415
• /
• 2001

Advances in computer and sensor technology have made it possible to obtain superlarge manufacturing process data in real time, letting us to extract meaningful information from these superlarge data sets. We propose a systematic data analysis procedure which field engineers can apply easily to manufacture quality products. The procedure consists of data cleaning and data analysis stages. Data cleaning stage is to construct a database suitable for statistical analysis from the original superlarge manufacturing process data. In the data analysis stage, we suggest a graphical easy-to-implement approach to extract practical information from the cleaned database. This study will help manufacturing companies to achieve six sigma quality.

• International Journal of Quality Innovation
• /
• v.6 no.3
• /
• pp.70-94
• /
• 2005

The IC packaging industry heavily relies on shop floor information, necessitating the development of a model to flexibly define shop floor information and timely handle manufacturing data. This study presents a novel data model of product manufacturing flow to define shop floor information to effectively respond to accelerated developments in IC package industry. The proposed data model consists of four modules: operation template setup, general process setup, enhanced bill of manufacture (EBOMfr) setup, and work-order process setup. The data model can flexibly define the required shop floor information and decision rules for shop floor product manufacturing flow, allowing one to easily adopt changes of the product and on the shop floor. However, to handle floor dynamics of the IC packaging industry, this work also proposes a WIP (i.e. work-in-process) system for monitoring and controlling the product manufacturing flow on the shop floor. The WIP system integrates the data model with a WIP execution module. Furthermore, an illustrative example, the MIRL WIP System, developed by Mechanical Industrial Research Laboratories of Industrial Technology Research Institute, demonstrates the effectiveness of the proposed model.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2006.05a
• /
• pp.615-616
• /
• 2006

Many manufacturing companies manage their production-related data for quality management and production management. Nevertheless, production related-data should be closely related to each other Stored data is mainly used to monitor their process and products' error. In this paper, we provide an enterprise-wide production data model for decision support system and product automation. Process data, quality-related data, and test data are integrated to identify the process inter or intra dependency, the yield forecasting, and the trend of process status. In addition, it helps the manufacturing decision support system to decide critical manufacturing problems.