Automatic Identification of Defect Patterns in Semiconductor Wafer Maps Using Spatial Correlogram and Dynamic Time Warping

A wafer map is a graphical illustration of the locations of defective chips on a wafer. Defective chips are likely to exhibit a spatial dependence across the wafer map, which contains useful information on the process of integrated circuit (IC) fabrication. An analysis of wafer map data helps to better understand ongoing process problems. This paper proposes a new methodology in which spatial correlogram is used for the detection of the presence of spatial autocorrelations and for the classification of defect patterns on the wafer map. After the detection of spatial autocorrelation based on our proposed spatial randomness test using spatial correlogram, the dynamic time warping algorithm which provides nonlinear alignments between two sequences to find optimal warping path is adopted for the automatic classification of spatial patterns based on spatial correlogram. We also develop generalized join-count (JC)-based statistics and then propose a procedure to determine the optimal weights of JC-based statistics. The proposed method is illustrated using real-life examples and simulated data sets. The experimental results show that our method is robust to random noise and has a robust performance regardless of defect location and size.

[1]  Vijayan N. Nair,et al.  Monitoring wafer map data from integrated circuit fabrication processes for spatially clustered defects , 1997 .

[2]  Winson Taam,et al.  Detecting Spatial Effects From Factorial Experiments: An Application From Integrated-Circuit Manufacturing , 1993 .

[3]  H.-W. Hsieh,et al.  Recognition of defect spatial patterns in semiconductor fabrication , 2004 .

[4]  Fei-Long Chen,et al.  A neural-network approach to recognize defect spatial pattern in semiconductor fabrication , 2000 .

[5]  Alan Agresti,et al.  Categorical Data Analysis , 1991, International Encyclopedia of Statistical Science.

[6]  J. Keith Ord,et al.  Spatial Processes Models and Applications , 1981 .

[7]  Lee-Ing Tong,et al.  Monitoring defects in IC fabrication using a Hotelling T/sup 2/ control chart , 2005, IEEE Transactions on Semiconductor Manufacturing.

[8]  M.K. Jeong,et al.  Optimal automatic control of multistage production processes , 2005, IEEE Transactions on Semiconductor Manufacturing.

[9]  Giuseppe De Nicolao,et al.  Unsupervised spatial pattern classification of electrical-wafer-sorting maps in semiconductor manufacturing , 2005, Pattern Recognit. Lett..

[10]  Eamonn J. Keogh,et al.  Everything you know about Dynamic Time Warping is Wrong , 2004 .

[11]  S. F. Liu,et al.  Wafer bin map recognition using a neural network approach , 2002 .

[12]  Chenn-Jung Huang,et al.  Clustered defect detection of high quality chips using self-supervised multilayer perceptron , 2007, Expert Syst. Appl..

[13]  Trevor C. Bailey,et al.  Interactive Spatial Data Analysis , 1995 .

[14]  Scott MacKinnon,et al.  Statistical methods for visual defect metrology , 1998 .

[15]  G. De Nicolao,et al.  Unsupervised Spatial Pattern Classification of Electrical Failures in Semiconductor Manufacturing , 2003 .

[16]  Lee-Ing Tong,et al.  Monitoring defects in IC fabrication using a Hotelling T/sup 2/ control chart , 2005 .

[17]  C. K. Hansen,et al.  Use of wafer maps in integrated circuit manufacturing , 1998 .

[18]  Chi-Hyuck Jun,et al.  A simulation-based semiconductor chip yield model incorporating a new defect cluster index , 1999 .

[19]  Fred Spiring,et al.  Introduction to Statistical Quality Control , 2007, Technometrics.

[20]  Winson Taam,et al.  An Autologistic Model for Integrated Circuit Manufacturing , 2000 .

[21]  Chen-Fu Chien,et al.  Hybrid data mining approach for pattern extraction from wafer bin map to improve yield in semiconductor manufacturing , 2007, International Journal of Production Economics.

[22]  Eamonn J. Keogh,et al.  Making Time-Series Classification More Accurate Using Learned Constraints , 2004, SDM.