An improved Neural Kalman Filtering Algorithm in the analysis of cyclic behaviour of concrete specimens

Agnieszka Krok

Agnieszka Krok Institute of Computer Methods in Civil Engineering, Cracow University of Technology, Kraków

Abstract

The article is related to the results of research on Node Decoupled Extended Kalman Filtering (NDEKF) as a learning method for the training of Multilayer Perceptron (MPL). Developments of this method made by the author are presented. The application of NDEKF and MPL and other methods (pruning of MLP, Gauss Process model calibrated by Genetic Algorithm and Bayesian learning methods) are discussed on the problem of hysteresis loop simulations for tests of compressed concrete specimens subjected to cyclic loading.

Keywords

Artificial Neural Networks (ANN), Kalman Filter (KF), Node Decoupled Extended Kalman Filtering (NDEKF), Multilayer Perceptron (MPL), Genetic Algorithm (AG), Bayesian methods, concrete specimens, cyclic loading, hysteresis loops,

References

[1] S. Haykin. Neural Networks, A Comprehensive Foundation, 2nd Ed. MacMillan College Publ., Engle-wood Cliffs, NJ, 1999.
[2] S. Haykin. [Ed.], Kalman Filtering and Neural Networks, John Wiley & Sons, New York, 2001.
[3] R.E. Kalman. A new approach to linear filtering and prediction problems. Transactions of ASME, Journal of Basic Engineering, 82(D): 35–45, 1960.
[4] A. Krok, Z.Waszczyszyn. Neural prediction of response spectra from mining tremors using recurrent layered networks and Kalman filtering. In: J-K.Bathe [Ed.] Proc. 3rd MIT Conf. Computational Fluid and Solid Mechanics, pp. 302–305. Elsevier, 2005.
[5] A. Krok, Z. Waszczyszyn. Simulation of building loops for a superconductor using neural networks with Kalman filtering. Computer Assisted Mechanics and Engineering Sciences, 13: 575–582, 2006.
[6] A.Krok, Z. Waszczyszyn. Kalman filtering for neural prediction of response spectra from mining tremors. Computers and Structures, 85(15–16): 1257–1263, 2007.
[7] A. Krok. Analysis of Mechanics of Structures and Material Problems Applying Artificial Neural Networks Learnt by Means of Kalman Fltering (in Polish), Ph.D. Thesis, Institute of Computer Methods in Civil Engineering. Cracow Univ. of Technology, 2007.
[8] D. MacKay. Information Theory, Inference, and Learning Algorithms. Cambridge Univ. Press, 2003.
[9] I.T. Nabney. Netlab, Algorithms for pattern recognition. Springer, 2006.
[10] L. Prechelt. Adaptive Parameter Pruning in Neural Networks. International Computer Science Institute, University of California Technical Report TR-95-009, 1995.
[11] B.P. Sinha, K. H. Gerstle, L. G. Tulin, Stress-strain relations for concrete under cyclic loading. Journal of American Concrete Inst., 61(12): 1964.
[12] Neural Network Toolbox for Use with MATLAB, User’s Guide, Version 4. The MathWorks, Inc., Natick, MA,
2000.