• Journal of Intelligence and Information Systems
• /
• v.14 no.4
• /
• pp.89-101
• /
• 2008

The most used tool for quality control is control chart in manufacturing industry. But it has limitations at current situation where most of manufacturing facilities are automated and several manufacturing processes have interdependent relationship such as CCM assembly line. To Solve problems, we propose quality management system based on data mining that are consisted of monitoring system where it monitors flows of processes at single window and feature extraction system where it predicts the yield of final product and identifies which processes have impact on the quality of final product. The quality management system uses decision tree, neural network, self-organizing map for data mining. We hope that the proposed system can help manufacturing process to produce stable quality of products and provides engineers useful information such as the predicted yield for current status, identification of causal processes for lots of abnormality.

• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 1995.04a
• /
• pp.185-192
• /
• 1995

A common control model used to implement computer integrated manufacturing(CIM) is based on the hierarchical decomposition of the shop floor activities, in which supervisory controllers are responsible for all the interactions among subordinates. Although the hierarchical control philosophy provides for easy understanding of complex systems, an emerging manufacturing paradigm, agile manufacturing, requires a new control structure necessary to accommodate the rapid development of a shop floor controller. This is what is called CSCW(computer supported cooperative work)-based control or component-based heterarchical control. As computing resources and communication network on the shop floor become increasingly intelligent and powerful, the new control architecture is about to come true in a modern CIM system. In this paper, CSCW-based control is adopted and investigated, in which a controller for a unit of device performs 3 main functions - planning, scheduling and execution. In this paper, attention is paid to a planning function and all the detailed planning activities for CSCW-based shop floor control are identified. Interactions with other functions are also addressed. Generally speaking, planning determines tasks to be scheduled in the future. In other words, planning analyzes process plans and transforms process plans into detailed plans adequate for shop floor control. Planning is also responsible for updating the process plan and identifying/resolving replanning activities whether they come from scheduling or execution.

• Journal of the Korean Society for Precision Engineering
• /
• v.17 no.3
• /
• pp.15-21
• /
• 2000

The Intelligent Manufacturing Systems (IMS) Rapid Product Development (RPD) Project is an international partnership formed to build a pre-competitive research and development program that will address the integration of new technologies in manufacturing and provide an infrastructure for industry to cooperate much more closely in the product development cycle. In this explanatory paper, a research trend of the RPD project is briefly presented, together with its background and state-of-the-art, focusing on objectives and target results of its sub-projects which include rapid development of functional parts and tools, validation and reverse engineering, and information logistic system.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2000.05a
• /
• pp.991-994
• /
• 2000

Recently, reliability engineering is regarded as the major field for aerospace and electronics, semiconductor related industry to improve safety and life cycle. And advanced manufacturing systems with high speed and intelligent have been developed for the betterment of machining ability In this case, reliability prediction has also important roll from design procedure to manufacturing and assembly process. Accordingly in this study, reliability evaluation system has been developed for prevention trouble. quality and life cycle improvement extremely for advanced mother machinary.

• Journal of the Korean Society of Manufacturing Technology Engineers
• /
• v.19 no.2
• /
• pp.241-250
• /
• 2010

A recurrent adaptive model-free intelligent control with a friction estimation law is proposed to enhance the positioning performance of the mover in PMLSM system. For the PMLSM with nonlinear friction and uncertainty, an adaptive recurrent fuzzy neural network(ARFNN) and compensated control law in $H_{\infty}$ performance criterion are designed to mimic a perfect control law and compensate the approximated error between ideal controller and ARFNN. Combined with friction observer to estimate nonlinear friction parameters of the LuGre model, on-line adaptive laws of the controller and observer are derived based on the Lyapunov stability criterion. To analyze the effectiveness our control scheme, some simulations for the PMLSM with nonlinear friction and uncertainty were executed.

• Journal of the Korean Society for Precision Engineering
• /
• v.11 no.2
• /
• pp.17-22
• /
• 1994

짧아진 제품의 주기, 고객의 다양한 제품선호 경향등에 대응하기 위해서, 제조업체들은 다품종 소량체제에 맞게 유연한 생산시스템을 갖추어야한다. 생산성과 유연성을 동시에 추구하고자하는 유연생산 시스템(Foexible Manufacturing System: FMA)의 도입에는 막대한 투자가 따르기 때문에 시스템의 가동률을 극대화하고 유휴시간( Nonproductive Time)을 최소화해야 단 기간내에 투자비를 상환할 수 있으므로, 생산시스템을 경제적 및 효율적으로 운용하는 것이 매우 중요하다. 한편 이산계 시뮬레이션(Discrete Event Simulation)기법은 시스템의 정적 및 동적인 거동 특성을 모델링하여 모의적 실험을 통해 시스템의 성능이나 특성을 예측할 수 있도록 개발된 유용한 해석 도구로서, 생산 시스템 설계 및 평가등의 분야에 이 기법을 적용한 연구가 매우 활발하게 이루어져 왔으며, 최근 FMS운용을 위한 생산계획, 일정계획등의 문제 해결에도 매우 중요한 해석도구로 인식되고 있다.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.21 no.11
• /
• pp.650-661
• /
• 2020

The digital transformation of the 4th industrial revolution is leading to changes and innovations in the global economy. Various countries are focusing on reviving their manufacturing industries and economic recovery through smart factories. The purpose of this study is to empirically identify technological determinants for the successful implementation of the smart factory and to verify teose effects on manufacturing operations and the firms' operational/environmental performances. Five factors, including sensor network, platform technology, information system, intelligent automation, and safety, were defined as core technologies. The SEM analysis results of 157 small and medium-sized manufacturing firms that have implemented smart factories are as follows. First, sensor network, platform technology, and information system had significant effects on smart manufacturing operations. Second, smart manufacturing operations have improved firm performance. This study is valuable in that it has confirmed the effectiveness of government-funded projects and systemized key technologies for implementing smart factories. Meanwhile, it is helpful for practitioners to support an efficient and effective decision-making for the new adoption.

• 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.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.44 no.2
• /
• pp.43-57
• /
• 2021

Smart factories can be defined as intelligent factories that produce products through IoT-based data. In order to build and operate a smart factory, various new technologies such as CPS, IoT, Big Data, and AI are to be introduced and utilized, while the implementation of a MES system that accurately and quickly collects equipment data and production performance is as important as those new technologies. First of all, it is very essential to build a smart factory appropriate to the current status of the company. In this study, what are the essential prerequisite factors for successfully implementing a smart factory was investigated. A case study has been carried out to illustrate the effect of implementing ERP and MES, and to examine the extensibilities into a smart factory. ERP and MES as an integrated manufacturing information system do not imply a smart factory, however, it has been confirmed that ERP and MES are necessary conditions among many factors for developing into a smart factory. Therefore, the stepwise implementation of intelligent MES through the expansion of MES function was suggested. An intelligent MES that is capable of making various decisions has been investigated as a prototyping system by applying data mining techniques and big data analysis. In the end, in order for small and medium enterprises to implement a low-cost, high-efficiency smart factory, the level and goal of the smart factory must be clearly defined, and the transition to ERP and MES-based intelligent factories could be a potential alternative.

• Journal of Intelligence and Information Systems
• /
• v.10 no.2
• /
• pp.189-209
• /
• 2004

The collaboration between businesses in a demand chain has three layers: Integration, Exchange, and Synchronize. The latter the layer is, the stronger the collaboration gets. This paper investigated drivers influencing intelligent demand chain integration strategy (supply integration, demand integration, demand chain integration) in Korea manufacturing and services. The drivers are classified into two types: rational efficiency driven and bandwagon driven. We find tile differences in the characteristics of drivers affecting the strategies. Besides, this study suggests the better integration strategy for Korea firms. In conclusion it says that demand integration strategy is chosen to improve efficiency, whereas supply integration strategy is influenced by external pressure.