|/ Hyoung-Gon Lee (Presenter) (Dept. of Industrial Engineering, Seoul National University)
/ Jinwoo Park (Dept. of Industrial Engineering, Seoul National University)
|Date: 2005년 03월 14일 ~ 2005년 03월 15일
|start / end date
|city / nation
|wafer fabrication, due-date assignment, neural network
|Assigning due date and delivering timely are an important factor determining the competitive strength of a manufacturing company. Once an order received, we should check the inventory status before anything else. If the stock runs short, we should make the product. In this case, predicting the cycle time of the product is important for the due date assignment.
Due to the complicated process flow of wafer fabrication, distinctive approaches that differ from common scheduling method are required. Especially, more than one thousand different products might be produced simultaneously in wafer fabrication facilities producing multiple product types like ASIC or power semiconductor. Besides, each product type has different process flow and product types and layers that can be processed together in each batch processing equipment are predetermined. Because of Such characteristics, estimating the flow time of each product is very difficult task.
In this study, we propose a method to predict the cycle time and assign the due date as accurately as possible even if the product mix varies continuously. For this, we group the products according to the similarity of process flow and use the information from the groups to predict the cycle time using artificial neural network. The experimental results show that the proposed method is superior to common due date assignment method.
|ISP vs. ISP+CDN: Can ISPs in Duopoly Profit by Introducing CDN Services?
|Inventory Management System using 3D-Camera & Deep Learning
|Impact of Information Visibility of Quality and Physical Flow on the Closed-loop Supply Chain
|INTERACTIVE PLACEMENT METHOD FOR CONTAINER LOADING PROBLEM USING DEPTH CAMERA
|Design for a Hybrid System of Integration Kanban with MRPII
|Performance Improvement Methodology for a Manufacturing System using Petri Nets and Simulation Analysis
|Inventory Management in a Supply Chain using Neural Networks
|Performance Evaluation of Alternative Designs for the Car Recycling System Using Simulation Analysis
|Designing Product Platform for Efficient Production Planning Process
|A Shifting Bottleneck Procedure for Job-Shop Scheduling minimizing the Sum of Earliness and Tardiness
|An Intelligent Batch Splitting method for Schedule Improvement in MRP Environment
|FMS Scheduling Strategies in a Distributed Coordination Environment
|Knowledge Acquisition using Neural Network and Simulator
|Real-time Progress Monitoring System: Application In Block Assembly Shop In Shipyard
|A study on due-date assignment method in wafer fabrication facility producing multiple product types
|Operational Performance metrics in manufacturing process: Based on SCOR model and RFID technology
|IW on IMS
|Maximally permissive adaptive control of an automated manufacturing cell
|Open Innovation in SMEs - The Case of KICMS
|Framework Design of Intelligent Service System for the Middle-of-Life Product
|A framework for the ubiquitous MES using RFID and Web services technology