D-optimal input design for nonlinear FIR-type systems: a dispersion-based approach

DOI10.1016/J.AUTOMATICA.2016.04.052zbMATH Open1372.93204arXiv1703.08401OpenAlexW2514881778MaRDI QIDQ2409286FDOQ2409286

Johan Schoukens, Alexander De Cock, Michel Gevers

Publication date: 11 October 2017

Published in: Automatica (Search for Journal in Brave)

Abstract: Optimal input design is an important step of the identification process in order to reduce the model variance. In this work a D-optimal input design method for finite-impulse-response-type nonlinear systems is presented. The optimization of the determinant of the Fisher information matrix is expressed as a convex optimization problem. This problem is then solved using a dispersion-based optimization scheme, which is easy to implement and converges monotonically to the optimal solution. Without constraints, the optimal design cannot be realized as a time sequence. By imposing that the design should lie in the subspace described by a symmetric and non-overlapping set, a realizable design is found. A graph-based method is used in order to find a time sequence that realizes this optimal constrained design. These methods are illustrated on a numerical example of which the results are thoroughly discussed. Additionally the computational speed of the algorithm is compared with the general convex optimizer cvx.

Full work available at URL: https://arxiv.org/abs/1703.08401

Recommendations

• D-optimal design for parameter estimation in discrete-time nonlinear dynamic systems
• A graph theoretical approach to input design for identification of nonlinear dynamical models
• Input design for structured nonlinear system identification
• scientific article; zbMATH DE number 6315686
• On robust input design for nonlinear dynamical models

zbMATH Keywords

convex optimizationsystem identificationnonlinear systemsinput design

Mathematics Subject Classification ID

Convex programming (90C25) Nonlinear systems in control theory (93C10) Estimation and detection in stochastic control theory (93E10) Identification in stochastic control theory (93E12)

Cites Work

• Using SeDuMi 1.02, A Matlab toolbox for optimization over symmetric cones
• Title not available (Why is that?)
• Monotonic convergence of a general algorithm for computing optimal designs
• Dynamic system identification. Experiment design and data analysis
• Closed loop experiment design for linear time invariant dynamical systems via LMIs
• Least costly identification experiment for control
• Experimental design for dynamics identification of cellular processes
• Closed-Loop Optimal Experiment Design: Solution via Moment Extension
• System identification of complex and structured systems
• Optimal experiment design for open and closed-loop system identification
• Eulerian graphs and related topics. Part 1, Volume 1
• Discussion on: ``Identification of multivariable models of fast ferries
• Title not available (Why is that?)
• Finding All the Elementary Circuits of a Directed Graph
• A graph theoretical approach to input design for identification of nonlinear dynamical models
• Input design for structured nonlinear system identification
• Computing Optimal Experimental Designs via Interior Point Method
• Control-relevant experiment design for multivariable systems described by expansions in orthonormal bases

Cited In (3)

• Iterative identification algorithms for bilinear-in-parameter systems with autoregressive moving average noise
• Information matrix and D-optimal design with Gaussian inputs for Wiener model identification
• Title not available (Why is that?)

Uses Software

• SeDuMi
• CVX

This page was built for publication: D-optimal input design for nonlinear FIR-type systems: a dispersion-based approach

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2409286)