A fuzzy-neural approach is proposed in this study for estimating the remaining cycle time of each job in a semiconductor manufacturing factory, which was seldom investigated in the past studies but is a critical task for semiconductor manufacturing industry. The proposed methodology applies the FCM-FBPN approach with multiple buckets to estimate both the cycle time and the step cycle time of a job, and then derives the remaining cycle time with the proportional adjustment approach. To evaluate the effectiveness of the proposed methodology, production simulation is used to generate some test data. According to the experimental results, the estimation accuracy of the proposed methodology was significantly better than those of many existing approaches.
|Number of pages||15|
|Journal||International Journal of Innovative Computing, Information and Control|
|State||Published - 1 Aug 2009|
- Remaining cycle time
- Semiconductor manufacturing
- Step cycle time