Skip to main content
Log in

A neural-Taguchi-based quasi time-optimization control strategy for chemical-mechanical polishing processes

  • Original Article
  • Published:
The International Journal of Advanced Manufacturing Technology Aims and scope Submit manuscript

Abstract

Besides the major factors such as the down force, back pressure and the rotating speed of wafer carrier, effect of polishing time is also an important issue in CMP processes. In this study, a neural-Taguchi method based on a cost-effective quasi time-optimisation technique for chemical-mechanical polishing (CMP) processes is developed. The key concept of this new technique is that an optimal process parameter set is obtained through a neural-network-simulated CMP process model. Under such an optimal parameter set, the desired material removal rate within-wafer-nonuniformity can be reached with the optimal polishing time. It has been proved by experiment that the proposed method can offer a better polishing performance while reducing the polishing time by 1/3.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Similar content being viewed by others

References

  1. O’Mara WC (1994) Planarization by CMP: forecasting the future. Semicond Int July, pp 140–146

    Google Scholar 

  2. Semiconductor Industry Association (1994) The national technology roadmap for semiconductors. Semiconductor Industry Association, San Jose, CA

  3. Steigerwald JM, Murarka SP, Gutmann RJ (1997) Chemical mechanical planarization of microelectronic materials. Wiley, New York

  4. Tsai MS (1998) Short course for the integrated-circuit process. National Nano Device Lab., Taiwan

  5. Chen LJ, Huang YL, Lin ZH, Chiou HW (1998) Pad thermal image endpointing for CMP process. CMP-MIC Conference, pp 28–35, 19–20 Feb 1998

  6. Chan DA, Swedek B, Wiswesser A, Birang M (1998) Process control and monitoring with laser interferometry based endpoint detection in chemical mechancial planarization. IEEE/SEMI Advanced Semiconductor Manufacturing Conference, pp 377–384

  7. Fang SJ, Barda A, Janecko T, Little W, Outley D, Hemple G, Joshi S, Morrison B, Shinn GB, Birang M (1998) Control of dielectric chemical mechancial polishing using an interferometry based endpoint sensor. Interconnect Technology Conference, pp 76–78

  8. Wang GJ, Chen JL, Hwang JY (2001) A new optimization strategy for chemical mechanical polishing process. JSME Int J Series C 44(2):534–543

    Article  Google Scholar 

  9. Tsai MY, Tsai JC, Liu C (1999) Mechanical wear models and experimental investigation for CMP process. Proceeding of the Sixth Symposium on Nano Device Technology, pp 20–23, Hsin-Chu, Taiwan

  10. Wang GJ, Tsai JC, Tzeng PC (1998) Neural-Taguchi method for robust design analysis. J Chin Soc Mech Eng 19(2):223–230

    Google Scholar 

  11. Wang GJ, Wu JG, Chang K (2000) A new neural network based parameters optimization method. Proceeding of the Sixth International Conference on Automation Technology, Taipei, pp 609–616

  12. Preston F (1927) The theory and design of plate glass polishing machines. J Soc Technol 11:214

    Google Scholar 

  13. Taguchi G, Wu YI (1979) Introduction to off-line quality control. Japan Qual Control Assoc, Nayoga, Japan

  14. Ross P (1988) Taguchi techniques for quality engineering. McGraw-Hill, New York

  15. Wang GJ, Chen JJ (2000) Cascade steepest descendant learning algorithm for multilayer feedforward neural network. JSME Int J C 43(2):350–358

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to G.-J. Wang.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Wang, GJ., Chou, MH. A neural-Taguchi-based quasi time-optimization control strategy for chemical-mechanical polishing processes. Int J Adv Manuf Technol 26, 759–765 (2005). https://doi.org/10.1007/s00170-003-1859-8

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00170-003-1859-8

Keywords

Navigation