Abstract
Feedforward neural networks have been used for kinetic parameters determination and signal filtering in differential scanning calorimetry. The proper learning function was chosen and the network topology was optimized, using an empiric procedure. The learning process was achieved using simulated thermoanalytical curves. The resilient-propagation algorithm have led to the best minimization of the error computed over all the patterns. Relative errors on the thermodynamic and kinetic parameters were evaluated and compared to those obtained with the usual thermal analysis methods (single scan methods). The errors are much lower, especially in presence of noisy signals. Then, our program was adapted to simulate thermal effects with known thermodynamic and kinetic parameters, generated electrically, using a PC computer and an electronic interface on the serial port. These thermal effects have been generated by using an inconel thread.
Similar content being viewed by others
References
K. Hornik, M. Stinchcombe and H. White, Neural Networks, 2 (1989) 359.
B. Irie and S. Miyake, In IEEE Second Int. Conf. Neural Networks, Vol.1, San Diego 1988, p. 641.
N. Sbirrazzuoli, D. Brunel and L. Elégant, J. Thermal Anal., 38 (1992) 1509.
N. Sbirrazzuoli and D. Brunel, Neural Comput. and Applic., 5 (1997) in press.
E. Cesari, P. C. Gravelle, J. Gutenbaum, J. Hatt, J. Navarro, J. L. Petit, R. Point, V. Torra, E. Utzig and W. Zielenkiewicz, J. Thermal Anal., 20 (1981) 47.
T. J. McAvoy, H. T. Su, N. S. Wang, M. He, J. Norwath and H. Semerjian, Biotech. Bioeng., 40 (1992) 53.
A. P.De Weijer, C. B. Lucasius, G. Kateman, H. M. Heuvel and H. Mannee, Anal. Chem., 66 (1994) 23.
S. R. Gallant, S. P. Fraleigh and S. M. Cramer, Chemometrics and Intelligent Laboratory Systems, 18 (1993) 41.
P. M. J. Coenegracht, H. J. Metting, E. M. van Loo, G. J. Snoeijer and D. A. Doornbos, J. Chromatogr., 631 (1993) 145.
T. Fechner, Third International Conference on Artificial Neural Networks, London, IEEE, 1993, p. 143–147.
H. Leung and S. Haykin, Neural Computation, 5 (1993) 928.
L. Ying, J. Astola and Y. Neuvo, IEEE Transactions on Signal Processing, 41 (1993) 1201.
N. Sbirrazzuoli, Y. Girault and L. Elégant, Thermochim. Acta, 260 (1995) 147.
SNNS: Stuttgart Neural Network Simulator, University of Stuttgart, Institute for parallel and distributed high performance systems (IPVR), release 3.1.
N. Sbirrazzuoli, Thermochim. Acta, 273 (1996) 169.
N. Sbirrazzuoli, Y. Girault and L. Elégant, Thermochim. Acta, 249 (1995) 179.
M. Riedmiller and H. Braun, Proc. IEEE International of Neural Networks, Vol. 1, San Francisco 1993, p. 586–591.
M. Riedmiller, Computer Standards and Interfaces, 16 (1994) 265.
W. Shiffman, M. Joost and R. Werner, Proc. European symposium on artificial neural networks ESANN 93, Brussels, Verleysen (Ed.), 1993, p. 97–104.
H. Ishiwatari, J. Kammruzzaman and Y. Kumagai, Proc. 35th Midwest Symposium on Circuits and Systems, New York, Vol. 2, IEEE, 1992, p. 875–878.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Sbirrazzuoli, N., Brunel, D. & Elégant, L. Neural networks for kinetic parameters determination, signal filtering and deconvolution in thermal analysis. Journal of Thermal Analysis 49, 1553–1564 (1997). https://doi.org/10.1007/BF01983715
Issue Date:
DOI: https://doi.org/10.1007/BF01983715