Article

Modified dynamic minimization algorithm for parameter estimation of chaotic system from a time series

Nonlinear Dynamics (Impact Factor: 2.85). 10/2011; 66(1):213-229. DOI: 10.1007/s11071-010-9922-0

ABSTRACT

This paper proposes a modified dynamic minimization algorithm for parameter estimation of chaotic systems, based on a scalar
time series. Comparing with the previous design proposed by Maybhate and Amritkar (Phys. Rev. E 59:284–293, 1999), two important new design concepts related to the feedback control and the auxiliary functions for parametric updating laws
are introduced. Two different types of estimates can then be derived, and numerical simulations confirm their superior performances
to the designs based on the original dynamic minimization algorithm or other existing approaches. Furthermore, a circuit experiment
is carried out to demonstrate the robustness and practicability of the proposed design.

KeywordsChaotic systems–Dynamic minimization–Darameter estimation–Synchronization

1 Follower
 · 
8 Reads
  • [Show abstract] [Hide abstract]
    ABSTRACT: A method for estimating model parameters based on chaotic system response data is described. This estimation problem is made challenging by sensitive dependence to initial conditions. The standard maximum likelihood estimation method is practically infeasible due to the non-smooth nature of the likelihood function. We bypass the problem by introducing an alternative, smoother function that admits a better-defined maximum and show that the parameters that maximize this new function are asymptotically equivalent to maximum likelihood estimates. We use simulations to explore the influence of noise and available data on model Duffing and Lorenz oscillators. We then apply the approach to experimental data from a chaotic Duffing system. Our method does not require estimation of initial conditions and parameter estimates may be obtained even when system dynamics have been estimated from a delay embedding.
    No preview · Article · Oct 2012 · Nonlinear Dynamics
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: The identification of lithologies is a crucial task in continental scientific drilling research. In fact, in complex geological situations such as crystalline rocks, more complex nonlinear functional behaviors exist in well log interpretation/classification purposes; thus posing challenges in accurate identification of lithology using geophysical log data in the context of crystalline rocks. The aim of this work is to explore the capability of k-nearest neighbors classifier and to demonstrate its performance in comparison with other classifiers in the context of crystalline rocks. The results show that best classifier was neural network followed by support vector machine and k-nearest neighbors. These intelligence machine learning methods appear to be promising in recognizing lithology and can be a very useful tool to facilitate the task of geophysicists allowing them to quickly get the nature of all the geological units during exploration phase.
    Full-text · Conference Paper · Jun 2015
  • [Show abstract] [Hide abstract]
    ABSTRACT: This paper presents a principle of timing-sequence geometry that is used to express any dynamic system with highly precise and dynamic properties. It provides unified theoretical support for dynamic systems of different characteristics, and it is subversive compared with the traditional and related theories. The principle uses time series that implicate dynamic characteristics as the study object , skilfully embeds critical time elements in non-uniform rational B-splines (NURBSs) through a kind of thought “timing-geometry,” and obtains a “functional” relationship between geometry and time, called S-NURBS, which quantizes the nonlinear system and its dynamical properties. Two methods were provided for different research purposes. The first is the direct time NURBS method, which is appropriate for the study of the analytic properties of the dynamic system state space, and the other is the tangent vector NURBS method for the study of differential properties a system. In terms of the process of studying chaos characteristics, we proposed a new algorithm for the maximum Lyapunov exponent of chaotic time series based on the foundation of our principle. Using a few nonlinear systems, we verified the correctness and effectiveness of these methods within acceptable error limits according to the experimental results.
    No preview · Article · Nov 2015 · Nonlinear Dynamics