Abstract
This study proposes a monitoring chart for anomaly detection of non-linear process signals generated by semiconductor manufacturing processes. In these manufacturing processes, fault detection and classification (FDC) and statistical process control (SPC) have been established as fundamental techniques to improve production efficiency and yield. Non-linear process signals are collected through automatic sensing during each operation cycle of a manufacturing process. As these cyclic signals non-linearly vary on the process state, the usage of the prevalent SPC chart is limited. Therefore, we propose a more efficient monitoring chart considering non-linear and time-variant characteristics. Using the principal curve, a non-linear smoothing algorithm, we construct a time-variant centerline that represents the standard pattern of the process. Then, control limits are calculated with time-variant variances over the course of the process. To evaluate performance, the proposed method was applied to industrial data for chemical vapor deposition (CVD), a semiconductor manufacturing process. We employed the misdetection ratio of signals to evaluate the performance. The proposed method demonstrated superior performance compared to other existing methods.
Similar content being viewed by others
References
Baraka A, Panoutsos G, Cater S (2015) A real-time quality monitoring framework for steel friction stir welding using computational intelligence. J Manuf Procs 20:137–148
Kim JS, Lee JH, Kim J-H, Baek J-G, Kim S-S (2010) Fault detection of cycle-based signals using wavelet transform in FAB processes. Int J Precis Eng Man 11(2):237–246
Montgomery DC (2005) Introduction to statistical quality control. 5th ed., Wiley
Shi J, ** J (2000) Diagnostic feature extraction from stam** tonnage signals based on design of experiments. J Manuf Sci E-T ASME 122:360–369
Kang L, Albin SL (2000) On-line monitoring when the process yields a linear profile. J Qual Technol 32(4):418–426
** J, Shi J (2001) Automatic feature extraction of waveform signals for in-process diagnostic performance improvement. J Intell Manuf 12(3):257–268
Rakitzis AC, Antzoulakos DL (2012) Control charts with switching and sensitizing runs rules for monitoring process variation. J Stat Comput Sim 84(1):37–56
Chongfuangprinya P, Kim SB, Park S-K, Sukchotrat T (2011) Integration of support vector machines and control charts for multivariate process monitoring. J Stat Comput Sim 81(9):1157–1173
Moguerza JM, Alberto M, Stelios P (2007) Monitoring nonlinear profiles using support vector machines. Lect Notes Comput Sc 4756:574–583
Vaghefi A, Tajbakshs S, Noorossana R (2009) Phase II monitoring of nonlinear profiles. Commun Stat-Theor M 38(11):1834–1851
Einbeck J, Kauermann G (2003) Online monitoring with local smoothing methods and adaptive ridging. J Stat Comput Sim 73(12):913–929
Park SH, Kim JS, Park C-S, Kim S-S, Baek J-G (2010) A fault detection of cyclic signals using support vector machine-regression. J Korean Soc Qual Manag 38(3):354–362
Kim J-H, Huang A, Shi J, Chang T-S (2006) Online multichannel forging tonnage monitoring and fault pattern discrimination using principal curve. J Manuf Sci E-T ASME 128:944–950
Ganesan R (2008) Real-time monitoring of complex sensor data using wavelet-based multiresolution analysis. Int J Adv Manuf Technol 39:543–558
Hastie T, Stuetzle W (1989) Principal curves. J Am Stat Assoc 84(406):502–516
Ozertem U, Erdogmus D, Arikan O (2008) Piecewise smooth signal denoising via principal curve projections. IEEE Workshop on Machine Learning for Signal Processing (MLSP), pp 426–431
Hastie T, Tibshirani R, Friedman J (2008) The elements of statistical learning: data mining. Inference and prediction, 2nd edn. Springer, New York
Park J, Kwon I-H, Kim S-S, Baek J-G (2011) Spline regression based feature extraction for semiconductor process fault detection using support vector machine. Expert Syst Appl 38(5):5711–5718
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Park, S.H., Park, CS., Kim, JS. et al. Principal curve-based monitoring chart for anomaly detection of non-linear process signals. Int J Adv Manuf Technol 90, 3523–3531 (2017). https://doi.org/10.1007/s00170-016-9624-y
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00170-016-9624-y