Browse > Article
http://dx.doi.org/10.12989/sem.2013.45.1.053

Modeling and assessment of VWNN for signal processing of structural systems  

Lin, Jeng-Wen (Department of Civil Engineering, Feng Chia University)
Wu, Tzung-Han (Department of Civil Engineering, Feng Chia University)
Publication Information
Structural Engineering and Mechanics / v.45, no.1, 2013 , pp. 53-67 More about this Journal
Abstract
This study aimed to develop a model to accurately predict the acceleration of structural systems during an earthquake. The acceleration and applied force of a structure were measured at current time step and the velocity and displacement were estimated through linear integration. These data were used as input to predict the structural acceleration at next time step. The computation tool used was the Volterra/Wiener neural network (VWNN) which contained the mathematical model to predict the acceleration. For alleviating problems of relatively large-dimensional and nonlinear systems, the VWNN model was utilized as the signal processing tool, including the Taylor series components in the input nodes of the neural network. The number of the intermediate layer nodes in the neural network model, containing the training and simulation stage, was evaluated and optimized. Discussions on the influences of the gradient descent with adaptive learning rate algorithm and the Levenberg-Marquardt algorithm, both for determining the network weights, on prediction errors were provided. During the simulation stage, different earthquake excitations were tested with the optimized settings acquired from the training stage to find out which of the algorithms would result in the smallest error, to determine a proper simulation model.
Keywords
gradient descent with adaptive learning rate algorithm; Levenberg/Marquardt algorithm; modeling; Taylor series; Volterra/Wiener neural network;
Citations & Related Records
Times Cited By KSCI : 2  (Citation Analysis)
연도 인용수 순위
1 Pei, J.S., Smyth, A.W. and Kosmatopoulos, E.B. (2004), "Analysis and modification of Volterra/Wiener neural networks for the adaptive identification of non-linear hysteretic dynamic systems", Journal of Sound and Vibration, 275, 693-718.   DOI   ScienceOn
2 Peng, C.Y. (2010), "Risk assessment and modeling of debris flow", Master Thesis, Feng Chia University, Taiwan. (In Chinese)
3 Qian, N. (1999), "On the momentum term in gradient descent learning algorithms", Neural Networks, 12, 145-151.   DOI   ScienceOn
4 Vyas, N.S. and Chatterjee, A. (2011), "Non-parametric identification of rotor-bearing system through Volterra-Wiener theories", IUTAM Symposium on Emerging Trends in Rotor DynamicsIUTAM Bookseries, 1011, 309-320.
5 Yeh, Y.C. (2003), Applications and Practices of Neural Network Models, Scholars Books, Taiwan. (In Chinese)
6 Adnani, A., Basri, M., Chaibakhsh, N., Abdul Rahman, M.B. and Salleh, A.B. (2011), "Artificial neural network analysis of lipase-catalyzed synthesis of sugar alcohol ester", Industrial Crops and Products, 33(1), 42-48.   DOI   ScienceOn
7 Barrio, R., Rodríguez, M., Abad, A. and Blesa, F. (2011), "Breaking the limits: the Taylor series method", Applied Mathematics and Computation, 217(20), 7940-7954.   DOI   ScienceOn
8 Chen, T.C., Han, D.J., Au, F.T.K. and Tham, L.G. (2003), "Acceleration of Levenberg-Marquardt training of neural networks with variable decay rate", International Joint Conference on Neural Networks Proceedings, Portland, Oregon, July, 1873-1878.
9 De Oliveira, M.A. (2011), "The influence of ARIMA-GARCH parameters in feed forward neural networks prediction", Neural Computing and Applications, 20, 687-701.   DOI   ScienceOn
10 Franz, M.O. and Scholkopf, B. (2006), "A unifying view of wiener and volterra theory and polynomial kernel regression", Neural Computation, 18(12), 3097-3118.   DOI   ScienceOn
11 Gao, Z. and Chen, X. (2011), "Structure data processing and damage identification based on wavelet and artificial neural network", Research Journal of Applied Sciences, Engineering and Technology, 3(10), 1203-1208.
12 Lin, J.W. and Chen, H.J. (2009), "Repetitive identification of structural systems using a nonlinear model parameter refinement approach", Shock and Vibration, 16(3), 229-240.   DOI
13 Haykin, S.O. (1994), Neural Networks: A Comprehensive Foundation, Prentice-Hall, Englewood Cliffs, NJ.
14 Kosmatopoulos, E.B., Smyth, A.W., Masri, S.F. and Chassiakos, A.G. (2001), "Robust adaptive neural estimation of restoring forces in nonlinear structures", Journal of Applied Mechanics, 68, 880-893.   DOI   ScienceOn
15 Lautour, O.R. and Omenzetter, P. (2010), "Damage classification and estimation in experimental structures using time series analysis and pattern recognition", Mechanical Systems and Signal Processing, 24, 1556-1569.   DOI   ScienceOn
16 Lin, J.W. (2010), "Mode-by-mode evaluation of structural systems using a bandpass-HHT filtering approach", Struct. Eng. Mech., 36(6), 697-714.   DOI   ScienceOn
17 Lin, J.W. (2011), "A hybrid algorithm based on EEMD and EMD for multi-mode signal processing", Struct. Eng. Mech., 39(6), 813-831.   DOI   ScienceOn
18 Lynch, J.P. and Loh, K.J. (2006), "A summary review of wireless sensors and sensor networks for structural health monitoring", The Shock and Vibration Digest, 38(2), 91-128.   DOI   ScienceOn
19 Masri, S.F., Smyth, A.W., Chassiakos, A.G., Nakamura, M. and Caughey, T.K. (1999), "Training neural networks by adaptive random search techniques", Journal of Engineering Mechanics, 125(2), 123-132.   DOI   ScienceOn
20 MathWorks (1994), Document Central: Traingda, Retrieved October 30, 2012, from http://www.mathworks.com/help/nnet/ref/traingda.html
21 Park, H.S., Lee, H.M. and Adeli, H. (2007), "A new approach for health monitoring of structures: terrestrial laser scanning", Computer-Aided Civil and Infrastructure Engineering, 22, 19-30.   DOI   ScienceOn
22 Park, S., Ahmad, S., Yun, C.B. and Roh, Y. (2006), "Multiple crack detection of concrete structures using impedance-based structural health monitoring techniques", Experimental Mechanics, 46, 609-618.   DOI   ScienceOn