A systematic estimation model for fraction nonconforming of a wafer in semiconductor manufacturing research

The clustering phenomenon of defects usually occurs in semiconductor manufacturing. However, previous studies did not pay much attention to the influence of clustering phenomenon for estimating fraction nonconforming of a wafer. Thus, this paper presents a systematic estimation model with considering relevant variables about clustering defects for fraction nonconforming of a wafer. The method combines back-propagation neural network (BPNN) with genetic algorithm (GA) to obtain an estimation model. In this study, GA aims to optimize the parameters of BPNN. Five relevant variables: number of defects (ND), squared coefficient of angle variation (SCVA) for defects, squared coefficient of distance variation (SCVD) for defects, defect cluster index (CIM), and the number of cluster groups (NCG) for defects by self-organized map (SOM) are utilized as inputs for GA–BPNN. Finally, a simulation case and a real-world case are used to confirm the effectiveness of proposed method.

.Figure optionsDownload as PowerPoint slideHighlights
► Concurrent consideration for cluster defect-pattern and group is the study's novelty.
► This study uses the five variables to feature the characteristics of clustered defects.
► GA–BPNN may construct a systematic wafer-estimation model with high accuracy.