Before making a due date commitment to our customer, we need to estimate the cycle times of jobs. For this reason, many of the most-advanced methods classify jobs, before or after estimating the cycle times. However, job classification is not directly helpful to optimize the performances of these estimation methods. To solve this problem, a job-classifying and data-mining approach is proposed in this study to improve the performance of cycle time estimation by optimizing the results of job classification. In addition, some association rules are also extracted from the estimation results to facilitate the practical application of the proposed methodology. According to the results of a case study, the job-classifying and data-mining approach achieved a better estimation performance and could produce some useful estimation rules.
|Number of pages||12|
|Journal||International Journal of Advanced Manufacturing Technology|
|State||Published - 1 Sep 2012|
- Cycle time
- Data mining
- Job classification
- Wafer fabrication