• Journal of the Semiconductor & Display Technology
• /
• v.19 no.4
• /
• pp.121-125
• /
• 2020

With miniaturization of semiconductor, the manufacturing process become more complex, and undetected small changes in the state of the equipment have unexpectedly changed the process results. Fault detection classification (FDC) system that conducts more active data analysis is feasible to achieve more precise manufacturing process control with advanced machine learning method. However, applying machine learning, especially in supervised learning criteria, requires an arduous data labeling process for the construction of machine learning data. In this paper, we propose a semi-supervised learning to minimize the data labeling work for the data preprocessing. We employed equipment status variable identification (SVID) data and optical emission spectroscopy data (OES) in silicon etch with SF6/O2/Ar gas mixture, and the result shows as high as 95.2% of labeling accuracy with the suggested semi-supervised learning algorithm.

• Proceedings of the KSRS Conference
• /
• 2008.10a
• /
• pp.216-219
• /
• 2008

It is necessary to study encryption for protection and safe transmission of the important information. Specially, the security in satellite data is also getting more and more important. This paper introduces DES and TDES algorithm, studies how to apply to satellite data with those algorithms and process of encryption and decryption for satellite data. Proposed encryption process in this paper will be utilized in satellite data for encryption in many satellites.

• International Journal of Contents
• /
• v.4 no.4
• /
• pp.7-11
• /
• 2008

This paper embodies the agent based cinder monitoring system which supports PDA{Personal Digital Assistant). Monitoring system automatically manages data by using data managing agents such as a state managing agent, a location managing agent, a badness managing agent, a circumstances managing agent, etc, and uses a massive data processing agent to manage massive data. The development of agent based data monitoring system for the stable cinder reuse will be an epoch-making method to develop the process mechanized or manual-labored that widely spreads into the real-time automated process.

• 제어로봇시스템학회:학술대회논문집
• /
• 1997.10a
• /
• pp.1516-1519
• /
• 1997

With disseminationof Distributed Control Systems(DCS), the huge amounts of process operation data could have been available and led to figure out process behaviors better on the statistical basis. Until now, the statistical modeling technology has been susally applied to process monitoring and fault diagnosis. however, it has been also thought that these process information, extracted from statistical analysis, might serve a great opportunity for process operation improvements and process improvements. This paper proposed a general methodolgy for process operation improvements including data analysis, backing up the result of analysis based on the methodology, and the mapping physical physical phenomena to the Principal Components(PC) which is the most distinguished feature in the methodology form traditional statistical analyses. The application of the proposed methodology to the Balst Furnace(BF) process has been presented for details. The BF process is one of the complicated processes, due to the highly nonlinear and correlated behaviors, and so the analysis for the process based on the mathematical modeling has been very difficult. So the statisitical analysis has come forward as a alternative way for the useful analysis. Using the proposed methodology, we could interpret the complicated process, the BF, better than any other mathematical methods and find the direction for process operation improvement. The direction of process operationimprovement, in the BF case, is to increase the fludization and the permeability, while decreasing the effect of tapping operation. These guide directions, with those physical meanings, could save fuel cost and process operator's pressure for proper actions, the better set point changes, in addition to the assistance with the better knowledge of the process. Open to set point change, the BF has a variety of steady state modes. In usual almost chemical processes are under the same situation with the BF in the point of multimode steady states. The proposed methodology focused on the application to the multimode steady state process such as the BF, consequently can be applied to any chemical processes set point changing whether operator intervened or not.

• Journal of Korean Society for Geospatial Information Science
• /
• v.13 no.3 s.33
• /
• pp.3-13
• /
• 2005

This study aims to establish the quality management method for spatial data construction process. Total 17 regulations related to spatial database construction and major aerial survey firms were analyzed in terms of working process, equipments, accuracy of results. It is standardized the process of making new digital maps using aerial photography, revising existing digital maps, producing digital elevation models and developing imagery maps. Quality checking factors for spatial data construction process are also established.

• Proceedings of the Korean Society of Surveying, Geodesy, Photogrammetry, and Cartography Conference
• /
• 2004.11a
• /
• pp.355-360
• /
• 2004

This study is aimed at developing the system to manage the process and metadata of spatial data construction. The process of spatial data construction is standardized by analyzing knowhow of major firms and the provisions of MOCT(Ministry of the Construction and Transportation), and by appling the development methodology of information system. The system from this study has the capability to manage efficiently the process and metadata of spatial data construction. The process is shown by using index map. Also, it is shown by using Gantt chart and PERT chat after developing the interface for MS Project. The metadata is generated from the process, and managed systematically.

• 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 Korean Society of Manufacturing Process Engineers
• /
• v.20 no.9
• /
• pp.90-96
• /
• 2021

As real-time data of factories can be collected using various sensors, the adaptation of intelligent unmanned processing systems is spreading via the establishment of smart factories. In intelligent unmanned processing systems, data are collected in real time using sensors. The equipment is controlled by predicting future situations using the collected data. Particularly, a technology for the prediction of tool wear and for determining the exact timing of tool replacement is needed to prevent defected or unprocessed products due to tool breakage or tool wear. Directly measuring the tool wear in real time is difficult during the cutting process in milling. Therefore, tool wear should be predicted indirectly by analyzing the cutting load of the main spindle, current, vibration, noise, etc. In this study, data from the current and acceleration sensors; displacement data along the X, Y, and Z axes; tool wear value, and shape change data observed using Newroview were collected from the high-speed, two-edge, flat-end mill machining process of SKD11 steel. The support vector machine technique (machine learning technique) was applied to predict the amount of tool wear using the aforementioned data. Additionally, the prediction accuracies of all kernels were compared.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.18 no.4
• /
• pp.219-226
• /
• 2018

IIoT(Industrial Internet of Thing) means that all manufacturing processes are informed beyond the conventional automation of process automation. The objective of the system is to build an information system based on the data collected from the sensors installed in each process and to maintain optimal productivity by managing and automating each process in real time. Data collected from sensors in each process is unstructured and many studies have been conducted to collect and process such unstructured data effectively. In this paper, we propose a system using Node-RED as middleware for effective big data collection and processing.

• 한국데이터정보과학회:학술대회논문집
• /
• 2005.04a
• /
• pp.7-17
• /
• 2005

Consider a stuffing process where sausage-casings are filled with sausage-kneading. One of the most important factors in the stuffing process is weights of stuffed sausages. Sausages weighting above the specified limit are sold in a regular market price for a fixed price, and underfilled sausages are reworked at the expense of reprocessing cost. In this paper, the sausage stuffing process is inspected for improving productivity and quality levels. Several statistical process control tools are suggested by using real data obtained from a Korean Vienna sausage company.