A Processing Quality Prognostics Scheme for Plasma Sputtering in TFT-LCD Manufacturing

Abstract

A novel quality prognostics scheme (QPS) for plasma sputtering in TFT-LCD manufacturing processes is proposed. The QPS consists of a conjecture model and a prediction model. The conjecture model can use processing parameters and sensor data to estimate the processing quality (sputtering thickness) in real time. This conjecture function is also called virtual metrology. On the other hand, the prediction model is capable of predicting the processing quality of the next-lot glasses. Neural networks and weighted moving average algorithms are applied to construct the QPS. In particular, a reliance index is developed such that online evaluation of whether the conjecture results of the QPS are trustworthy or not is possible. For increasing the accuracy of the QPS, a self-searching mechanism is designed to automatically search the best set of parameters and functions used by the conjecture and prediction algorithms for cases that the processing properties vary or the recipe changes. Also, an auto-adjusting mechanism is developed for tuning the system parameters of the QPS and bringing the conjecture accuracy within an acceptable bound. Thorough tests using normal and abnormal processing data on one set of plasma sputtering equipment in a TFT-LCD plant show that the values of the mean absolute percentage error of both the conjecture and the prediction results are less than 2%, which validates the effectiveness of the proposed QPS.Index Terms-Conjecture model, neural networks (NNs), prediction model, quality prognostics scheme (QPS), reliance index, virtual metrology.

Outsourcing reverse logistics of high-tech manufacturing firms by using a systematic decision-making approach: TFT-LCD sector in Taiwan

“…The TFT-LCD sector in Taiwan generated over U$14 billion in 2004, becoming the largest supplier ahead of South Korea (Hung, 2006;Su et al, 2006). However, globalization has accelerated the demand for reverse logistics services.…”

“…Based on the RBV approach, TFF-LCD manufacturers must identify organizational resources such as infrastructure, semiconductor manufacturing equipment, as well as plant and human resources (Hung, 2006), while the next step involves identifying capabilities of a firm such as manufacturing process quality (Su et al, 2006), TFT fabrication, and LC (liquid-crystal) assembly and module assembly processes (Jeong, Sim, Jeong, & Kim, 2002). Next, industrial marketing managers must evaluate the potential for SCA.…”

“…As is widely anticipated, TFT-LCD reverse logistics requirements will increase even further. Taiwan manufactures more than 40% of the global supply of TFT-LCDs, becoming the largest supplier worldwide in 2004 (Hung, 2006;Su, Hung, Cheng, & Chen, 2006). Therefore, the TFT-LCD sector is adopted as a case study in this work to investigate its reverse logistics service requirements.…”

Data mining for yield enhancement in TFT-LCD manufacturing: an empirical study

“…However, only a few studies have examined TFT-LCD manufacturing. Su et al [28], in particular, proposed a quality prognostics scheme, which used an integrated neural network and weighted moving average algorithm to estimate the thickness of plasma sputtering in TFT-LCD manufacturing.…”

Intelligent Prognostics System Design and Implementation

“…The PMS is used mainly to monitor equipment sensors and to determine the condition of equipment such that an alarm can be sent before a failure occurs. The VMS is applied to conjecture operation performance of a process tool based on data sensed from the process tool and without physical metrology operations [12], [18].…”