Topic
System identification
About: System identification is a research topic. Over the lifetime, 21291 publications have been published within this topic receiving 439142 citations.
Papers published on a yearly basis
Papers
More filters
••
TL;DR: It is argued that for satisfactory modeling of dynamical systems, neural networks should be endowed with such internal memory as to identify systems whose order is unknown or systems with unknown delay.
Abstract: This paper discusses memory neuron networks as models for identification and adaptive control of nonlinear dynamical systems. These are a class of recurrent networks obtained by adding trainable temporal elements to feedforward networks that makes the output history-sensitive. By virtue of this capability, these networks can identify dynamical systems without having to be explicitly fed with past inputs and outputs. Thus, they can identify systems whose order is unknown or systems with unknown delay. It is argued that for satisfactory modeling of dynamical systems, neural networks should be endowed with such internal memory. The paper presents a preliminary analysis of the learning algorithm, providing theoretical justification for the identification method. Methods for adaptive control of nonlinear systems using these networks are presented. Through extensive simulations, these models are shown to be effective both for identification and model reference adaptive control of nonlinear systems. >
355 citations
•
01 Jan 2006TL;DR: In this article, the authors present a model of a single degree of freedom (SFL) system, which is a combination of linear and asymmetric feedback control systems with Damping.
Abstract: Preface. 1. SINGLE DEGREE OF FREEDOM SYSTEMS. Introduction. Spring-Mass System. Spring-Mass-Damper System. Forced Response. Transfer Functions and Frequency Methods. Measurement and Testing. Stability. Design and Control of Vibrations. Nonlinear Vibrations. Computing and Simulation in Matlab. Chapter Notes. References. Problems. 2. LUMPED PARAMETER MODELS. Introduction. Classifications of Systems. Feedback Control Systems. Examples. Experimental Models. Influence Methods. Nonlinear Models and Equilibrium. Chapter Notes. References. Problems. 3. MATRICES AND THE FREE RESPONSE. Introduction. Eigenvalues and Eigenvectors. Natural Frequencies and Mode Shapes. Canonical Forms. Lambda Matrices. Oscillation Results. Eigenvalue Estimates. Computational Eigenvalue Problems in Matlab. Numerical Simulation of the Time Response in Matlab. Chapter Notes. References. Problems. 4. STABILITY. Introduction. Lyapunov Stability. Conservative Systems. Systems with Damping. Semidefinite Damping . Gyroscopic Systems. Damped Gyroscopic Systems. Circulatory Systems. Asymmetric Systems. Feedback Systems. Stability in the State Space. Stability Boundaries. Chapter Notes. References. Problems. 5. FORCED RESPONSE OF LUMPED PARAMETER SYSTEMS. Introduction. Response via State Space Methods. Decoupling Conditions and Modal Analysis. Response of Systems with Damping. Bounded-Input, Bounded-Output Stability. Response Bounds. Frequency Response Methods. Numerical Simulations in Matlab. Chapter Notes. References. Problems. 6. DESIGN CONSIDERATIONS. Introduction. Isolators and Absorbers. Optimization Methods. Damping Design. Design Sensitivity and Redesign. Passive and Active Control. Design Specifications. Model Reduction. Chapter Notes. References. Problems. 7. CONTROL OF VIBRATIONS. Introduction. Controllability and Observability. Eigenstructure Assignment. Optimal Control. Observers (Estimators). Realization. Reduced-Order Modeling. Modal Control in State Space. Modal Control in Physical Space. Robustness. Positive Position Feedback Control. Matlab Commands for Control Calculations. Chapter Notes. References. Problems. 8. VIBRATION MEASUREMENT. Introduction. Measurement Hardware. Digital Signal Processing. Random Signal Analysis. Modal Data Extraction (Frequency Domain). Modal Data Extraction (Time Domain). Model Identification. Model Updating. Chapter Notes. References. Problems. 9. DISTRIBUTED PARAMETER MODELS. Introduction. Vibrations of Strings. Rods and Bars. Vibration of Beams. Membranes and Plates. Layered Materials. Viscous Damping. Chapter Notes. References. Problems. 10. FORMAL METHODS OF SOLUTION. Introduction. Boundary Value Problems and Eigenfunctions. Modal Analysis of the Free Response. Modal Analysis in Damped Systems. Transform Methods. Green's Functions. Chapter Notes. References. Problems. 11. OPERATORS AND THE FREE RESPONSE. Introduction. Hilbert Spaces. Expansion Theorems. Linear Operators. Compact Operators. Theoretical Modal Analysis. Eigenvalue Estimates. Enclosure Theorems. Oscillation Theory. Chapter Notes. References. Problems. 12. FORCED RESPONSE AND CONTROL. Introduction. Response by Modal Analysis. Modal Design Criteria. Combined Dynamical Systems. Passive Control and Design. Distribution Modal Control. Nonmodal Distributed Control. State Space Control Analysis. Chapter Notes. References. Problems. 13. APPROXIMATIONS OF DISTRIBUTED PARAMETER MODELS. Introduction. Modal Truncation. Rayleigh- Ritz-Galerkin Approximations. Finite Element Method. Substructure Analysis. Truncation in the Presence of Control. Impedance Method of Truncation and Control. Chapter Notes. References. Problems. APPENDIX A: COMMENTS ON UNITS. APPENDIX B: SUPPLEMENTARY MATHEMATICS. Index.
354 citations
••
08 Nov 2004TL;DR: A detailed overview of particle methods, a set of powerful and versatile simulation-based methods to perform optimal state estimation in nonlinear non-Gaussian state-space models, is provided.
Abstract: Particle methods are a set of powerful and versatile simulation-based methods to perform optimal state estimation in nonlinear non-Gaussian state-space models. The ability to compute the optimal filter is central to solving important problems in areas such as change detection, parameter estimation, and control. Much recent work has been done in these areas. The objective of this paper is to provide a detailed overview of them.
352 citations
••
TL;DR: An efficient and flexible parameter estimation scheme for grey-box models in the sense of discretely, partially observed Ito stochastic differential equations with measurement noise is presented along with a corresponding software implementation that provides more accurate and more consistent estimates of the parameters of the diffusion term.
351 citations
•
24 Apr 2006TL;DR: This paper presents a meta-modelling architecture for adaptive control of Nonlinear Discrete-Time Systems using a model called Adaptive NN Control Design using State Measurements Output Feedback NN Controller Design.
Abstract: BACKGROUND ON NEURAL NETWORKS NN Topologies and Recall Properties of NN NN Weight Selection and Training NN Learning and Control Architectures References Problems BACKGROUND AND DISCRETE-TIME ADAPTIVE CONTROL Dynamical Systems Mathematical Background Properties of Dynamical Systems Nonlinear Stability Analysis and Controls Design Robust Implicit STR References Problems Appendix 2.A NEURAL NETWORK CONTROL OF NONLINEAR SYSTEMS AND FEEDBACK LINEARIZATION NN Control with Discrete-Time Tuning Feedback Linearization NN Feedback Linearization Multilayer NN for Feedback Linearization Passivity Properties of the NN Conclusions References Problems NEURAL NETWORK CONTROL OF UNCERTAIN NONLINEAR DISCRETE-TIME SYSTEMS WITH ACTUATOR NONLINEARITIES Background on Actuator Nonlinearities Reinforcement NN Learning Control with Saturation Uncertain Nonlinear System with Unknown Deadzone and Saturation Nonlinearities Adaptive NN Control of Nonlinear System with Unknown Backlash Conclusions References Problems Appendix 4.A Appendix 4.B Appendix 4.C Appendix 4.D OUTPUT FEEDBACK CONTROL OF STRICT FEEDBACK NONLINEAR MIMO DISCRETE-TIME SYSTEMS Class of Nonlinear Discrete-Time Systems Output Feedback Controller Design Weight Updates for Guaranteed Performance Conclusions References Problems Appendix 5.A Appendix 5.B NEURAL NETWORK CONTROL OF NONSTRICT FEEDBACK NONLINEAR SYSTEMS Introduction Adaptive NN Control Design Using State Measurements Output Feedback NN Controller Design Conclusions References Problems Appendix 6.A Appendix 6.B SYSTEM IDENTIFICATION USING DISCRETE-TIME NEURAL NETWORKS Identification of Nonlinear Dynamical Systems Identifier Dynamics for MIMO Systems NN Identifier Design Passivity Properties of the NN Conclusions References Problems DISCRETE-TIME MODEL REFERENCE ADAPTIVE CONTROL Dynamics of an mnth-Order Multi-Input and Multi-Output System NN Controller Design Projection Algorithm Conclusions References Problems NEURAL NETWORK CONTROL IN DISCRETE-TIME USING HAMILTON-JACOBI-BELLMAN FORMULATION Optimal Control and Generalized HJB Equation in Discrete-Time NN Least-Squares Approach Numerical Examples Conclusions References Problems NEURAL NETWORK OUTPUT FEEDBACK CONTROLLER DESIGN AND EMBEDDED HARDWARE IMPLEMENTATION Embedded Hardware-PC Real-Time Digital Control System SI Engine Test Bed Lean Engine Controller Design and Implementation EGR Engine Controller Design and Implementation Conclusions References Problems Appendix 10.A Appendix 10.B INDEX
351 citations