A monitoring method of semiconductor manufacturing processes using Internet of Things–based big data analysis

Abstract

This article proposes an intelligent monitoring system for semiconductor manufacturing equipment, which determines spec-in or spec-out for a wafer in process, using Internet of Things-based big data analysis. The proposed system consists of three phases: initialization, learning, and prediction in real time. The initialization sets the weights and the effective steps for all parameters of equipment to be monitored. The learning performs a clustering to assign similar patterns to the same class. The patterns consist of a multiple time-series produced by semiconductor manufacturing equipment and an after clean inspection measured by the corresponding tester. We modify the Line, Buzo, and Gray algorithm for classifying the time-series patterns. The modified Line, Buzo, and Gray algorithm outputs a reference model for every cluster. The prediction compares a time-series entered in real time with the reference model using statistical dynamic time warping to find the best matched pattern and then calculates a predicted after clean inspection by combining the measured after clean inspection, the dissimilarity, and the weights. Finally, it determines spec-in or spec-out for the wafer. We will present experimental results that show how the proposed system is applied on the data acquired from semiconductor etching equipment.

Chaotic association feature extraction of big data clustering based on Internet of Things

“…In this paper, the extracted CCD is utilized as the chaotic element of huge data clustering. Based on phase space rebuilding, 1-D time series can be stretched out in multi-layered space to separate chaotic element aspect highlights [23]. As per the procedure analyzed in earlier section, the recreated time series can be acquired:…”

Rapid fault cause identification in surface mount technology processes based on factory-wide data analysis

“…[9][10][11][12][13] In addition, to overcome the underestimation problems of the regression methods, faulty products can be detected and classified directly by employing novelty detection methods. 14 Jang and Kim 15 proposed a monitoring system to predict the ''after clean inspection'' value of wafers by using a dynamic time warping and clustering method. Datadriven approaches have widely spread to other manufacturing domains, including rolling mill production, 16 food manufacturing, 17 color filter manufacturing, 18 and home appliances manufacturing.…”