A Case Study on Applying Neural Networks and Multi-Agent Systems to Production Planning and Inventory Monitoring

• Main Authors: Ming-Chang Chen, 陳泯璋
• Other Authors: Von-Wun Soo
• Format: Others
• Language: zh-TW
• Published: 2008
• Online Access: http://ndltd.ncl.edu.tw/handle/98612946047017279062

碩士 === 國立清華大學 === 資訊系統與應用研究所 === 96 === It is more and more competitive in modern commercial environment; the enterprises often adjust their production plans because of uncertain factors. For example, the sales fall short of their expectations, the demand of consumers change, etc. Therefore, it is very important to the enterprises to rapidly adjust their production strategy caused by the changes of extrinsic environment. This research treats of how to employ the agents on production planning and inventory monitor, and takes the paper manufacturing industry as an example. There is little cooperation among each department in the traditional paper manufacturing industry. Therefore, the production plans still depend on historical experiences. There is high variance of production because of its lack of integrated tools among each department. In order to improve this problem, the agent-based system which can integrate information is developed by neural network in this research. It can integrate information among each department and support more efficient decision-making. In this research, the system analysis is processed to get requirements at first, and capture the collaboration requirements among the various functions of planning, the categories and functions of agents are created in the designed stage. Finally, in the executive stage, the real data got from case enterprise are used to make an experiment.