DocumentCode :
1377548
Title :
Selection Schemes of Dual Virtual-Metrology Outputs for Enhancing Prediction Accuracy
Author :
Wu, Wei-Ming ; Cheng, Fan-tien ; Lin, Tung-Ho ; Zeng, Deng-Lin ; Chen, Jyun-Fang
Author_Institution :
Inst. of Manuf. Inf. & Syst., Nat. Cheng Kung Univ., Tainan, Taiwan
Volume :
8
Issue :
2
fYear :
2011
fDate :
4/1/2011 12:00:00 AM
Firstpage :
311
Lastpage :
318
Abstract :
Selection schemes between neural-network (NN) and multiple-regression (MR) outputs of a virtual metrology system (VMS) are studied in this paper. Both NN and MR are applicable algorithms for implementing virtual-metrology (VM) conjecture models. A MR algorithm may achieve better accuracy only with a stable process, whereas a NN algorithm may have superior accuracy when equipment property drift or shift occurs. To take advantage of both MR and NN algorithms, the simple-selection scheme (SS-scheme) is first proposed to enhance the VM conjecture accuracy. This SS-scheme simply selects either NN or MR output according to the smaller Mahalanobis distance between the input process data set and the NN/MR-group historical process data sets. Furthermore, a weighted-selection scheme (WS-scheme), which computes the VM output with a weighted sum of NN and MR results, is also developed. This WS-scheme generates a well-behaved system with continuity between the NN and MR outputs. Both the CVD and photo processes of a fifth-generation TFT-LCD factory are adopted in this paper to test and compare the conjecture accuracy among the solo-NN, solo-MR, SS-scheme, and WS-scheme algorithms. One-hidden-layered back-propagation neural network (BPNN-I) is applied to establish the NN conjecture model. Test results show that the conjecture accuracy of the WS-scheme is the best among those solo-NN, solo-MR, SS-scheme, and WS-scheme algorithms.
Keywords :
backpropagation; liquid crystal displays; neural nets; production engineering computing; semiconductor device measurement; thin film transistors; virtual instrumentation; CVD process; Mahalanobis distance; TFT-LCD factory; back propagation neural network; dual virtual metrology outputs; multiple regression method; prediction accuracy enhancement; thin film transistor-liquid crystal display factory; weighted selection scheme; Accuracy; Artificial neural networks; Data models; Glass; Metrology; Predictive models; Dual-VM outputs; simple selection scheme (SS-scheme); virtual metrology (VM); weighted selection scheme (WS-scheme);
fLanguage :
English
Journal_Title :
Automation Science and Engineering, IEEE Transactions on
Publisher :
ieee
ISSN :
1545-5955
Type :
jour
DOI :
10.1109/TASE.2010.2089451
Filename :
5634122
Link To Document :
بازگشت