Integrating Computational Fluid Dynamics and Neural Networks to Predict Temperature Distribution of the Semiconductor Chip with Multi-heat Sources

  • Yean-Der Kuan
  • Yao-Wen Hsueh
  • Hsin-Chung Lien
  • Wen-Ping Chen
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3973)


In this paper, an artificial intelligent system to predict the temperature distribution of the semiconductor chip with multi-heat sources is presented by integrating the back-propagation neural network (BNN) and the computational fluid dynamics (CFD) techniques. Six randomly generated coordinates of three power sections on the chip die are the inputs and sixty-four temperature monitoring points on the top of the chip die are the outputs. In the present methodology, one hundred sets of training data obtained from the CFD simulations results were sent to the BNN for the intelligent training. There are other sixteen generated input sets to be the test data and compared the results between CFD simulation and BNN, it shows that the BNN model is able to accurately estimate the corresponding temperature distribution as well as the maximum temperature values under different power distribution after well trained.


Computational Fluid Dynamic Simulation Junction Temperature Computation Fluid Dynamics Result Hide Layer Node Artificial Intelligent System 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    The International Technology Roadmap for Semiconductors (2001)Google Scholar
  2. 2.
    Soule, C.A.: Future Trends in Heat Sink Design. Electronics Cooling 7(1), 18–27 (2001)Google Scholar
  3. 3.
    Kraus, A., Bar-Cohen, A.: Thermal Analysis and Control of Electronic Equipment. Hemisphere Publishing Corp. (1983)Google Scholar
  4. 4.
    Kraus, A.D., Bar-Cohen, A.: Design and Analysis of Heat Sinks. John Wiley & Sons, Inc., Chichester (1995)Google Scholar
  5. 5.
    Wong, H., Lee, T.Y.: Thermal Evaluation of a PowerPC 620 Multi-Processor in a Multi-Processor Computer. IEEE Transaction on Components, Packaging, and Manufacturing Technology – Part A 19(4), 469–477 (1996)CrossRefGoogle Scholar
  6. 6.
    Chang, J.Y., Yu, C.W., Webb, R.L.: Identification of Minimum Air Flow Design for a Desktop Computer Using CFD Modeling. Journal of Electronic Packaging. Transactions of the ASME 123, 225–231 (2001)Google Scholar
  7. 7.
    Yu, C.W., Webb, R.L.: Thermal Design of a Desktop System Using CFD Analysis. In: Seventeenth IEEE SEMI-THERM Symposium, pp. 18–26 (2001)Google Scholar
  8. 8.
    Goh, T.J., Seetharamu, K.N., Quadir, G.A., Zainal, Z.A., Jeevan, K.: Prediction of Temperature in Silicon Chip with Non-uniform power: A Lagrangian Interpolation Approach. Microelectronics International 21(2), 29–35 (2004)CrossRefGoogle Scholar
  9. 9.
    Goh, T.J., Seetharamu, K.N., Quadir, G.A., Zainal, Z.A., Ganeshamoorthy, K.J.: Thermal Investigations of Microelectronic Chip with Non-Uniform Power Distribution: Temperature Prediction and Thermal Placement Design Optimization. Microelectronics International 21(3), 29–43 (2004)CrossRefGoogle Scholar
  10. 10.
    Cheng, H.-C., Chen, W.-H., Chung, I.-C.: Integration of Simulation and Response Surface Methods for Thermal Design of Multichip Modules. IEEE Transactions on Components and Packaging Technologies 27(2), 359–372 (2004)CrossRefGoogle Scholar
  11. 11.
    Lien, H.C., Lee, S.: A Method of Feature Selection for Textile Yarn Grading Using the Effective Distance Between Clusters. Textile Res. J. 72(10), 870–878 (2002)CrossRefGoogle Scholar
  12. 12.
    Lien, H.C., Lee, S.: Applying Pattern Recognition Principles to Grading Textile Yarns. Textile Res. J. 72(4), 320–326 (2002)CrossRefGoogle Scholar
  13. 13.
    Lien, H.C., Lee, S.: Applications of Neural Networks for Grading Textile Yarns. Neural Computing and Applications 13, 185–193 (2004)CrossRefGoogle Scholar
  14. 14.
    Ludwig, L., Sapozhnikova, E., Lunin, V., Rosenstiel, W.: Error Classification and Yield Prediction of Chips in Semiconductor Industrial Applications. Neural Computing & Applications 9, 202–210 (2000)MATHCrossRefGoogle Scholar
  15. 15.
    Verikas, A., Malmqvist, K., Bergman, L., Signahl, M.: Color Classification by Neural Networks in Graphic Arts. Neural Computing & Applications 7, 52–64 (1998)MATHCrossRefGoogle Scholar
  16. 16.
    Kos, A.: Approach to Thermal Placement in Power Electronics Using Neural Networks. In: Proceedings - IEEE International Symposium on Circuits and Systems, vol. 4, pp. 2427–2430 (1993)Google Scholar
  17. 17.
    Kuan, Y.D., Lien, H.C.: The Integration of the Neural Network and Computational Fluid Dynamics for the Heatsink Design. In: Wang, J., Liao, X.-F., Yi, Z. (eds.) ISNN 2005. LNCS, vol. 3498, pp. 933–938. Springer, Heidelberg (2005)CrossRefGoogle Scholar
  18. 18.
    Icepak 4.1 User’s Guide, Fluent Inc. (2003)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Yean-Der Kuan
    • 1
  • Yao-Wen Hsueh
    • 1
  • Hsin-Chung Lien
    • 1
  • Wen-Ping Chen
    • 2
  1. 1.Department of Mechanical EngineeringNorthern Taiwan Institute of Science and TechnologyTaipeiTaiwan, R.O.C.
  2. 2.Institute of Mechatronic EngineeringNorthern Taiwan Institute of Science and TechnologyTaipeiTaiwan, R.O.C.

Personalised recommendations