Recognition of Plasma-Induced X-Ray Photoelectron Spectroscopy Fault Pattern Using Wavelet and Neural Network

  • Byungwhan Kim
  • Sooyoun Kim
  • Sang Jeen Hong
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3973)


To improve device yield and throughput, faults in plasma processing equipment should be quickly and accurately diagnosed. Despite many useful information of ex-situ sensor measurements, their applications to recognize plasma faults have not been investigated. In this study, a new technique to identify fault causes by recognizing X-ray photoelectron spectroscopy (XPS) using neural network and continuous wavelet transformation (CWT). The presented technique was evaluated with the plasma etch data. A total of 17 experiments were conducted for model construction. Model performance was investigated from the perspectives of training error, testing error, and recognition accuracy with respect to various thresholds. CWT-based BPNN models demonstrated a higher prediction accuracy of about 26%. Their advantages over pure XPS-based models were conspicuous in all three measures at small networks.


Recognition Accuracy Continuous Wavelet Transformation BPNN Model Fault Symptom Radio Frequency Source 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Stevenson, J.O., Ward, P.P., Smith, M.L., Markle, R.J.: A Plasma Process Monitor/Control System. Surf. Interf. Anal. 26, 124–133 (1998)CrossRefGoogle Scholar
  2. 2.
    Bose, F., Patrick, R., Baltes, H.: Measurement of Discharge Impedance for Dry Etch Proc-ess Control. SPIE 2336, 101–110 (1994)CrossRefGoogle Scholar
  3. 3.
    Kim, B., Lee, C.: Monitoring Plasma Impedance Match Characteristics in a Multipole In-ductively Coupled Plasma for Process Control. J. Vac. Sci. Technol. A 18(1), 58–62 (2000)CrossRefGoogle Scholar
  4. 4.
    Hong, S.J., May, G.S., Park, D.C.: Neural Network Modeling of Reactive Ion Etching Us-ing Optical Emission Spectroscopy Data. IEEE Trans. Semicond. Manufact. 16(4), 598–608 (2003)CrossRefGoogle Scholar
  5. 5.
    Kim, B., Kim, S.: Partial Diagnostic Data to Plasma Etch Modeling Using Neural Network. Microelectron. Eng. 75(4), 397–404 (2004)CrossRefGoogle Scholar
  6. 6.
    Kim, B., Kim, S.: Diagnosis of Plasma Processing Equipment Using Neural Metwork Recognition of Wavelet-Filtered Impedance Matching. Microelectron. Eng. 82(1), 44–52 (2005)CrossRefGoogle Scholar
  7. 7.
    Kim, B., May, G.S.: Real-Time Diagnosis of Semiconductor Manufacturing Equipment Using a Hybrid Neural Network Expert System. IEEE Trans. Comp. Packag. Manufact. Technol. 20(1), 39–47 (1997)CrossRefGoogle Scholar
  8. 8.
    Rummelhart, D.E., McClelland, J.L.: Parallel Distributed Processing. MIT Press, Cam-bridge (1986)Google Scholar
  9. 9.
    Kim, B., Lee, S.Y., Lee, B.T.: Etching of 4-H SiC in a NF3/CH4 Incudctively Coupled Plasma. J. Vac. Sci. Technol. B 21(6), 2455–2460 (2003)CrossRefGoogle Scholar
  10. 10.
    Kim, B., Park, S.: An Optimal Neural Network Plasma Model: a Case Study. Chemometr. Intell. Lab. Syst. 56(1), 39–50 (2001)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Byungwhan Kim
    • 1
  • Sooyoun Kim
    • 1
  • Sang Jeen Hong
    • 2
  1. 1.Department of Electronic EngineeringSejong UniversitySeoulKorea
  2. 2.Department of Electronic EngineeringMyongji UniversityYonginKorea

Personalised recommendations