Adaptive Structural Control Using Dynamic Hyperspace

Adaptive Structural Control Using Dynamic Hyperspace

S. Laflamme

Department of Civil, Construction, and Environmental Engineering, Iowa State University, Ames, U.S.A.

| |
| | Citation



The design of closed-loop structural control systems necessitates a certain level of robustness to cope with system uncertainties. Neurocontrollers, a type of adaptive control system, have been proposed to cope with those uncertainties. However, the performance of neural networks can be substantially influenced by the choice of the input space, or the hyperspace in which the representation lies. For instance, input selection may influence computation time, adaptation speed, effects of the curse of dimensionality, understanding of the representation, and model complexity. Input space selection is often overlooked in literature, and inputs are traditionally determined offline for an optimized performance of the neurocontroller. Such offline input selection is often unrealistic to conduct in the case of civil structures. In this paper, a novel method for automating the input selection process for neural networks is presented. The method is purposefully designed for online input selection during adaptive identification and control of nonlinear systems. Input selection is conducted online and sequentially, while the excitation is occurring. The algorithm designed for the adaptive input space assumes local quasi-stationarity of the time series, and embeds local maps sequentially in a delay vector using the embedding theorem. The input space of the representation is subsequently updated. The performance of the proposed dynamic input selection method is demonstrated through simulating semi-active control of an existing structure located in Boston, MA, U.S.A. Simulation results show the substantial performance of the proposed algorithm over traditional fixed-inputs strategies.


Adaptive control, adaptive hyperspace, adaptive input, online sequential network, self- organizing input, sequential neural network, structural control


[1] Poggio, T. & Girosi, F., Networks for approximation and learning. Proceedings of the IEEE, 78(9), pp. 1481–1497, 1990. doi:

[2] Zhang, Q., Benveniste, A. & Hogskola, L., Wavelet networks. IEEE Transactions on Neural Networks, 3(6), pp. 889–898, 1992. doi:

[3] Bowden, G., Dandy, G. & Maier, H., Input determination for neural network models in water resources applications. Part 1–background and methodology. Journal of Hydrol-ogy, 301(1–4), pp. 75–92, 2005. doi:

[4] da Silva, A., Alexandre, P., Ferreira, V. & Velasquez, R., Input space to neural network based load forecasters. International Journal of Forecasting, 24(4), pp. 616–629, 2008. doi:

[5] Sindelar, R. & Babuska, R., Input selection for nonlinear regression models. Fuzzy Systems, IEEE Transactions on, 12(5), pp. 688–696, 2004. doi:

[6] Hong, X., Mitchell, R., Chen, S., Harris, C., Li, K. & Irwin, G., Model selection approaches for non-linear system identification: a review. International Journal of Systems Science, 39(10), pp. 925–946, 2008. doi:

[7] Blum, A. & Langley, P., Selection of relevant features and examples in machine learning. Artificial Intelligence, 97(1–2), pp. 245–271, 1997. doi:

[8] Kohavi, R. & John, G., Wrappers for feature subset selection. Artificial Intelligence, 97(1–2), pp. 273–324, 1997. doi:

[9] Guyon, I. & Elisseeff, A., An introduction to variable and feature selection. The Journal of Machine Learning Research, 3, pp. 1157–1182, 2003.

[10] Yu, D., Gomm, J. & Williams, D., Neural model input selection for a MIMO chemical process. Engineering Applications of Artificial Intelligence, 13(1), pp. 15–23, 2000. doi:

[11] Li, K. & Peng, J., Neural input selection: a fast model-based approach. Neurocomputing, 70(4–6), pp. 762–769, 2007. doi:

[12] Tikka, J., Simultaneous input variable and basis function selection for RBF networks. Neurocomputing, 72(10–12), pp. 2649–2658, 2009. doi:

[13] Kourentzes, N. & Crone, S., Frequency independent automatic input variable selection for neural networks for forecasting. The 2010 International Joint Conference on Neural Networks (IJCNN), pp. 1–8, 2010. doi:

[14] Takens, F., Detecting Systems and Turbulence. Lecture Notes in Mathematics, Warwick 1980, 898, pp. 366–381, 1980.

[15] Stark, J., Delay embeddings for forced systems. I. Deterministic forcing. Journal of Nonlinear Science, 9(3), pp. 255–332, 1999. doi:

[16] Caballero, V., On an embedding theorem. Acta Mathematica Hungarica, 88(4), pp. 269–278, 2000. doi:

[17] Stark, J., Broomhead, D., Davies, M. & Huke, J., Delay embeddings for forced systems. II. Stochastic forcing. Journal of Nonlinear Science, 13(6), pp. 519–577, 2003. doi:

[18] Hirata, Y., Suzuki, H. & Aihara, K., Reconstructing state spaces from multivariate data using variable delays. Physical Review E, 74(2), p. 26202, 2006. doi:

[19] Nerukh, D., Ryabov, V. & Glen, R., Complex temporal patterns in molecular dynamics: a direct measure of the phase-space exploration by the trajectory at macroscopic time scales. Physical Review E, 77(3), p. 36225, 2008. doi:

[20] Monroig, E., Aihara, K. & Fujino, Y., Modeling dynamics from only output data. Physical Review E, 79(5), p. 56208, 2009. doi:

[21] Laflamme, S., Slotine, J.E. & Connor, J., Self-organizing input space for control of structures. Smart Materials and Structures, 21(11), p. 115015, 2012. doi:

[22] Kohonen, T., The self-organizing map. Proceedings of the IEEE, 78(9), pp. 1464–1480, 1990. doi:

[23] Laflamme, S., Slotine, J. & Connor, J., Wavelet network for semi-active control. J of Engineering Mechanics, 137(7), pp. 462–474, 2011. doi:

[24] Fraser, A. & Swinney, H., Independent coordinates for strange attractors from mutual information. Physical Review A, 33(2), pp. 1134–1140, 1986. doi:

[25] Kennel, M., Brown, R. & Abarbanel, H., Determining embedding dimension for phase-space reconstruction using a geometrical construction. Physical Review A, 45(6), pp. 3403–3411, 1992. doi:

[26] Overbey, L., Olson, C. & Todd, M., A parametric investigation of state-space-based prediction error methods with stochastic excitation for structural health monitoring. Smart Materials and Structures, 16, pp. 1621–1638, 2007. doi:

[27] McNamara, R. & Taylor, D., Fluid viscous dampers for high-rise buildings. The Structural Design of Tall and Special Buildings, 12(2), pp. 145–154, 2003. doi:

[28] Laflamme, S., Taylor, D., Abdellaoui Maane, M. & Connor, J., Modified friction device for control of large-scale systems. Structural Control and Health Monitoring, 19(4), pp. 548–564, 2012. doi: