Volume 19 (2009): Issue 2 (June 2009)

The form of topological derivatives for an integral shape functional is derived for a class of semilinear elliptic equations. The convergence of finite element approximation for the topological derivatives is shown and the error estimates in the L∞ norm are obtained. The results of numerical experiments which confirm the theoretical convergence rate are presented.

The article considers the effectiveness of various methods used to solve systems of linear equations (which emerge while modeling computer networks and systems with Markov chains) and the practical influence of the methods applied on accuracy. The paper considers some hybrids of both direct and iterative methods. Two varieties of the Gauss elimination will be considered as an example of direct methods: the LU factorization method and the WZ factorization method. The Gauss-Seidel iterative method will be discussed. The paper also shows preconditioning (with the use of incomplete Gauss elimination) and dividing the matrix into blocks where blocks are solved applying direct methods. The motivation for such hybrids is a very high condition number (which is bad) for coefficient matrices occuring in Markov chains and, thus, slow convergence of traditional iterative methods. Also, the blocking, preconditioning and merging of both are analysed. The paper presents the impact of linked methods on both the time and accuracy of finding vector probability. The results of an experiment are given for two groups of matrices: those derived from some very abstract Markovian models, and those from a general 2D Markov chain.

The combination of model predictive control based on linear models (MPC) with feedback linearization (FL) has attracted interest for a number of years, giving rise to MPC+FL control schemes. An important advantage of such schemes is that feedback linearizable plants can be controlled with a linear predictive controller with a fixed model. Handling input constraints within such schemes is difficult since simple bound contraints on the input become state dependent because of the nonlinear transformation introduced by feedback linearization. This paper introduces a technique for handling input constraints within a real time MPC/FL scheme, where the plant model employed is a class of dynamic neural networks. The technique is based on a simple affine transformation of the feasible area. A simulated case study is presented to illustrate the use and benefits of the technique.

This paper describes structured neural models and a computationally efficient (suboptimal) nonlinear Model Predictive Control (MPC) algorithm based on such models. The structured neural model has the ability to make future predictions of the process without being used recursively. Thanks to the nature of the model, the prediction error is not propagated. This is particularly important in the case of noise and underparameterisation. Structured models have much better long-range prediction accuracy than the corresponding classical Nonlinear Auto Regressive with eXternal input (NARX) models. The described suboptimal MPC algorithm needs solving on-line only a quadratic programming problem. Nevertheless, it gives closed-loop control performance similar to that obtained in fully-fledged nonlinear MPC, which hinges on online nonconvex optimisation. In order to demonstrate the advantages of structured models as well as the accuracy of the suboptimal MPC algorithm, a polymerisation reactor is studied.

Time-delay systems exist in many engineering fields such as transportation systems, communication systems, process engineering and, more recently, networked control systems. It usually results in unsatisfactory performance and is frequently a source of instability, so the control of time-delay systems is practically important. In this paper, a design of the state predictive model following control system (PMFCS) with time-delay is discussed. The bounded property of the internal states for the control is given, and the utility of this control design is guaranteed. Finally, examples are given to illustrate the effectiveness of the proposed method, and state predictive control techniques are applied to congestion control synthesis problems for a TCP/AQM network.

It is shown that the asymptotic stability of positive 2D linear systems with delays is independent of the number and values of the delays and it depends only on the sum of the system matrices, and that the checking of the asymptotic stability of positive 2D linear systems with delays can be reduced to testing that of the corresponding positive 1D systems without delays. The effectiveness of the proposed approaches is demonstrated on numerical examples.

In the paper the problem of practical stability of linear positive discrete-time systems of fractional order is addressed. New simple necessary and sufficient conditions for practical stability and for practical stability independent of the length of practical implementation are established. It is shown that practical stability of the system is equivalent to asymptotic stability of the corresponding standard positive discrete-time systems of the same order. The discussion is illustrated with numerical examples.

A modification of digital controller algorithms, based on the introduction of a virtual reference value, which never exceeds active constraints in the actuator output is presented and investigated for some algorithms used in single-loop control systems. This idea, derived from virtual modification of a control error, can be used in digital control systems subjected to both magnitude and rate constraints. The modification is introduced in the form of on-line adaptation to the control task. Hence the design of optimal (in a specified sense) digital controller parameters can be separated from actuator constraints. The adaptation of the control algorithm (to actuator constraints) is performed by the transformation of the control error and is equivalent to the introduction of a new, virtual reference value for the control system. An application of this approach is presented through examples of three digital control algorithms: the PID algorithm, the dead-beat controller and the state space controller. In all cases, clear advantages of transients are observed, which yields some general conclusions to the problem of processing actuator constraints in control.

The paper presents a novel description of the interplay between the windup phenomenon and directional change in controls for multivariable systems (including plants with an uneven number of inputs and outputs), usually omitted in the literature. The paper also proposes a new classification of anti-windup compensators with respect to the method of generating the constrained control signal.

Many applications of wireless sensor networks (WSN) require information about the geographical location of each sensor node. Self-organization and localization capabilities are one of the most important requirements in sensor networks. This paper provides an overview of centralized distance-based algorithms for estimating the positions of nodes in a sensor network. We discuss and compare three approaches: semidefinite programming, simulated annealing and two-phase stochastic optimization—a hybrid scheme that we have proposed. We analyze the properties of all listed methods and report the results of numerical tests. Particular attention is paid to our technique—the two-phase method—that uses a combination of trilateration, and stochastic optimization for performing sensor localization. We describe its performance in the case of centralized and distributed implementations.

The paper presents an improved method for 1-24 hours load forecasting in the power system, integrating and combining different neural forecasting results by an ensemble system. We will integrate the results of partial predictions made by three solutions, out of which one relies on a multilayer perceptron and two others on self-organizing networks of the competitive type. As the expert system we will apply different integration methods: simple averaging, SVD based weighted averaging, principal component analysis and blind source separation. The results of numerical experiments, concerning forecasting the hourly load for the next 24 hours of the Polish power system, will be presented and discussed. We will compare the performance of different ensemble methods on the basis of the mean absolute percentage error, mean squared error and maximum percentage error. They show a significant improvement of the proposed ensemble method in comparison to the individual results of prediction. The comparison of our work with the results of other papers for the same data proves the superiority of our approach.

The main area which Formal Safety Assessment (FSA) methodology was created for is maritime safety. Its model presents quantitative risk estimation and takes detailed information about accident characteristics into account. Nowadays, it is broadly used in shipping navigation around the world. It has already been shown that FSA can be widely used for the assessment of pilotage safety. On the basis of analysis and conclusion on the FSA approach, this paper attempts to show that the adaptation of this method to another area—risk evaluating in operating conditions of buildings—is possible and effective. It aims at building a mathematical model based on fuzzy logic risk assessment with different habitat factors included. The adopted approach lets us describe various situations and conditions that occur in creating and exploiting of buildings, allowing for automatic control of the risk connected to them.

The paper investigates the possibility of decomposing vibration signals into deterministic and nondeterministic parts, based on the Wold theorem. A short description of the theory of adaptive filters is presented. When an adaptive filter uses the delayed version of the input signal as the reference signal, it is possible to divide the signal into a deterministic (gear and shaft related) part and a nondeterministic (noise and rolling bearings) part. The idea of the self-adaptive filter (in the literature referred to as SANC or ALE) is presented and its most important features are discussed. The flowchart of the Matlab-based SANC algorithm is also presented. In practice, bearing fault signals are in fact nondeterministic components, due to a little jitter in their fundamental period. This phenomenon is illustrated using a simple example. The paper proposes a simulation of a signal containing deterministic and nondeterministic components. The self-adaptive filter is then applied—first to the simulated data. Next, the filter is applied to a real vibration signal from a wind turbine with an outer race fault. The necessity of resampling the real signal is discussed. The signal from an actual source has a more complex structure and contains a significant noise component, which requires additional demodulation of the decomposed signal. For both types of signals the proposed SANC filter shows a very good ability to decompose the signal.

The paper considers the forecasting of the Warsaw Stock Exchange price index WIG20 by applying a state space wavelet network model of the index price. The approach can be applied to the development of tools for predicting changes of other economic indicators, especially stock exchange indices. The paper presents a general state space wavelet network model and the underlying principles. The model is applied to produce one session ahead and five sessions ahead adaptive predictors of the WIG20 index prices. The predictors are validated based on real data records to produce promising results. The state space wavelet network model may also be used as a forecasting tool for a wide range of economic and non-economic indicators, such as goods and row materials prices, electricity/fuel consumption or currency exchange rates.

In the present study the notion of watershed contour dynamics, defined within the framework of mathematical morphology, is examined. It is shown that the dynamics are a direct measure of the "sharpness" of transition between neighboring watershed basins. The expressions for the expected value and the statistical error of the estimation of contour dynamics are derived in the presence of noise, based on extreme value theory. The sensitivity of contour dynamics to noise is studied. A statistical approach to the notion of contour dynamics is developed and a definition of statistical dynamics is proposed.