Advanced ART2 scheme for enhancing metrology-data-quality evaluation

Abstract

The metrology-data-quality-index (DQIy) algorithm was proposed to perform metrology-data-quality evaluation of the automatic virtual metrology system developed by the authors. The DQIy algorithm is based on the adaptive-resonance-theory 2 (ART2). ART2 divides data into different patterns according to the similarity of process data, and then calculates the corresponding DQIy value and its threshold, DQIyT, for evaluation and judgment. However, in practical applications, the classical ART2 technique still could not cluster process data very precisely. Since some samples with dissimilar process parameters might be sorted into the same cluster, two or more groups could be found in the corresponding metrology-data cluster. This phenomenon may cause invalid DQIy detection. To solve the problem above, the advanced ART2 scheme is proposed in this paper to enhance the accuracy of the DQIy algorithm. A large industrial data-set showing both a shift in metrology measurements without a process shift and a process shift that was not captured by the metrology of the actual photo and color-filter production tools of a TFT-LCD factory were adopted as illustrative examples to verify the practicality of the proposed scheme. Experimental results show that the performance of the advanced ART2 is indeed better than that of the original ART2.