Advertisement

Thermal Efficiency Supervision by NN Based Functional Approximation Techniques

  • Ramon Ferreiro Garcia
  • José Luis Calvo Rolle
  • Javier Perez Castelo
Part of the Advances in Intelligent and Soft Computing book series (AINSC, volume 87)

Abstract

Thermal efficiency monitoring allows us evaluating the performance of thermal engines which operates under the Rankine cycle. In this research work, massive application of backpropagation neural networks (BPNN) is used with the aim of evaluating the thermal efficiency of processes operating under the Rankine cycle with various working fluids. Knowing the thermal efficiency behavior allows us estimating the best working fluid as well as the optimal operating temperatures for which thermal efficiency is maximized. Achieving mentioned objectives requires a critic modeling task in which massive application of BPNNs are applied. The required information to train the BPNNs is achieved from the NIST database. With such monitoring method, the way to improving the efficiency results a simple reliable task.

Keywords

Backpropagation feedforward NNs Conjugate gradient Functional approximation Organic Rankine cycle Thermal efficiency 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Norgard, M., Ravn, O., Poulsen, N., Hansen, L.: Networks for Modelling and Control of Dynamic Systems. Springer, London (2000)Google Scholar
  2. 2.
    Rutkowski, L.: New Soft Computing Techniques for System Modelling, Pattern Classification and Image Processing. Springer, Berlin (2004)zbMATHGoogle Scholar
  3. 3.
    Witczak, M.: Modelling and Estimation Strategies for Fault Diagnosis of Non-linear Systems. Springer, Berlin (2007)zbMATHGoogle Scholar
  4. 4.
    Huang, G.: Learning capability and storage capacity of two-hidden layer feedforward networks. IEEE. Trans. Neural Networks 14(2), 274–281 (2003)CrossRefGoogle Scholar
  5. 5.
    Setiono, R.: Feedforward neural network construction using cross validation. Neural Comput. 13, 2865–2877 (2001)zbMATHCrossRefGoogle Scholar
  6. 6.
    Fine, T.L.: Feedforward Neural Network Methodology. Springer, New York (1999)zbMATHGoogle Scholar
  7. 7.
    Tang, H., Tan, K.C., Yi, Z.: Neural Networks: Computational Models and Applications. Springer, Heidelberg (2007)zbMATHCrossRefGoogle Scholar
  8. 8.
    NIST.: Reference Fluid Thermodynamic and Transport Properties Database (REFPROP) Version 8.0, U.S. Department of Commerce, Maryland (2007)Google Scholar
  9. 9.
    Fletcher, R., Reeves, C.M.: Function minimisation by conjugate gradients. Computer Journal 7, 149–154 (1964)MathSciNetzbMATHCrossRefGoogle Scholar
  10. 10.
    Irigoyen, E., Larrea, M., Valera, J., Gómez, V., Artaza, F.: A neuro-genetic control scheme application for industrial R3 workspaces. In: Graña Romay, M., Corchado, E., Garcia Sebastian, M.T. (eds.) HAIS 2010. LNCS, vol. 6076, pp. 343–350. Springer, Heidelberg (2010)CrossRefGoogle Scholar
  11. 11.
    Gómez-Garay, V., Irigoyen, E., Artaza, F.: GENNET-Toolbox: An Evolving Genetic Algorithm for Neural Network Training. In: Romay, M.G., Corchado, E., Teresa Garcia-Sebastian, M. (eds.) HAIS 2010. LNCS, vol. 6076, pp. 368–375. Springer, Heidelberg (2010)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Ramon Ferreiro Garcia
    • 1
  • José Luis Calvo Rolle
    • 2
  • Javier Perez Castelo
    • 2
  1. 1.ETSNMSpain
  2. 2.EUP, Dept. Industrial Eng.University of La CoruñaSpain

Personalised recommendations