The Transformer coupled plasma (TCP) reactors, which usually cost several millions of US dollars, have high capability of producing extremely tiny features and are often used in the semiconductor fabrication etching process. However, because of lacking real-time etching control, it often results in some unacceptable process shifting and thus leads to lower yield of wafer. Besides, if the reactor is halted due to process faults, its productivity will be reduced. In order to maximize the product/wafer yield and tool productivity, a timely and effective fault process detection and classification is required in a plasma reactor.
Optical emission spectroscopy (OES) is one of the most frequency used metrology in in-situ process monitoring. An OES is a non-invasive system and can measure the variation of the optical emission intensity of plasma, which can be used to monitor the etching rate, uniformity, selectivity, critical dimensions, and even the profile of etching features on a wafer. However, an OES may provide a huge amount of information such that the data cannot be analyzed timely. As a result, a real-time fault detection and classification with rapid algorithm is needed.
This study proposes two novel methods for fault process detection and one new method for fault classification. The first fault process detection method adapts the technique of digital image process skill and applies the time series of OES full spectrum intensity, which can be transferred into a binary image. By comparing the image patterns of the process conditions between the incoming test and the normal process, the fault process condition in each recipe step can be found by calculating the difference by each pixel. The second fault process detection method uses statistical skill to build up a healthy process sigma model, utilized to compare the uncertainly process OES data and to generate a match rate indicator, a maker to show whether the process is normal or not. The experiments were conducted and the results showed that this proposal methods can detect the fault process in real-time with high successful rate. Finally, a fault process classification method is proposed using the match rate concept to identify the fault process type. The match rate generated by OES data is transferred into twelve different match rates, by spectrum bands, which are used to build up the models of fault causes. Comparing the test data to the constructed models, the probability indexes (PI) for the fault causes are generated, from which the highest value of PI is regarded as the fault cause. A real-time classification of plasma faults is thus achieved. Experiments were conducted to validate the novel fault classification. From the experimental results, it concludes that the proposed method is feasible providing that the overall accuracy rate of the classification for fault event shifts is 27 out of 28 or about 96.4% in success.

變壓器耦合式電漿(TCP)是一種高密度與低操作壓力電漿技術其利用電磁力去驅使反應氣體離子化，並引起化學反應使得半導體晶圓得到其所需的圖形結構與薄膜生成。變壓器耦合式電漿反應器有高度能力去製造極端微小的結構，其並廣泛使用於半導體晶圓製造中蝕刻不同物質。在先進製程製造中，此種設備的價格往往大約在數百萬美元左右。然而因為其缺少即時蝕刻控制，常常造成無法接受的製程偏移，此偏移可能會導致半導體晶圓的報廢或良率不佳。再者，長時間因設備的故障而產生的低設備妥善率，往往造成投資的浪費與較高的晶片製造成本。因此為了獲得最大製程良率與最高的設備妥善率，一種即時偵測與診斷變壓器耦合式電漿真實失效製程的裝置是必須的。
此外，光放射式光譜儀(OES)是一種常用來量測反應器原處電漿製程光放射的製程監控裝置，此光譜儀可以量測電漿之光放射能量強度並可以用來監控半導體晶圓蝕刻率，蝕刻均勻度，蝕刻選擇比，關鍵性尺寸甚至蝕刻結構外型。即使光放射式光譜儀有著非侵入裝置的優點，它所提供的大量資料，卻造成在資料分析的一大挑戰。
為了實現即時偵測與診斷分類失效電漿製程，本論文提出兩種偵測方法與一種診斷分類方法來實現即時偵測與診斷分類失效電漿製程。首先，應用了一種二維式影像處理方法，此被處理影像是由光放射式光譜儀的頻譜資料依時間序列所組成的，為了方便資料的處理使用影像轉成黑白無灰階之二元影像與比對的統計技巧，並設計一個指示變數與吻合率的計算去分辨何者為正常電漿製程何者為無效電漿製程。實驗的結果告訴我們此方法可以偵測氣體流量，射頻功率，反應氣體壓力，反應溫度等製程參數的偏移。此外，本論文也提出標準差變異數吻合模型之失效製程偵測的方法，使用正常製程光放射式光譜儀參數資料，建立正常健康製程標準差變異數吻合模型，利用比對方式與吻合率計算來偵測失效電漿製程。此方法也可以成功偵測上述製程參數的偏移。最後，利用上述吻合率於不同頻段分佈的不同來區分診斷失效電漿製程發生何種控制參數的偏離。實驗的結果驗證上述方法可以成功區別失效製程型態，減少設備診斷失效原因分析的時間，進而提昇設備妥善率。

[1] S. J. Hong and G. S. May, “ Neural Network Based Time Series Modeling of Optical Emission Spectroscopy Data for Fault Detection in Reactive Ion Etching,” Process and Materials Characterization and Diagnostics in IC Manufacturing, Kenneth W. Tobin, Jr., Proceedings of SPIE Vol. 5041, 2003.
[2] S. J. Qin, G. Cherry, R. Good, J. Wang, and C.A. Harrison, “Semiconductor Manufacturing Process Control and Monitoring: A Fab-Wide Framework,” Jornal of Process Control, Vol. 16, Pages 171-191, 2006.
[3] M. K. Jeong, J. -C. Lu and N. Wang, “Wavelet-based SPC Procedure for Complicated Functional Data,” International Journal of Production Research, Vol. 44, Issue 4, Pages 729 – 744, 2006.
[4] J. Moyne, H. Haji, K. Beatty, R. Lewandowski, “SEMI E133-The Process Control System Standard: Deriving a Software Interoperability Standard for Advanced Process Control in Semiconductor Manufacturing,” Semiconductor Manufacturing, IEEE Transactions on, Vol. 30, No. 4, Pages 408-420, 2007.
[5] J. Ahn, D. Ryu, J. Oh, and S. Hong, “Real-Time In-Situ Plasma Etch Process Monitoring for Sensor-Based Process Control Using PECSTM,” In Proc. 17th Korean Semiconductor Conference, Busan, Korea, Feb. 2010.
[6] Gowri P. Kotaa, Jorge Luquea, Mircea Dusab, and Adolph Hunterb, “Advanced Process Control Applied to 90-nm Lithography and Etch,” Optical Microlithography XVI, Proceedings of SPIE Vol. 5040, Pages 972-978, 2003.
[7] J. B. Yu and L. F. Xi, “Using an MQE Chart Based on a Self-organizing Map NN to Monitor Out-of-control Signals in Manufacturing Processes,” International Journal of Production Research, Vol.46, No.21, Pages 5907–5933, Nov. 2008.
[8] T. Chen, J. Morris and E. Martin, “Probability Density Estimation Via an Infinite Gaussian Mixture Model: Application to Statistical Process Monitoring,” Appl. Statist.Vol. 55, No. 5, Pages 699–715, Oct. 2006.
[9] J. Chen and J. Liu, “Mixture Principal Component Analysis Models for Process Monitoring,” Industrial Engineering and Chemistry Research, Vol.38, No.4, Pages1478-1488, Feb. 2004.
[10] S. J. Zhao, J. Zhang, and Y. M. Xu, “Monitoring of Processes with Multiple Operating Modes Through Multiple Principal Component Analysis Models,” Ind. Eng. Chem. Res. Vol. 43, No. 22, Pages 7025–7035, Sep. 2004.
[11] H. H. Yue, S. J. Qin, R.J. Markle, C. Nauert, and M. Gatto, “Fault Detection of Plasma Etchers Using Optical Emission Spectra,” Semiconductor Manufacturing, IEEE Transactions on Vol. 13, Issue 3, Pages 374-385, Aug 2000.
[12] B. M. Wise, N. B. Gallagher and E. B. Martin “Application of PARAFAC2 to Fault Detection and Diagnosis in Semiconductor Etch,” Journal of Chemometrics, Vol. 15, Issue 4, Pages 285-298, 26 Apr 2001.
[13] S.J. Hong and G.S. May, “Neural-Network-Based Sensor Fusion of Optical Emission and Mass Spectroscopy Data for Real-Time Fault Detection in Reactive Ion Etching,” Industrial Electronics, IEEE Transactions on Vol. 52, Issue 4, Pages 1063-1072, Aug. 2005.
[14] N. B. Gallagher and B. M. Wise, “Development And Benchmarking of Multivariate Statistical Process Control Tools For A Semiconductor Etch Process: Improve Robustness Through Model Updating,” IFAC ADCHEM'97, 1997.
[15] E.K. Lada, J. C. Lu and J.R. Wilson, “A Wavelet-based Procedure For Process Fault detection,” Semiconductor Manufacturing, IEEE Transactions on, Vol. 15, Issue 1, Pages 79-90, Feb 2002.
[16] W. A. Wilkinson and M. D. Cox, “Discrete Wavelet Analysis of Power System Transients,” IEEE Transaction on Power System, Vol. 11, Pages 2038–2044.
[17] Z.Y. He, Y.M. Cai and Q.Q. Qian, “A Study of Wavelet Entropy Theory and Its Applications in Power System”, Proc. of Int. Conf. on Intelligent Mechatronics and Automation, China, Aug. 2004.
[18] Z.M. Li, W.X. Li and R.Y. Liu, “Applications of Entropy Principles in Power System: A Survey”, IEEE/PES Transmission and Distribution conference and Exhibition, China, 2005.
[19] G. S.May, and C. J. Spanos, “Automated Malfunction Diagnosis of Semiconductor Fabrication Equipment: A Plasma Etch Application,” Semiconductor Manufacturing, IEEE Transactions on, Vol. 6, Issue 1, Pages 28-40, Feb 1993.
[20] M.M. Gardner, J. C. Lu, R.S. Gyurcsik, J.J. Wortman, B.E. Hornung, H.H. Heinisch, E.A. Rying, S. Rao, J.C. Davis, and P.K. Mozumder, “Equipment Fault Detection Using Spatial Signatures,” Components, Packaging, and Manufacturing Technology, Part C, IEEE Transactions on, Vol. 20, Issue 4, Pages 295-304, Oct 1997.
[21] Anderson, Harold, Gunther, Steve and Fry, Bob, “Plasma Etch Endpoint and Fault Detection Along with UV-Vis Absorption Spectroscopy from a Single Compact Solid State Detector,” American Physical Society, 54th Annual Gaseous Electronics Conference October 9 - 12, 2001.
[22] R. Bunkofske, C. Ambrozic, and M. Sanders, in AEC/APC Symposium XIII, Page 31, Banff, Canada, 2001.
[23] A. M. Ison, W. Li, and C. J. Spanos, “Fault diagnosis of plasma etch equipment,” in Proceedings of the IEEE International Symposium on Semiconductor Manufacturing, Pages B49-B52, San Francisco, CA , 1997.
[24] P. L. Love, and M. Simaan, “A Knowledge-Based System for the Detection and Diagnosis of Out-of-Control Events,” in Manufacturing Processes in Proceedings of the IEEE International Symposium on Intelligent Control, Pages 2394-2399, Pittsburgh, PA, 1989.
[25] G. S. May, and C. J. Spanos, and C. Almgren, “The Role of RF Measurements in Plasma Etching,” Semiconductor Manufacturing, IEEE Transactions on, Semiconductor International, Vol. 19, No. 8, Pages 99-104, 1997.
[26] F. Martinez, P. Scullin and J. Scanlan, “Broadband RF Process–State Sensor for Fault Detection and Classification,” Proceeding of SPIE – The International Society for Optical Engineering, Vol. 5755, Pages 178-186, 2005.
[27] M. S. Chen, T. F. Yen and B. Coonan, “Real-time Fault Detection and Classification for Semiconductor Manufacturing Tools,” Proceeding of Semiconductor Manufacturing Technology Workshop, Pages 103-106, 2004.
[28] B. E. Goodlin, DX Boning, H.H. Sawin and B.M. Wise, “Simultaneous Fault Detection and Classification for Semiconductor Manufacturing Tools”, in Meeting of the Electrochemical, International Symposium on Plasma Processing XIV, Philadelphia, PA, May 2002.
[29] A. M. Ison, “Probabilistic Modeling for Fault Classification of Plasma Equipment”, Ph.D.thesis, 1999.
[30] R. Dunia and S.J.Qin, “A Unified Geometric Approach to Process and Sensor Fault Identification and Reconstruction: The Unidimensional Case”, Computers and Chemical Engineering, Vol. 22, Pages 927-943, 1998.
[31] M. Kezunovic and I. Rikalo, “Detect and Classify Faults Using Neural Nets,” IEEE Computation Appl. Power, Vol. 9, Pages 42–47, Oct. 1996.
[32] B. Zhang, Z.Y. He and Q.Q. Qian, “Application of Wavelet Entropy and Adaptive Nerve-Fuzzy Inference to Fault Classification”, Proc. Int. Conf. on Power System Technology, 2006.
[33] Z.Y. He, X.Q. Chen and G.M. Li, "Wavelet Entropy Definition and its Application for Transmission Line Fault Detection and Identification (Part I: Definition and Methodology), Proc. Int. Conf. on Power System Technology, 2006.
[34] F. Martinez, P. Scullin and J. Scanlan, “Broadband RF Process-State Sensor for Fault Detection and Classification,” Data Analysis and Modeling for Process Control II, Proceedings of SPIE Vol. 5755, Pages 178-186.
[35] S. J. Honga, G. S. May, J. Yamartinob, and A. Skumanichb, “Automated Fault Detection and Classification of Etch Systems Using Modular Neural Networks,” Data Analysis and Modeling for Process Control, Jr., Proceeding of SPIE, Vol. 5378, Pages 134-141, 2004.
[36] J. Jin, and J. Shi, “Automatic Feature Extraction of Waveform Signals for In-Process Diagnostic Performance Improvement," Journal of Intelligent Manufacturing, Vol. 12, Pages 257-268, 2001.
[37] J. Jin, and J. Shi, “Feature-Preserving Data Compression of Stamping Tonnage Information Using Wavelets," Technometrics, Vol. 41, No. 4, Pages 327-339, 1999.
[38] M. S. Chen, T.F. Yen and B. Coonan, “Real-time Fault Detection and Classification for Manufacturing Etch Tools,” Proceeding of Semiconductor Manufacturing Technology Workshop, Pages 103-106, 2004.
[39] K.-A. Toh, Q.-L. Tran, and D. Srinivasan, “Benchmarking a Reduced Multivariate Polynomial Pattern Classifier,” Pattern Analysis and Machine Intelligence, IEEE Transactions on, Vol 26, Issue 6, Pages 740-755, 2004.
[40] K. H. Baek and et. al., “Chamber Maintenance and Fault Detection Technique for a Gate Etch Process Via Self-excited Electron Resonance Spectroscopy,” Journal of Vacuum Science and Technology b: Microelectronics and Nanometer Structures, Vol. 23, No. 1, Pages 125-129, 2005.
[41] M. H. Cheng, S. Y. Lin and et. al., “Fault Detection and Isolation for Plasma Etching Using Model–Based Approach,” IEEE International Symposium on Semiconductor Manufacturing Conference, Proceedings, Pages 208-214, 2003.
[42] W. Li and S. Shah, “Structured Residual Vector-based Approach to Sensor Fault Detection and Isolation”, Journal of Process Control, Vol. 12, Pages 429-443, 2002.
[43] P. Kesavh and J.H. Lee, “A Set based Approach to Detection and Isolation of Faults in Multivariable System”, Computers and Chemical Engineering, Vol. 25, Pages 925-940, 2001.
[44] H. Wang, 2. Song and H. Wang, “Statistical Process Monitoring Using Improved PCA with Optimized Sensor Locations” Journal of Process Control, Vol. 12, Pages 735-144, 2002.
[45] E. A. Rietman, “A Study on Failure Prediction in a Plasma Reactor,” Semiconductor Manufacturing, IEEE Transactions on, Vol. 11, No. 4, Pages 670-680, November 1998.
[46] G. Spitzlsperger, C. Schmidt, G. Ernst, H. Strasser, and M. Speil, “Fault Detection for a Via Etch Process Using Adaptive Multivariate Methods,” Semiconductor Manufacturing, IEEE Transactions on, Vol. 18, No. 4, November 2005.
[47] E. A. Rying, R. S. Gyurcsik, J. C. Lu, G. Bilbro, G. Parsons and F. Y. Sorrell, “Wavelet Analysis of Mass Spectrometry Signals for Transient Event Detection and Run-to-run Process Control," in Proceedings of the Second International Symposium on Process Control, Diagnostics, and Modeling in Semiconductor Manufacturing, Pages 37-44, 1997.
[48] Koh, C. K. H., J. Shi, Williams W. J., and J. Ni, “Multiple Fault Detection and Isolation Using the Haar Transform, Part 2: Application to the Stamping Process," Transactions of the ASME, Pages 295-299, 1999.
[49] H.M. Anderson, “Plasma Diagnostics for Semiconductor Processing,” Electronic-Enhanced Optics, Optical Sensing in Semiconductor Manufacturing, Electro-Optics in Space, Broadband Optical Networks, 2000. Digest of the LEOS Summer Topical Meetings, Aventura, FL , USA.
[50] J. Liu, and D. S. Chen, “Operational Performance Assessment and Fault Isolation for Multimode Processes,” Ind. Eng. Chem. Res., Vol.49, No.8, Pages 3700-3714, Mar. 2010.
[51] E. A. Rying, G. L. Bilbro, and J.-C. Lu, “Focused Local Learning with Wavelet Neural Networks,” IEEE Transactions on Neural Networks, in revision.
[52] N. Saito, “Simultaneous Noise Suppression and Signal Compression Using a Library of Orthonormal Bases and The Minimum Description Length Criterion,” in Wavelets in Geophysics, E. Foufoula-Georgiou and P. Kumar, Eds. New York: Academic Press, Pages 299–324, 1994.
[53] X. Z. Wang, B. H. Chen, S. H. Yang, and C. McGreavy, “Application of Wavelets and Neural Networks to Diagnostic System Development, 2, An Integrated Framework and Its Application,” Computers and Chemical Engineering, Vol. 23, Pages 945–954, 1999.
[54] B. M. Wise, N. B. Gallagher, S. W. Butler, D. D. Jr White and G. G. Barna, “A Comparison of Principal Component Analysis, Multiway Principal Component Analysis, Trilinear Decomposition and Parallel Factor Analysis for Fault Detection in a Semiconductor Etch Process,” Journal of Chemometrics, Vol.13, No.3-4, Pages 379-396, Jul. 1999.
[55] Q. P. He and J. Wang, “Statistical Fault Detection of Batch Processes in Semiconductor Manufacturing,” in Proc. AIChE Annu. Conf., San Francisco, CA, Nov. 2006.
[56] J. Roland, P. Marcoux, G. Ray, and G. Rnakin, “Endpoint Detection In Plasma Etching,” J. Vac. Sci. Technol. A, Vol. 3, May 1985.
[57] P. Kang, H. Lee, S. Cho, D. Kim, J. Park, C. Park, and S. Doh, “A Virtual Metrology System for Semiconductor Manufacturing,” Expert Systems with Applications, Vol. 39, Pages 12554-12561, 2009.
[58] H. H. Yue, S. J. Qin, J. Wiseman, and A. Toprac,“Plasma Etching Endpoint Detection Using Multiple Wavelengths for small-open area wafers,” Semiconductor Manufacturing, IEEE Transactions on, Vol. 19, No. 1, Pages 66-75, 2001.
[59] S. Siu, R. Patrick, and V. Vahedi, “Effect of Plasma Density and Uniformity, Electron Temperature, Process Gas, and Chamber on Electron Shading Damage,” Proceedings of Plasma Process-Induced Damage, Monterey, CA, USA, May 10-11, 1999.
[60] V. C. Venugopal , A. J. Perry, Kim V. Wallace and David J. Cooperberg, “Manufacturability Considerations in Designing Optical Monitoring Methods for Control of Plasma Etch Processes,” Advanced Characterization Techniques for Optics, Semiconductors, and Nanotechnologies, Proceedings of SPIE Vol. 5188, 2003.
[61] H. M. Park, D. S. Grimard, J. W. Grizzle, and Fred L. Terry, “Etch Profile Control of High-Aspect Ratio Deep Submicrometerα-Si Gate Etch,” Semiconductor Manufacturing, IEEE Transactions on, Vol. 14, No. 3, August 2001.
[62] P. I. Klimecky, J. W. Grizzle, and F. L. Terry, “Compensation for Transient Chamber Wall Condition Using Real-Time Plasma Density Feedback Control in An Inductively Coupled Plasma Etcher,” Journal of Vacuum Science Technology, Pages 706-717, May/Jun, 2003.
[63] W. Z. Collison, T. Q. Ni, and M. S. Barnes, “Studies of The Low-Pressure Inductively-Coupled Plasma Etching for a Larger Area Wafer Using Plasma Modeling and Langmuir Probe,” Journal of Vacuum Science Technology, Pages 100-107, Jan/Feb 1998.
[64] R. Shadmehr, D. Angell, P. B. Chou, G. S. Oehrlein and R. Jaffe, “Principal Component Analysis of Optical Emission Spectroscopy And Mass Spectrometry: Application to Reactive Ion Etch Process Parameter Estimation Using Neural Networks,” J. Electrochem. Soc. Vol. 139, No. 3, Pages 907-915, Mar. 1992.
[65] S. Hong and G. May, “Neural Network Modeling of Reactive Ion Etching Using Principal Component Analysis of Optical Emission Spectroscopy Data,” Proceeding of Advance Semiconductor Manufacturing Conference, Boston, MA, Apr. 2002.
[66] S.M. Irving, “Kodak Photoresist Seminar,” February 26, 1968.
[67] H.B Bonham and et.al., “Plasma Cleaning for Improved Wire Bonding on Thin-film Hybrids,” Electronic Packaging and Production, Feb. 1979.
[68] M. A. Lieberman and A. J. Lichtenberg, “Principles of Plasma Discharges and Materials Processing, “ Wiley, New York, 1994.
[69] P. Singer, “The Many Challenges of Oxide Etching”, Semiconductor International, Cahners Publishing, CO, Pages 109-114, June 1997.
[70] P. Singer, “Plasma Etch: A Matter of Fine-Tuning”, Semiconductor International, Cahners Publishing, CO, Pages 65-68, Dec 1995.
[71] M. A. Lieberman and R. A. Gottscho, "Design of High Density Plasma Sources for Materials Processing," in Physics of Thin Films, M. Francombe and J. Vossen, Eds., Academic Press, Inc., New York, 1993.
[72] B. Roger, M. Berry, I. Turlik, P. Garrow and D. Castillo, “Soft Mask for Via Patterning in Benzocyclobutene,” Int. J. Micro. and Elect. Packaging, Vol. 17, No. 3, Pages 210-218, 3rd Quarter, 1994.
[73] Goodlin, E. Brain, C. Schmidt, G. Ernst and et. al. “Simultaneous Fault Detection and Classification for Semiconductor Manufacturing Tools,” Journal of the Electrochemical Society, Vol. 150, No. 12, Pages G778-G784, December, 2003.