• DocumentCode
    49088
  • Title

    Efficient Determination of Copper Electroplating Chemistry Additives

  • Author

    Ellis, Charles D. ; Hamilton, Michael C. ; Nakamura, James R. ; Wilamowski, Bogdan M.

  • Author_Institution
    Dept. of Electr. & Comput. Eng., Auburn Univ., Auburn, AL, USA
  • Volume
    4
  • Issue
    8
  • fYear
    2014
  • fDate
    Aug. 2014
  • Firstpage
    1380
  • Lastpage
    1390
  • Abstract
    Determination of copper electroplating additives is critical to ensuring consistent copper plating of conductors and through-silicon-vias used in semiconductor processing and electronics packaging. The present analysis methods require many chemical analysis steps, generate waste, and are not very accurate. A new set of analysis methods utilizes a reduced number of steps and along with the use artificial neural networks (NNs) overcomes the present limitations, and provides an accurate and ecologically green analysis procedure. Using a newly developed second-order NN algorithm called neuron-by-neuron analysis, accuracies less than 1% have been realized. A step-by-step procedure to implement this method is provided.
  • Keywords
    additives; copper; electroplating; neural nets; production engineering computing; semiconductor device packaging; Cu; artificial neural networks; copper electroplating chemistry additives; electronics packaging; green analysis; neuron-by-neuron analysis; second order NN algorithm; semiconductor processing; wastes; Additives; Artificial neural networks; Calibration; Copper; Polynomials; Training; Vectors; Copper electroplating; extreme learning machine (ELM); machine learning; neural networks (NNs); support vector machine; support vector machine.;
  • fLanguage
    English
  • Journal_Title
    Components, Packaging and Manufacturing Technology, IEEE Transactions on
  • Publisher
    ieee
  • ISSN
    2156-3950
  • Type

    jour

  • DOI
    10.1109/TCPMT.2014.2325941
  • Filename
    6832549