Yield is undoubtedly the most critical factor to the competitiveness of a product in a semiconductor fabrication plant. Therefore, evaluating the competitiveness of a product with its yield is a reasonable idea. For this purpose, a systematic procedure is established to evaluate the mid-term competitiveness of a product based on the yield learning model. Further, a new correction function is designed to incorporate expert opinions about the mid-term yield target to main the competitiveness of a product into Chen and Wang's fuzzy yield learning model. Such expert opinions are very valuable to controlling the yield learning process and have not been considered in traditional models. The modified model ought to be more practical and accurate than the original one. To evaluate the advantages or disadvantages of the proposed methodology, it is applied to the practical data of four products. Experimental results show that the proposed model outperforms the other models by reducing MAPE to only 2%. Besides, as the evaluated competitiveness decreases, the superiority of the proposed model becomes more evident.
- Correction function
- Yield learning