Browsing by Author "Chen, Kai-Ying"

Now showing 1 - 6 of 6

A Web Services-Based Collaborative Planning, Forecasting, and Replenishment (CPFR) Framework for Managing Spare Parts of Semiconductor Equipment
(2009-11-01)
Chen, Mu-Chen
;
Chen, Kai-Ying
;
Hsu, Ming-Fu
;
Yeh, Cheng-Ta
;
運輸與物流管理系註：原交通所+運管所
In a semiconductor foundry, equipment failure has long been recognized as a major cause of unpredicted breakdown which results in an excessive production loss. Equipment maintenance management is one of the essential tasks in semiconductor manufacturing. Due to the prosperity of Internet and IT, e-diagnostics and e-maintenance through the web have become important applications in the semiconductor industry. Web services (WSs) can assist the data integration in heterogeneous e-facturing systems to support faster and remote maintenance functions. In this paper, a WS-based collaborative planning, forecasting and replenishment (CPFR) framework, namely WS-CPFR, is developed to collaboratively manage the logistics activities of spare parts in semiconductor equipment between equipment suppliers and semiconductor factories.
Agent-Based Control Framework for Mass Customization Manufacturing With UHF RFID Technology
(2009-09-01)
Tu, Mengru (Arthur)
;
Lin, Jia-Hong
;
Chen, Ruey-Shun
;
Chen, Kai-Ying
;
Jwo, Jung-Sing
Radio frequency identification (RFID) technology adoption in business environments has seen strong growth in recent years. Adopting an appropriate RFID-based information system has become increasingly important for enterprises making complex and highly customized products. However, most firms still use conventional barcode and run-card systems to manage their manufacturing processes. These systems often require human intervention during the production process. As a result, traditional systems are not able to fulfill the growing demand for managing dynamic process flows and are not able to obtain real-time work-in-process (WIP) views in mass customization manufacturing. This paper proposes an agent-based distributed production control framework with UHF RFID technology to help firms adapt to such a dynamic and agile manufacturing environment. This paper reports the design and development of the framework and the application of UHF RFID technology in manufacturing and logistic control applications. The framework's RFID event processing agent model is implemented in a smart end-point (SEP) device. A SEP can manage RFID readers, wirelessly communicate with shop-floor machines, make local decisions, and coordinate with other SEPs. A case study of a bicycle manufacturing company demonstrates how the proposed framework could improve a firm's mass customization operations. Results of experiments show the decentralized multiagent coordination scheme among SEPs outperformed the current practice of the firm in terms of reducing work-in-process and parts inventory.
Agent-Based Control Framework for Mass Customization Manufacturing With UHF RFID Technology (vol 3, pg 343, 2009)
(2009-12-01)
Tu, Mengru (Arthur)
;
Lin, Jia-Hong
;
Chen, Ruey-Shun
;
Chen, Kai-Ying
;
Jwo, Jung-Sing
Applying Neural Networks to Detect the Failures of Turbines in Thermal Power Facilities
(2009)
Chen, Kai-Ying
;
Chen, Long-Sheng
;
Chen, Mu-Chen
;
Lee, Chia-Lung
;
運輸與物流管理系註：原交通所+運管所
Due to the growing demand on electricity, how to improve the efficiency of equipment has become one of the critical issues in a thermal power plant. Related works reported that efficiency and availability depend heavily on high reliability and maintainability. Recently, the concept of e-maintenance has been introduced to reduce the cost of maintenance. In e-maintenance systems, the intelligent fault detection system plays a crucial role for identifying failures. Machine learning techniques are at the core of such intelligent systems and can greatly influence their performance. Applying these techniques to fault detection makes it possible to shorten shutdown maintenance and thus increase the capacity utilization rates of equipment. Therefore, this work applies Back-propagation Neural Networks (BPN) to analyze the failures of turbines in thermal power facilities. Finally, a real case from a thermal power plant is provided to evaluate the effectiveness.
Designing reusable building blocks of simulation models for FMS with multi-sections
(2007)
Chen, Kai-Ying
;
Lin, Yi-Chun
;
Chen, Mu-Chen
;
Yeh, Cheng Tah
;
運輸與物流管理系註：原交通所+運管所
Flexible Manufacturing System (FMS) is an automated manufacturing system that incorporates all the relatively individual processing stations (CNC machines) within the production plant. FMS is fundamental of reducing cost, rising reliability and coordination of flexibility, and productivity. This paper considers the simulation study in the efficiency of multi-sections FMS to perform the various types for several part operations in terms of maximize throughput, WIP and waiting time with alternative routes selection by synthesizing dispatching rules. The study will also focus on the reused modules building functionality. Modeling efforts can be reduced to a great extent through the development of domain specific modules that encapsulate the domain-specific logic and hide many of the modeling details. The key feature of this conception is to allow user to define new modeling modules that can be tailored to a specific problem domain.
Using SVM based method for equipment fault detection in a thermal power plant
(2011-01-01)
Chen, Kai-Ying
;
Chen, Long-Sheng
;
Chen, Mu-Chen
;
Lee, Chia-Lung
;
運輸與物流管理系註：原交通所+運管所
Due to the growing demand on electricity, how to improve the efficiency of equipment in a thermal power plant has become one of the critical issues. Reports indicate that efficiency and availability are heavily dependant upon high reliability and maintainability. Recently, the concept of e-maintenance has been introduced to reduce the cost of maintenance. In e-maintenance systems, the intelligent fault detection system plays a crucial role for identifying failures. Data mining techniques are at the core of such intelligent systems and can greatly influence their performance. Applying these techniques to fault detection makes it possible to shorten shutdown maintenance and thus increase the capacity utilization rates of equipment. Therefore, this work proposes a support vector machines (SVM) based model which integrates a dimension reduction scheme to analyze the failures of turbines in thermal power facilities. Finally, a real case from a thermal power plant is provided to evaluate the effectiveness of the proposed SVM based model. Experimental results show that SVM outperforms linear discriminant analysis (LDA) and back-propagation neural networks (BPN) in classification performance. (C) 2010 Elsevier B.V. All rights reserved.