DocumentCode :
231342
Title :
Random projection based k Nearest Neighbor rule for semiconductor process fault detection
Author :
Zhou Zhe ; Yang Chunjie ; Wen Chenglin
Author_Institution :
Zhejiang Univ., Hangzhou, China
fYear :
2014
fDate :
28-30 July 2014
Firstpage :
3169
Lastpage :
3174
Abstract :
Fault detection technique is essential for improving overall equipment efficiency of semiconductor manufacturing industry. It has been recognized that fault detection based on k nearest neighbor rule (kNN) can deal with some unique characteristics of semiconductor processes, such as multimode batch trajectories and nonlinearity. However, the computation complexity and storage space required in neighbors searching of kNN prevent it from online monitoring, especially for high dimensional cases. To deal with it, principal component based kNN is also presented in literature, in which dimension reduction by principal component analysis (PCA) is done before kNN rule applied to perform fault detection. However, the process of dimension reduction by PCA may distort the distances of pairwise samples (trajectories). Thus the performance of kNN for fault detection degenerates after projection by PCA. To overcome this drawback, we propose a new fault detection method based on random projection and kNN rule, which combines the advantages of random projection in distance preservation and kNN rule in dealing with the problems of multimodality and nonlinearity that often coexist in semiconductor processes. Industrial example illustrates the performance of the proposed method.
Keywords :
batch processing (industrial); computational complexity; fault diagnosis; principal component analysis; production equipment; semiconductor industry; PCA; distance preservation; equipment efficiency; fault detection method; fault detection technique; kNN; multimodality; multimode batch nonlinearity; multimode batch trajectories; nonlinearity; principal component analysis; random projection based k nearest neighbor rule; semiconductor manufacturing industry; semiconductor process fault detection; Aerospace electronics; Complexity theory; Fault detection; Industries; Principal component analysis; Training; Trajectory; Distance Preservation; Fault Detection; Random Projection; k Nearest Neighbor;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Control Conference (CCC), 2014 33rd Chinese
Conference_Location :
Nanjing
Type :
conf
DOI :
10.1109/ChiCC.2014.6895459
Filename :
6895459
Link To Document :
بازگشت