Self-organizing input space for control of structures

We propose a novel type of neural networks for structural control, which comprises an adaptive input space. This feature is purposefully designed for sequential input selection during adaptive identification and control of nonlinear systems, which allows the input space to be organized dynamically, while the excitation is occurring. The neural network has the main advantages of (1) automating the input selection process for time series that are not known a priori; (2) adapting the representation to nonstationarities; and (3) using limited observations. 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, which in our case is a wavelet neural network, is subsequently updated. We demonstrate that the neural net has the potential to significantly improve convergence of a black-box model in adaptive tracking of a nonlinear system. Its performance is further assessed in a full-scale simulation of an existing civil structure subjected to nonstationary excitations (wind and earthquakes), and shows the superiority of the proposed method.

[1]  F. Girosi,et al.  Networks for approximation and learning , 1990, Proc. IEEE.

[2]  Bijan Samali,et al.  Benchmark Problem for Response Control of Wind-Excited Tall Buildings , 2004 .

[3]  John Zolock,et al.  A Methodology for the Modeling of Forced Dynamical Systems From Time Series Measurements Using Time-Delay Neural Networks , 2009 .

[4]  Abdolreza Joghataie,et al.  Dynamic Analysis of Nonlinear Frames by Prandtl Neural Networks , 2008 .

[5]  Chin-Hsiung Loh,et al.  Semi-active control of a torsionally-responsive structure , 2009 .

[6]  Simon Laflamme.  Control of Large-Scale Structures with Large Uncertainties , 2011 .

[7]  Michael D. Todd,et al.  A parametric investigation of state-space-based prediction error methods with stochastic excitation for structural health monitoring , 2007 .

[8]  Jean-Jacques E. Slotine,et al.  Adaptive sliding controller synthesis for non-linear systems , 1986 .

[9]  Douglas P. Taylor,et al.  Fluid viscous dampers for high‐rise buildings , 2003 .

[10]  Qinghua Zhang,et al.  Wavelet networks , 1992, IEEE Trans. Neural Networks.

[11]  Faryar Jabbari,et al.  Structural control via semi-active and hybrid control , 1997, Proceedings of the 1997 American Control Conference (Cat. No.97CH36041).

[12]  Satish Nagarajaiah,et al.  A STFT semiactive controller for base isolated buildings with variable stiffness isolation systems , 2005 .

[13]  M. Moraud.  Wavelet Networks , 2018, Foundations of Wavelet Networks and Applications.

[14]  Mohamed Abdellaoui Maane,et al.  Modified friction device for control of large‐scale systems , 2012 .

[15]  Sheng Chen,et al.  Model selection approaches for non-linear system identification: a review , 2008, Int. J. Syst. Sci..

[16]  Michael C. Constantinou,et al.  Semi-active control systems for seismic protection of structures: a state-of-the-art review , 1999 .

[17]  Chin-Hsiung Loh,et al.  Semi-active control of floor isolation system using MR-damper , 2008, SPIE Smart Structures and Materials + Nondestructive Evaluation and Health Monitoring.

[18]  Isabelle Guyon,et al.  An Introduction to Variable and Feature Selection , 2003, J. Mach. Learn. Res..

[19]  J. Príncipe,et al.  Local dynamic modeling with self-organizing maps and applications to nonlinear system identification and control , 1998, Proc. IEEE.

[20]  Chih-Chen Chang,et al.  Adaptive fuzzy control for nonlinear building-magnetorheological damper system , 2003 .

[21]  E. Ryabov,et al.  Intramolecular vibrational redistribution: from high-resolution spectra to real-time dynamics , 2012 .

[22]  Hyung-Jo Jung,et al.  Semi‐active neurocontrol of a base‐isolated benchmark structure , 2006 .

[23]  Gary C. Hart,et al.  The structural design of tall and special buildings , 2005 .

[24]  Jerome J. Connor,et al.  Application of self-tuning Gaussian networks for control of civil structures equipped with magnetorheological dampers , 2009, Smart Structures and Materials + Nondestructive Evaluation and Health Monitoring.

[25]  Weiping Li,et al.  Applied Nonlinear Control , 1991 .

[26]  Hyun-Yong Jeong,et al.  A study on the hysteresis, surface temperature change and fatigue life of SM490A, SM490A-weld and FC250 metal materials , 2010 .

[27]  F. Takens.  Detecting strange attractors in turbulence , 1981 .

[28]  Application of self-tuning Gaussian networks for control of civil structures equipped with magnetorheological dampers , 2009 .

[29]  N. Wongprasert,et al.  Numerical evaluation of adaptive base-isolated structures subjected to earthquake ground motions , 2005 .

[30]  B. Sp,et al.  State of the Art of Structural Control , 2003 .

[31]  V. P. Plagianakos,et al.  Chaotic analysis of seismic time series and short term forecasting using neural networks , 2001, IJCNN'01. International Joint Conference on Neural Networks. Proceedings (Cat. No.01CH37222).

[32]  Hong-Nan Li,et al.  Seismic Responses Prediction of Nonlinear Building Structures Based on Multi-Branch BP Neural Network , 2009, ISNN.

[33]  Victoria Caballero,et al.  On an Embedding Theorem , 2000 .

[34]  Sheng-Guo Wang,et al.  Robust Control for Structural Systems with Parametric and Unstructured Uncertainties , 2001 .

[35]  Frequency independent automatic input variable selection for Neural Networks for forecasting , 2010, The 2010 International Joint Conference on Neural Networks (IJCNN).

[36]  Liangyue Cao,et al.  Predicting chaotic time series with wavelet networks , 1995 .

[37]  C. S. Cai,et al.  Experimental Study of Magnetorheological Dampers and Application to Cable Vibration Control , 2006 .

[38]  David S. Broomhead,et al.  Delay Embeddings for Forced Systems. II. Stochastic Forcing , 2003, J. Nonlinear Sci..

[39]  Robert Babu.  Input Selection for Nonlinear Regression Models , 2004 .

[40]  J. Stark,et al.  Delay Embeddings for Forced Systems. I. Deterministic Forcing , 1999 .

[41]  T. T. Soong,et al.  Future directions in structural control , 2009 .

[42]  J. N. Yang,et al.  Sliding Mode Control for Nonlinear and Hysteretic Structures , 1995 .

[43]  Dingli Yu,et al.  Neural model input selection for a MIMO chemical process , 2000 .

[44]  H. Abarbanel,et al.  Determining embedding dimension for phase-space reconstruction using a geometrical construction. , 1992, Physical review. A, Atomic, molecular, and optical physics.

[45]  Narasimhan Sundararajan,et al.  Adaptive control of nonlinear smart base‐isolated buildings using Gaussian kernel functions , 2008 .

[46]  David M. Walker,et al.  Radial-Basis Models for Feedback Systems With Fading Memory , 2001 .

[47]  Jean-Jacques E. Slotine,et al.  Space-frequency localized basis function networks for nonlinear system estimation and control , 1995, Neurocomputing.

[48]  Sheng-Guo Wang,et al.  Robust control for structural systems with uncertainties , 1999, Smart Structures.

[49]  Michael D. Todd,et al.  A multivariate, attractor-based approach to structural health monitoring , 2005 .

[50]  Teuvo Kohonen,et al.  The self-organizing map , 1990 .

[51]  Holger R. Maier,et al.  Input determination for neural network models in water resources applications. Part 1—background and methodology , 2005 .

[52]  Niels Kjølstad Poulsen,et al.  Neural Networks for Modelling and Control of Dynamic Systems: A Practitioner’s Handbook , 2000 .

[53]  Monroig Evan,et al.  Detection of changes in dynamical systems by nonlinear time series analysis , 2009 .

[54]  S. O. Oyadiji,et al.  Diagonal Recurrent Neural Networks for MDOF Structural Vibration Control , 2008 .

[55]  Kazuyuki Aihara,et al.  Modeling dynamics from only output data. , 2009, Physical review. E, Statistical, nonlinear, and soft matter physics.

[56]  Kang Li,et al.  Neural input selection - A fast model-based approach , 2007, Neurocomputing.

[57]  Robert Babuska,et al.  Input selection for nonlinear regression models , 2004, IEEE Transactions on Fuzzy Systems.

[58]  Billie F. Spencer,et al.  Large-scale MR fluid dampers: modeling and dynamic performance considerations , 2002 .

[59]  Hyung-Jo Jung,et al.  An Experimental Study of Semiactive Modal Neuro-control Scheme Using MR Damper for Building Structure , 2008 .

[60]  Vitor Hugo Ferreira,et al.  Input space to neural network based load forecasters , 2008 .

[61]  Jamshid Ghaboussi,et al.  Active Control of Structures Using Neural Networks , 1995 .

[62]  Jarkko Tikka,et al.  Simultaneous input variable and basis function selection for RBF networks , 2009, Neurocomputing.

[63]  Fraser,et al.  Independent coordinates for strange attractors from mutual information. , 1986, Physical review. A, General physics.

[64]  Ron Kohavi,et al.  Wrappers for Feature Subset Selection , 1997, Artif. Intell..

[65]  Carlos Canudas de Wit,et al.  Friction Models and Friction Compensation , 1998, Eur. J. Control.

[66]  Pat Langley,et al.  Selection of Relevant Features and Examples in Machine Learning , 1997, Artif. Intell..

[67]  Bin Xu,et al.  NEURAL NETWORKS FOR DECENTRALIZED CONTROL OF CABLE-STAYED BRIDGE , 2003 .

[68]  Jerome J. Connor,et al.  Wavelet Network for Semi-Active Control , 2011 .