No abstract

Abnormal defect pattern detection plays a key role in preventing yield loss excursion events for the semiconductor manufacturing. We present a method for detecting and segmenting abnormal wafer map defect patterns using deep convolutional encoder-decoder neural network architectures. Using a defect pattern generation model, we create synthetic wafer maps for 8 basis defect patterns, which are used as training, validation, and test datasets. One of the key capabilities for any anomaly detection system is to detect unseen patterns. We demonstrate that by using only synthetic wafer maps with the basis patterns for network training, the models can detect unseen defect patterns from real wafer maps.

No abstract

No abstract

SUMMARYNon-conforming meshes are frequently employed in adaptive analyses and simulations of multi-component systems. We develop a discontinuous Galerkin formulation for the discretization of parabolic problems that weakly enforces continuity across non-conforming mesh interfaces. A benefit of the DG scheme is that it does not introduce constraint equations and their resulting Lagrange multiplier fields as done in mixed and mortar methods. The salient features of the formulation are highlighted through an a priori analysis. When coupled with a mesh refinement scheme the DG formulation is able to accommodate multiple hanging nodes per element edge and leads to an effective adaptive framework for the analysis of interface evolution problems. We demonstrate our approach by analysing the Stefan problem of solidification.