A new intelligent SOFM-based sampling plan for advanced process control

Sample measurement inspecting for a process parameter is a necessity in sem iconductor manufacturing because of the prohibitive amount of time involved in 100% inspection while maintaining sensitivity to all types of defects a nd abnormality. In current industrial practice, sample measurement location s are chosen approximately evenly across the wafer, in order to have all re gions of the wafer equally well represented, but they are not adequate if p rocess-related defective chips are distributed with spatial pattern within the wafer. In this paper, we propose the methodology for generating effective measurem ent sampling plan for process parameter by applying the Self-Organizing Fea ture Map (SOFM) network, unsupervised learning neural network, to wafer bin map data within a certain time period. The sampling plan specifies which c hips within the wafer need to be inspected, and how many chips within the w afer need to be inspected for a good sensitivity of 100% wafer coverage and defect detection. We finally illustrate the effectiveness of our proposed sampling plan using actual semiconductor fab data. (C) 2001 Elsevier Scienc e Ltd. All rights reserved.