Development Of System Identification Research Articles

Stages and main tasks of the century-long control theory and system identification development. Part IV. Methods and problems of designing robust control systems

The article provides a review of the most important methods and problems in the design of robust discrete control systems. In this case, the main attention was focused on the problems of suppressing limited external disturbances, information about which is presented only in the form of a limitation on their maximum value. The use of invariant ellipsoids is considered as the first mathematical apparatus for describing the characteristics of the influence of external disturbances on the trajectory of motion of dynamic systems. Theorems on the representation of invariant ellipsoids in the form of linear matrix inequalities (LMI) are formulated, which are further used to synthesize discrete state controllers that suppress external disturbances. The solution to a more general problem of robust suppression of limited disturbances based on the use of LMI in the presence of system uncertainties in the parameters of the mathematical model of the control object is considered. The use of H∞-control theory is considered as a second mathematical apparatus for suppressing external l2-limited external disturbances. In this case, the optimality criterion consists in minimizing the maximum ratio of the l2-norm of the vector of output stabilized coordinates to the l2-norm of the vector of input disturbances. The problem is solved by reducing it to the problem of robust control of a discrete dynamic system in space H∞ based on the Two-Ricatti approach. The standard H∞-optimization problem is also considered.

Stages and main tasks of the century-long control theory and system identification development. Part III. The problem of complex systems identifying by inaccurate data

The article presents the main most noteworthy research results on the identification problem and methods that are widely used in solving identification problems. The most significant here is the problem of modeling especially complex systems, for which it is impossible, even in general, but in constructive form for identification, to write down a class of models in which the system under study has the most accurate description in which there is one of them adequate to the available data obtained from experiments. If the available knowledge on the object under study does not allow us to write down a suitable class of models in mathematical form, then asymptotic modeling should be used, as is done in computational mathematics. Instead of differential, integral and other equations, for example, algebraic equations approximating them are solved, the solutions of which approach the exact ones with increasing dimension and discretization step. Various forms of asymptotic expansions are used in identification, including rational approximation as applied to irrational and infinite-dimensional systems. However, in the presence of errors in the data, the use of asymptotic modeling leads to the fact that, with intentions to increase the accuracy of the resulting model due to its large dimension, in many cases the identification problems becomes incorrectly posed. Therefore, we have to look for a compromise or trade-off between bias and variance, which should determine the best-quality model. In addition to the modeling problem, the article discusses two concepts on the basis of which most existing methods for solving identification problems are based. Both of them give their own interpretation of the errors present in the data, namely, stochastic and nonstochastic. With the stochastic concept, errors are treated as a random process or sequence. The concept of estimation consistency is introduced, which makes it possible to use widely the theory of statistics in justifying methods for solving identification problems. The nonstochastic identification paradigm allows for arbitrary but bounded uncertainties in the data, i.e. belonging to some bounded sets. The largest number of different methods, as well as algorithms and software implementations, are made within the framework of the stochastic concept. Within the framework of nonstochastic identification, we mainly consider various modifications of the so-called subspace methods. In relation to complex systems, problems were noted that did not allow the development of sufficiently universal and effective methods for solving identification problems. A number of research areas have been pointed out that need further development in order to obtain more accurate models of complex systems.

Stages and main tasks of the century-long control theory and system identification development

The article provides a review of the mathematical description of the dynamics of continuous and discrete linear stationary systems and objects, used at the development stage of the classical theory of automatic control in the form of mathematical models of the «input-output» type. The time and frequency characteristics of continuous and discrete control systems are described, typical links of stationary systems are considered, parametric discrete models of objects as part of typical digital control loops are presented. Stochastic discrete autoregressive models of stationary time series used to describe the dynamic objects in the synthesis of digital control systems are considered. A review of standard control laws for the implementation of continuous and discrete controllers has been completed. A method for synthesizing discrete controllers for multidimensional controlled objects with different, unknown and changing delays is considered, through which variable delays are compensated in the characteristic equation of a closed-loop control system. A common technique for synthesizing one-dimensional and multidimensional controllers for stochastic objects with delays based on ARMAX models is considered. An analysis of approaches to identifying delays in controlled objects is carried out and a method for identifying delays when using input-output models is considered, based on the calculation and comparison of impulse responses for extended and non-extended models of the controlled object. An analysis of the advantages and disadvantages of «input-output» type models is given, as well as the possibilities of their application for solving various classes of control theory problems.

Stages and main tasks of the century-long the control theory and system identification development. Part I. State space method in the theory of linear automatic control systems

This article opens a series of publications dedicated to the scientific and technical achievements of the century-long development of control theory and methods. Problems that could not be fully resolved based on one approach or another are also noted. The first of these articles is devoted to the state space method, which began to actively develop somewhere in the 70-80s of the last century within the framework of systems theory and general systems theory. A description of the method is given in relation to linear automatic control systems. A generally accepted description of controlled and observable dynamic processes in such systems is given. The problems of synthesis of stabilizing control in closed loop systems with feedback based on the theory of stability formulated by Lyapunov are mainly considered. In addition to stability, within the framework of the state space method, such important qualitative properties as controllability and observability are formulated. The most developed method is the synthesis of state-based linear controllers. Among them, a special pole placement by method of modal control synthesis occupies a special place which is considered within the framework of the Jordan implementation and various modifications of the method depending on the dimension of the control vector. The synthesis of an optimal controller with a quadratic criterion of a fairly general form is considered. In case of incomplete measurements, when the dimension of the output is less than the dimension of the state vector, in order to implement synthesized control laws based on the state, it becomes necessary to include a state estimator in the control system. In the deterministic case, you can use the Luenberger estimator described in the article, and in the presence of measurement errors in the form of zero-mean white noise, the widely used Kalman filter, also presented in the article. The output control method was not left unattended in the work. The conclusions give the advantages and disadvantages of control methods based on state-space descriptions.

Development of system identification from traditional concepts to real-time soft computing based

Advancement in computer and data acquisition technology gave the system identification a push forward, especially in the speed of the process and parallel calculation techniques. This article reviews the progress of system identification methods and techniques from traditional to modern methods and from offline to fast on-line analysis through previous years till these days. It takes into account part of artificial intelligence techniques (soft computing techniques), primarily artificial neural networks methods, for off-line system data analysis and real-time system identification, including the linear and non-linear issues. This study will provide a very concise survey for researchers about the development of system identification, its implementations, and techniques that have been used.

Robust EM kernel-based methods for linear system identification

Recent developments in system identification have brought attention to regularized kernel-based methods. This type of approach has been proven to compare favorably with classic parametric methods. However, current formulations are not robust with respect to outliers. In this paper, we introduce a novel method to robustify kernel-based system identification methods. To this end, we model the output measurement noise using random variables with heavy-tailed probability density functions (pdfs), focusing on the Laplacian and the Student’s t distributions. Exploiting the representation of these pdfs as scale mixtures of Gaussians, we cast our system identification problem into a Gaussian process regression framework, which requires estimating a number of hyperparameters of the data size order. To overcome this difficulty, we design a new maximum a posteriori (MAP) estimator of the hyperparameters, and solve the related optimization problem with a novel iterative scheme based on the Expectation–Maximization (EM) method. In the presence of outliers, tests on simulated data and on a real system show a substantial performance improvement compared to currently used kernel-based methods for linear system identification.

Improving Fatigue Evaluations of Structures Using In-Service Behavior Measurement Data

Conservative models and code practices are usually employed for fatigue-damage predictions of existing structures. Direct in-service behavior measurements are able to provide more accurate estimations of remaining-fatigue-life predictions. However, these estimations are often accurate only for measured locations and measured load conditions. Behavior models are necessary for exploiting information given by measurements and predicting the fatigue damage at all critical locations and for other load cases. Model-prediction accuracy can be improved using system identification techniques where the properties of structures are inferred using behavior measurements. Building upon recent developments in system identification where both model and measurement uncertainties are considered, this paper presents a new data-interpretation framework for reducing uncertainties related to prediction of fatigue life. An initial experimental investigation confirms that, compared with traditional engineering approaches, the methodology provides a safe and more realistic estimation of the fatigue reserve capacity. A second application on a full-scale bridge also confirms that using load-test data reduces the uncertainty related to remaining-fatigue-life predictions.

Identification of linear dynamic systems using the artificial bee colony algorithm

This paper presents an investigation into the development of system identification using the artificial bee colony (ABC) algorithm. A system identification task can be formulated as an optimization problem where the objective is to obtain a model and a set of parameters that minimize the prediction error between the measured plant outputs and the model outputs. The most common existing system identification approaches, such as the recursive least squares method and autoregressive exogenous method, are substantially analytical and based on a mathematical derivation of the system's model. Evolutionary computation, which seems to be a very promising approach, is an alternative to these methods because a little knowledge about the problem is sufficient in this approach and it can be easily combined with many other techniques from artificial intelligence, control engineering, machine learning, and so on. In this paper, an evolutionary approach for system identification is considered and attempted to demonstrate how the ABC algorithm can be applied in system identification tasks. Mathematical models of dynamic systems are obtained using difference equations represented in discrete time and the ABC algorithm is used to estimate the unknown parameters of the systems. Simulation results demonstrate that the proposed linear system identification method has good identification performance. Moreover, this method is applied to the identification of a direct current motor in order to show the performance of the ABC algorithm. The obtained results show that the identified and actual plant outputs successfully match each other.

Advance mathematical model to study and analyse the effects of total quality management (TQM) and operational flexibility on hospital performance

Total quality management (TQM) and operational flexibility are powerful and evolving management tools that are being implemented in many organisations worldwide, particularly in healthcare services. However, such implementation is yet to be seen in developing nations, particularly in health care. In an attempted response to such a gap, this paper provides a literature review on the principles and scope of TQM and operational flexibility in the healthcare industry and proposes a mathematical model, employing artificial neural networks, to study and analyse the implementation of TQM and operational flexibility dimensions towards improving hospital performance and reducing costs and medical errors. This study is the first of its kind in the field. The results yielded a very high degree of accuracy (more than 99.2%) in relating TQM variables and operational flexibility dimensions (inputs) to hospital performance (output), implying a highly accurate and strong model that can exactly determine the weaknesses in a hospitals performance and can define and pinpoint poor application of TQM and operations flexibility, particularly upon the development of system identification for this model.

System Identification Using Intelligent Algorithms

This research presents an investigation into the development of system identification using intelligent algorithms. A simulation platform of a flexible beam vibration using finite difference (FD) method is used to demonstrate the capabilities of the identification algorithms. A number of approaches and algorithms for system identifications are explored and evaluated. These identification approaches using (a) traditional Recursive Least Square (RLS) filter, (b) Genetic Algorithms (GAs) (c) Adaptive Neuro_Fuzzy Inference System (ANFIS) model (d) General Regression Neural Network (GRNN) and (e)Bees Algorithm (BA). The above algorithms are used to estimate a linear discrete second order model for the flexible beam vibration. The model is implemented, tested and validated to evaluate and demonstrate the merits of the algorithms for system identification. Finally, a comparative performance of error convergence of the algorithms is presented and discussed.

Identification from step responses with transient initial conditions

Over the last few years there have been some interesting developments in system identification from step and step-like responses. New methods have been proposed to simultaneously estimate model parameters and the delay from step responses that require the process to be at steady state when the step is applied. To deal with transient initial conditions, methods based on pulse responses and the so called piece-wise step tests and iterative algorithm based on a single step response have also been proposed. In this article we propose a new method to estimate model parameters and the delay from a single step response in the presence of transient initial conditions, which does not require iteration. The performance of the proposed procedure is demonstrated through simulations as well as applications on experimental data from a continuous heating tank process and a mixing process.

A personal view of the development of system identification: A 30-year journey through an exciting field

In this article the author describes the development of system identification in the control community as he has observed it over the last 30 years, both as a student of the subject eager to learn and understand the work of his colleagues and as an active participant in these developments. This article attempts to exhibit both the continuity and the motivation for developments in system identification in the last 30 years and also the significant new departures and insights that came as the result of some important breakthroughs

A personal view on the development of system identification

This paper presents the author's personal view on the development of identification theory in the control community, starting from the year 1965. We show how two landmark papers, (Ho and Kalman, 1965) and (Åström and Bohlin, 1965), gave birth to two main streams of research that have dominated the development of system identitication over the last fourty years. The Ho-Kalman paper, which gave a first solution to state-space realization theory, led to stochastic realization, and much later to subspace identification. The Åström-Bohlin paper laid the foundations for Maximum Likelihood methods based on parametric input-output models, which later became known as the highly successful Prediction Error Identification framework. The present paper also shows how the thinking in the identification community moved from a search for the "true system" to the formulation of identification as an approximation problem. This led to the view of identification as a design problem, in which the ultimate use of the model plays a paramount role in the formulation of the experiment design and in the choice of the identification criterion.

Ambient vibration studies for system identification of tall buildings

AbstractThe performance of a building under wind and seismic loads depends on stiffness and mass distribution, and may be estimated using finite element codes. Experience has, however, shown that such finite element models often fail to predict accurately the fundamental natural frequencies. Usually the frequencies will be underestimated, that is the building will turn out to be stiffer than anticipated, meaning the design would usually be conservative. On the other hand, effects like torsional eccentricity and foundation compliance may not be correctly modelled, which could be less desirable. A full understanding of linear performance under lateral loads can be obtained through experimental evaluation of the vibration modes. Traditionally only a limited range of modal analysis procedures and software has been applied to civil applications and the ‘special case’ where no input forces can be measured has been the usual situation for large civil structures. Recent developments in system identification, which is the set of procedures to build mathematical models of the dynamic structural systems based on measured data, have added significantly to the potential of ambient vibration or ‘output only’ testing. The aim of the research reported here has been to apply and evaluate the procedures on typical buildings. The procedures are briefly explained and two experimental programmes are then described; a long‐term tremor monitoring exercise on a 280m office tower and an ambient vibration survey of a smaller office block. The different forms of response data are examined to study the performance of the analysis procedures and expose benefits and limitations in their use. There is a growing interest in output‐only modal analysis procedures in civil engineering. The experience reported in this paper has shown that quick and reliable estimation of mode shapes and frequencies can be obtained, even with small amounts of data. Judgement of modal participation and damping ratios requires more detailed study yet the results are at least as convincing as existing and relatively limited frequency domain methods. Copyright © 2002 John Wiley & Sons, Ltd.

Development of System Identification

Development of System Identification

Hierarchical system identification of models for urban dynamics

A critical problem in urban modeling is the validation of system models and identification of system parameters within an assumed structure. This paper applies recent developments in system identification in hierarchical structure to identification of system parameters for two models of urban dynamics.