The incremental improved Back-Propagation (BP) neural network prediction model using the Levenberg-Marquardt algorithm based on optimizing theory is put forward, which can solve the problems existing in the process of calcinations for ammonium diuranate (ADU) by microwave heating, such as long testing cycle, high testing quantity, difficulty of optimization for process parameters. Many training data probably were offered by the way of increment batch and the limitation of the system memory could make the training data infeasible when the sample scale was large. The prediction model of the nonlinear system is built, which can effectively predict the experiment of microwave calcining of ADU, and the incremental improved BP neural network is very useful in overcoming the local minimum problem, finding the global optimal solution and accelerating the convergence speed.
LI Yang-Wei
,
LIU Bing-Guo
,
PENG Jin-Hui
,
LI Wei
. Prediction model of microwave calcining of ammonium diuranate using incremental improved back-propagation neural network[J]. Acta Metallurgica Sinica (English Letters), 2011
, 24(1)
: 34
-42
.
DOI: 10.11890/1006-7191-111-34
[1] C.S. Cundy, J.O. Forrest and R.J. Plaisted, Micropor Mesopor Mater 72 (2004) 67.
[2] C.S. Cundy, J.O. Forrest and R.J. Plaisted, Micropor Mesopor Mater 66 (2003) 143.
[3] P.S. Cho, K.W. Kim and J.H. Lee, Sens Actuators B 123 (2007) 1034.
[4] H. Zabova, J. Sobek, V. Cirkva, O. Solcova, S. Kment and M.Hajek, J Solid State Chem 182 (2009) 3387.
[5] J. Motuzas, S. Heng, P.P.S.Z. Lau, K.L. Yeung, Z.J.Beresnevicius and A. Julbe, Micropor Mesopor Mater 99 (2007) 197.
[6] J.N. Hart, D. Menzies, Y.B. Cheng, G.P. Simon and L.Spiccia, Sol Energy Mater Sol Cell 91 (2007) 6.
[7] J.N. Hart, Y.B. Cheng, G.P. Simon and L. Spiccia, Surf Coat Technol 198 (2005) 20.
[8] A. Lagashetty, V. Havanoor, S. Basavaraja, S.D. Balaji and A. Venkataraman, Sci Technol Adv Mater 8 (2007) 484.
[9] N.T.K. Sundaram, T. Vasudevan and A. Subramania, J Phys Chem Solids 68 (2007) 264.
[10] F.M. Moghaddam and H. Saeidian, Mater Sci Eng B 139 (2007) 265.
[11] J.H. Yang, K.W. Song, Y.W. Lee and J.H. Kim, J Nucl Mater 325 (2004) 210.
[12] B. Ayaz and A.N. Bilge, J Nucl Mater 280 (2000) 45.
[13] B.F. Pei and D.Z. Duan, Nucl Power Eng Technol 7 (1994) 41.
[14] A.J. Adeloye and A.D. Munari, J Hydrol 362 (2006) 215.
[15] B.G. Kermani, S.S. Schiffman and T. Nagle, Sens Actuators B 110 (2005) 13.
[16] G. Lera and M. Pinzolas, IEEE Trans Neural Netw 13 (2002) 1200.
[17] H. Mirzaee, Chaos Soliton Fract 41 (2009)1975.
[18] V. Singh, I. Gupta and H.O. Gupta, Eng Appl Artif Intel 20 (2007) 249.
[19] Y.W. Li, Z.T. Yu, X.Y. Meng, W.G. Che and C.L. Mao, Proc Int Conf Future Gener Commun Netw FGCN 2 (2008) 149.
[20] J. Ghosh and A.C. Nag, Neural Netw 2 (2002)1322.
[21] L.M. Fu, IEEE Trans Neural Netw 7 (1996)757.
[22] J. Zhang and A.J. Morris, Neural Netw 11 (1998) 65.
[23] R. Parekh, J. Yang and V. Honavar, IEEE Trans Neural Netw 11 (2000) 436.
[24] N.B. Karayiannis and G.W. Mi, IEEE Trans Neural Netw 8 (1997) 1492.
[25] G.L. Su and F.P. Deng, Bull Sci Technol 19 (2003) 130 (in Chinese).
[26] E.M. Bezerra, M.S. Bento, J.A.F.F. Rocco, K. Iha, V.L.Lourenco and L.C. Pardini, Comput Mater Sci 44 (2008)656.
[27] E.D. Ubeyli and I. Guler, Neurocomput 62 (2004) 349.
[28] X. Wen, L. Zhou and D.L. Wang, Matlab Neural Network Application Design (Science Press, Beijing, 2002) (in Chinese).
WeChat