A Predictive Maintenance System for Epitaxy Processes Based on Filtering and Prediction Techniques

Silicon epitaxial deposition is a process strongly influenced by wafer temperature behavior, which has to be constantly monitored to avoid the production of defective wafers. However, temperature measurements are not reliable, and the sensors have to be appropriately calibrated with some dedicated procedure. A predictive maintenance (PdM) system is proposed with the aim of predicting process behavior and scheduling control actions on the sensors in advance. Two different prediction techniques have been employed and compared: the Kalman predictor and the particle filter with Gaussian kernel density estimator. The accuracy of the PdM module has been tested on real industrial production datasets.

[1]  Nando de Freitas,et al.  Sequential Monte Carlo Methods in Practice , 2001, Statistics for Engineering and Information Science.

[2]  Jason Chao-Hsien Pan,et al.  A new strategy for defect inspection by the virtual inspection in semiconductor wafer fabrication , 2011, Comput. Ind. Eng..

[3]  Wallace E. Larimore,et al.  Canonical variate analysis in identification, filtering, and adaptive control , 1990, 29th IEEE Conference on Decision and Control.

[4]  Michèle Basseville,et al.  Detection of abrupt changes: theory and application , 1993 .

[5]  Jin Wang,et al.  Fault Detection Using the k-Nearest Neighbor Rule for Semiconductor Manufacturing Processes , 2007, IEEE Transactions on Semiconductor Manufacturing.

[6]  R. Jaeger.  Introduction to microelectronic fabrication , 1987 .

[7]  Neil J. Gordon,et al.  A tutorial on particle filters for online nonlinear/non-Gaussian Bayesian tracking , 2002, IEEE Trans. Signal Process..

[8]  Giuseppe De Nicolao,et al.  Proportional hazard model with ℓ1 Penalization applied to Predictive Maintenance in semiconductor manufacturing , 2011, 2011 IEEE International Conference on Automation Science and Engineering.

[9]  A. Beghi,et al.  A predictive maintenance system based on regularization methods for ion-implantation , 2012, 2012 SEMI Advanced Semiconductor Manufacturing Conference.

[10]  J. Blue,et al.  Recipe-Independent Indicator for Tool Health Diagnosis and Predictive Maintenance , 2009, IEEE Transactions on Semiconductor Manufacturing.

[11]  A. Chiuso,et al.  PREDICTION ERROR VS SUBSPACE METHODS IN CLOSED LOOP IDENTIFICATION , 2005 .

[12]  M. C. Jones,et al.  A reliable data-based bandwidth selection method for kernel density estimation , 1991 .

[13]  Bart De Moor,et al.  Subspace Identification for Linear Systems: Theory ― Implementation ― Applications , 2011 .

[14]  Dirk P. Kroese,et al.  Kernel density estimation via diffusion , 2010, 1011.2602.

[15]  E. Rying,et al.  A Novel Focused Local Learning Wavelet Network with Application to In Situ Monitoring During Selective Silicon Epitaxy , 2001 .

[16]  H. Lilliefors.  On the Kolmogorov-Smirnov Test for Normality with Mean and Variance Unknown , 1967 .

[17]  Giuseppe De Nicolao,et al.  Particle filtering of hidden Gamma processes for robust Predictive Maintenance in semiconductor manufacturing , 2010, 2010 IEEE International Conference on Automation Science and Engineering.

[18]  Giuseppe De Nicolao,et al.  Multilevel statistical process control of asynchronous multi-stream processes in semiconductor manufacturing , 2010, 2010 IEEE International Conference on Automation Science and Engineering.

[19]  J. Marron,et al.  Progress in data-based bandwidth selection for kernel density estimation , 1996 .

[20]  K. Cheng,et al.  Molecular beam epitaxy technology of III-V compound semiconductors for optoelectronic applications , 1997, Proc. IEEE.

[21]  John Ringwood,et al.  Particle filters for remaining useful life estimation of abatement equipment used in semiconductor manufacturing , 2010, 2010 Conference on Control and Fault-Tolerant Systems (SysTol).

[22]  Alessandro Chiuso,et al.  On the relation between CCA and predictor-based subspace identification. , 2005, CDC 2005.

[23]  T. Başar,et al.  A New Approach to Linear Filtering and Prediction Problems , 2001 .

[24]  Bonnie K. Ray,et al.  A note on moving average forecasts of long memory processes with an application to quality control , 2002 .

[25]  D. Cox.  Prediction by Exponentially Weighted Moving Averages and Related Methods , 1961 .

[26]  Jin Wang,et al.  Large-Scale Semiconductor Process Fault Detection Using a Fast Pattern Recognition-Based Method , 2010, IEEE Transactions on Semiconductor Manufacturing.

[27]  R. Keith Mobley,et al.  An introduction to predictive maintenance , 1989 .

[28]  J. Hyde,et al.  The use of unified APC/FD in the control of a metal etch area , 2004, 2004 IEEE/SEMI Advanced Semiconductor Manufacturing Conference and Workshop (IEEE Cat. No.04CH37530).

[29]  Ruey-Shan Guo,et al.  Age-based double EWMA controller and its application to CMP processes , 2001 .

[30]  Gian Antonio Susto,et al.  A Predictive Maintenance System for Silicon Epitaxial Deposition , 2011, 2011 IEEE International Conference on Automation Science and Engineering.

[31]  Gian Antonio Susto,et al.  Optimal tuning of epitaxy pyrometers , 2012, 2012 SEMI Advanced Semiconductor Manufacturing Conference.

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

[33]  J. Hartigan,et al.  A Bayesian Analysis for Change Point Problems , 1993 .

[34]  Duane S. Boning,et al.  Simultaneous Fault Detection and Classification for Semiconductor Manufacturing Tools , 2003 .