Identification Of Continuous Systems Research Articles

Identification of Continuous-Time Systems with Multiple Unknown Time Delays Using an Output Error Method from Sampled Data

This paper deals with simultaneous identification of continuous systems with multiple unknown time delays from sampled input–output data. In order to estimate, simultaneously, the parameters and the time delays of the system, an output errors method using a nonlinear programming algorithm based on sensitivity functions is discussed. Nevertheless, the initial values of the adjustable parameters should be determined from physical insight or guessed by previous methods. The convergence of the proposed method has been analyzed with theorems and proofs. The simulation example indicates that the proposed algorithm can generate highly accurate parameter estimates.

Real-time tracking control of electro-hydraulic force servo systems using offline feedback control and adaptive control

This paper focuses on an application of an electro-hydraulic force tracking controller combined with an offline designed feedback controller (ODFC) and an online adaptive compensator in order to improve force tracking performance of an electro-hydraulic force servo system (EHFS). A proportional-integral controller has been employed and a parameter-based force closed-loop transfer function of the EHFS is identified by a continuous system identification algorithm. By taking the identified system model as a nominal plant model, an H∞ offline design method is employed to establish an optimized feedback controller with consideration of the performance, control efforts, and robustness of the EHFS. In order to overcome the disadvantage of the offline designed controller and cope with the varying dynamics of the EHFS, an online adaptive compensator with a normalized least-mean-square algorithm is cascaded to the force closed-loop system of the EHFS compensated by the ODFC. Some comparative experiments are carried out on a real-time EHFS using an xPC rapid prototype technology, and the proposed controller yields a better force tracking performance improvement.

HS 최적화 알고리즘을 이용한 계단응답과 연속시스템 인식

HS 최적화 알고리즘을 이용한 계단응답과 연속시스템 인식

System Identification of Heat-Transfer Process of Frequency Induction Furnace for Melting Copper Based on Particle Swarm Algorithm

An adaptive evolutionary strategy in standard particle swarm optimization is introduced. Adaptive evolution particle swarm optimization is constructed to improve the capacity of global search. A method based on adaptive evolution particle swarm optimization for identification of continuous system with time delay is proposed. The basic idea is that the identification of continuous system with time delay is converted to an optimization of continuous nonlinear function. The adaptive evolution particle swarm optimization is utilized to find an optimal solution of continuous nonlinear function. Convergence conditions are given by the convergence analysis based on discrete time linear dynamic system theory. Numerical simulation results show that the proposed method is effective for a general continuous system with time delay and the system of heat-transfer process of frequency induction furnace for melting copper.

Identificación de sistemas en lazo cerrado basada en una estrategia híbrida AGA-Simplex

Closed-loop identification of continuous systems, which can be considered as a nonlinear optimization problem, may result in a difficult solution problem when conventional methods are used. In this paper it is presented a hybrid strategy based on an Adaptive Genetic Algorithm and the Simplex method, that results in a satisfactory solution for this problem. The proposal is compared with other techniques reported in the literature. Three examples show the performance of the method: identification of high order dynamics; identification of unstable second order dynamics in open-loop; and parameter estimation in power generation systems. Simulation results show that the proposed is a robust method for close-loop system identification.

Use of two-stage least-squares algorithms for identification of continuous systems with time delay based on pulse responses

This paper presents the so-called two-stage least-squares algorithms to deal with practical identification difficulties often encountered in field testing, such as unsteady initial states, unknown load disturbances, and noise-corrupted measurement. For step and ramp responses, a general linear regression equation is derived from multiple integration of the differential system equation. Four types of pulse inputs are then considered, each of which has its specific advantage in applications and can be represented as a combination of step or ramp inputs. Based on any of these pulse responses, the algorithms are able to overcome those difficulties and yield accurate parameter estimates in a sequential manner. The resulting identification scheme provides a convenient way to give the delay estimate along with system parameters and is robust with respect to noise and model structure mismatch.

The Laplace Image of Random Processes and Nonparametric Identification of Continuous Systems

The Laplace image of stationary random normal processes is studied. The covariance function of the Laplace image of white noise is converted by a linear shaping filter into the covariance function of the Laplace image of the filter output process. The relationship between the covariance function of the Laplace image of a random process and the autocovariance function and spectral density is determined. The covariance function of the Laplace image of measurement errors of a transition process in a stationary linear system is applied in optimal nonparametric identification of the transfer function.

Building inferential prediction models of batch processes using subspace identification

In this paper, a general method for converting available batch plant data into useful prediction models is proposed. A subspace identification method, which was proposed for identification of continuous systems, is used to develop a batch-to-batch correlation model from plant data. In this context, the state of the model is a holder of relevant information contained in the past batch data for predicting the behavior of current and future batches. The modeling framework naturally allows the user to capture correlations among the variables within each individual batch as well as those of successive batches, as reflected in the modeling data, and take advantage of them in prediction and control. It will be shown that the batch-to-batch model can be converted into a time transition model that can be used to predict the future behavior of the relevant variables, including the end-quality variables, in real time based on incoming measurements. Various practical issues will be addressed, such as the reduction of state dimension and incorporation of delayed laboratory measurements of quality variables.

Robust identification of continuous systems with dead-time from step responses

In this paper, a simple yet robust method is proposed for identification of linear continuous time-delay processes from step responses. New linear regression equations are derived from the solution and its various-order integrals of the process differential equation. The regression parameters are then estimated without iterations, and explicit relationship between the regression parameters and those in the process are given. Due to use of the process output integrals in the regression equations, the resulting parameter estimation is very robust in the face of large measurement noise in the output. The proposed method is detailed for a second-order plus dead-time model with one zero, which can approximate most practical industrial processes, covering monotonic or oscillatory dynamics of minimum-phase or non-minimum-phase processes. Such a model can be obtained without any iteration. The effectiveness of the identification method has been demonstrated through simulation and real-time implementation.

Nonlinear Continuous System Identification by Means of Multiple Integration II

This paper presents a new modification of the multiple integration method [1, 2, 3] for continuous nonlinear SISO system identification from measured input - output data. The model structure is changed compared with [1]. This change enables more sophisticated systems to be identified. The resulting MATLAB program is available in [4]. As was stated in [1], there is no need to reach a steady state of the identified system. The algorithm also automatically filters the measured data with respect to low frequency drifts and offsets, and offers the user a potent tool for selecting the frequency range of validity of the obtained model.

Optimal Identification of Continuous Systems and A New Fast Algorithm for On-Line Mode

The optimal method for identification of parameters Θ of continuous linear SISO system by the use of modulating functions is presented. Solution to this problem leads directly to minimization of quadratic form ΘTGΘ on the unit ball ΘTΘ=1 where G obtained from measurements is real, symmetric, positively defined Gram matrix and vector Θ∈Rn is unknown and should be found. The optimal solution for this minimization is eigenvector W1 related to minimal eigenvalue λ1 of matrix G. The main new problem stated and solved in this paper is the fast algorithm based on the behavior of some nonlinear differential equation which is fulfilled on eigenvector w1(t)=Θ(t) of nonstationary matrix G(t) obtained in on-line mode.

Parameter identification of continuous systems with multiple-input time delays via modulating functions

The identification of continuous systems with multiple-input delays is discussed. A batch algorithm for parametric identification of both multiple time delays and unknown parameters is proposed, using the modulating function approach. If the unknown delay is expressed as a linear combination of a bank of known delays, it is proven that the distribution of the identified coefficients is a sampling centred on the unknown delays; the result is then extended to the multiple delay case. The modulating function method guarantees a continuous-time approach and robustness for a high value of noise-to-signal ratio. Simulation results are included to illustrate the proposed technique.

A New Scheme of Nonlinear Continuous System Identification Using Radial Basis Function Networks

A New Scheme of Nonlinear Continuous System Identification Using Radial Basis Function Networks

Identification of continuous systems via markov parameters and time moments

This paper proposes an identification algorithm for MIMO continuous systems via the Markov parameters and the time moments. The considered system is transformed to a continuous-time system such that the transformed system is stable, the generalized time moment M i (α) of the transformed system exists for even unstable original system, and the Markov parameter G i of the original system is equal to M i (α)/ i ! ( i = 0, 1,…). The minimum realization of the MIMO continuous-time system is identified by the ॉ-minimal realization method using the Markov parameters, which can be achieved by approximately calculating the generalized time moments of the transformed system from sampled input-output data of the impulse response. An illustrative example shows that the algorithm provides robust identification results even if the system considered is unstable and there exists observing noise.

On-line Identification of Ship Maneuverability Indices by Using IIR Filters

The direct parameter estimation algorithm is applied to the simple linear maneuvering model (T-K model). The algorithm is composed of the IIR (Infinite Impulse Response) digital filters and RLS (Recursive Least Square) method. The IIR digital filters are introduced to avoid taking direct derivatives and to reduce the effects of measurement noise. Furthermore, the digital filters are free from the initial condition problem and the accumulation problem of integration error.In order to discuss the quantitative accuracy, the authors carried out onboard tests. And, the direct parameter estimation algorithm is compared with an indirect algorithm with RLS method. There is satisfactory agreement of the ship maneuverability indices T-K estimated by the direct identification method and the ordinary graphical analysis. This concludes that the direct parameter estimation algorithm With IIR filters is a powerful tool for on-line identification of continuous systems.

An Online Method for Identification of MIMO Systems using Hermite Polynomials

The use of orthogonal functions for continuous system identification has evoked a great interest among control scientists during the past few decades. In this paper a method for online identification of multi input-multi output (MIMO) systems via Hermite polynomials is presented. The proposed approach facilitates the use of continuous time model itself and a multivariable least square method is used for estimation. The method is general and can accommodate any other set of orthogonal functions. The algorithm is illustrated through an example. Monte Carlo results are also included.

Optimal Identification Of Continuous Systems In L2 Space By The Use Of Compact Support Filter

The authors present some new results of identification method for continuous systems, known as “modulating functions.” In the primary stage the parameter identification of a continuous SISO model described by an ordinary differential equation is based on convolution of the measured input-output signals and a special filtering function with compact support. This leads to a new model that has an alge-braic (nondifferential) form with the same parameters. In the next stage the authors formulate and find the solution of optimal identification problem for the latter model by minimizing the norm of the error in function space L . The procedures for online identification are presented.

Impulse Response Identification of Continuous Systems using Generalized Radial Basis Function Networks

In this paper, the authors propose a new identification method for the continuous-time impulse response model (CTIRM) of a linear system from sampled data in the ill-posed cases of band-limited input, fast sampling rate and measurement noise of high level which may be colored. To achieve smooth estimate, the CTIR which is viewed as a continuous function of time, is approximated by a generalized radial basis function network (GRBFN) in which the gaussian basis functions are equidistantly located in the time-domain and have the same width. Then the parameters of the GRBFN are estimated by the least-squares (LS) method. The design techniques of the center distance and the basis function width axe also shown using frequency-domain analysis. Simulation results are included to verify the performance of the proposed method.

Comparison of Direct and Indirect Approaches for Continuous System Identification

The direct and indirect approaches for parameter estimation of continuous-time systems are compared in the aspects such as pre-filtering of signals, the choices of the sampling period and the input signal, and the computational burden. Each approach has its merits and demerits. It is found that generally the direct approach is superior to the indirect approach for on-line applications because the direct approach is more straightforward and has less computational burden. Some important problems and their solutions in each approach are reviewed, and a number of illustrative experimental results are also presented.

Time Moments for Continuous System Identification

Time Moments for Continuous System Identification