Randomized General Regression Network for Identification of Defect Patterns in Semiconductor Wafer Maps
Defect detection and classification in semiconductor wafers has received an increasing attention from both industry and academia alike. Wafer defects are a significant issue that could cause large losses to the businesses’ yield. The defects occur as a results of a lengthy and complex fabrication method involving tons of stages, and they'll create distinctive patterns. If these patterns were to be identified and classified correctly, then the root of the fabrication drawback can be recognized and eventually resolved. Machine learning (ML) techniques are widely accepted and are well suited to such classification-/identification problems. But, none of the prevailing ML model’s performance exceeds 96% in identification accuracy for such tasks. During this paper, we have a tendency to develop a state-of-the-art classifying algorithm using multiple ML techniques, relying on a general-regression-network-based consensus learning model together with a powerful randomization technique. We compare our proposed methodology with the widely used ML models in terms of model accuracy, stability, and time complexity. Our technique has proved to be a lot of correct and stable as compared to any of the present algorithms reported within the literature, achieving its accuracy of ninety nine.8%, stability of 1.128, and TBM of fifteen.eight s.
Did you like this research project?
To get this research project Guidelines, Training and Code... Click Here