Showing papers in "International Journal of Systems Science in 2002"
TL;DR: A review and categorization of electric load forecasting techniques is presented, dividing them into nine categories: multiple regression, exponential smoothing, iterative reweighted least-squares, adaptive load forecasting, stochastic time series, ARMAX models based on genetic algorithms, fuzzy logic, neural networks, and expert systems.
Abstract: A review and categorization of electric load forecasting techniques is presented. A wide range of methodologies and models for forecasting are given in the literature. These techniques are classified here into nine categories: (1) multiple regression, (2) exponential smoothing, (3) iterative reweighted least-squares, (4) adaptive load forecasting, (5) stochastic time series, (6) ARMAX models based on genetic algorithms, (7) fuzzy logic, (8) neural networks and (9) expert systems. The methodology for each category is briefly described, the advantages and disadvantages discussed, and the pertinent literature reviewed. Conclusions and comments are made on future research directions.
670 citations
TL;DR: A modified combined wavelet transform technique that has been developed to analyse multilead electrocardiogram signals for cardiac disease diagnostics and two alternate diagnostic criteria have been used to check the diagnostic authenticity of the test results.
Abstract: This paper deals with a modified combined wavelet transform technique that has been developed to analyse multilead electrocardiogram signals for cardiac disease diagnostics. Two wavelets have been used, i.e. a quadratic spline wavelet (QSWT) for QRS detection and the Daubechies six coefficient (DU6) wavelet for P and T detection. After detecting the fundamental electrocardiogram waves, the desired electrocardiogram parameters for disease diagnostics are extracted. The software has been validated by extensive testing using the CSE DS-3 database and the MIT/BIH database. A procedure has been evolved using electrocardiogram parameters with a point scoring system for diagnosis of cardiac diseases, namely tachycardia, bradycardia left ventricular hypertrophy, and right ventricular hypertrophy. As the diagnostic results are not yet disclosed by the CSE group, two alternate diagnostic criteria have been used to check the diagnostic authenticity of the test results. The consistency and reliability of the identifi...
169 citations
TL;DR: The mechanism by which disturbances can be transmitted along the supply chain causing disruption and incurring costs to other supply chain echelons is elucidated and a heuristic feedback policy designed adaptively to tune the individual system designs in response to such disturbances is presented.
Abstract: The paper deals with the modelling and control of aggregated production-inventory systems as described by differential equations. Hitherto, research in the area has been characterized by the approximation of production delays by first-order lags rather than more realistic pure delays. We demonstrate the substantial qualitative differences between these two approaches and thus generate the motivation for the rest of the paper, which tackles pure delay systems. The application of some relatively new design methodologies for delay systems yields four design choices that are tested for their performance over a range of criteria including stability robustness. The investigation is then extended to the model of a supply chain comprising many such productioninventory systems. The mechanism by which disturbances can be transmitted along the supply chain causing disruption and incurring costs to other supply chain echelons is elucidated. A heuristic feedback policy designed adaptively to tune the individual system...
88 citations
TL;DR: In this article, the problem of H X filtering for continuous-time linear systems with Markovian jump was investigated and necessary and sufficient conditions for designing a Markovians jump linear filter that ensures a prescribed bound on the L 2 -induced gain from the noise signals to the estimation error was developed.
Abstract: The problem of H X filtering for continuous-time linear systems with Markovian jump is investigated. It was assumed that the jumping parameter was available. This paper develops necessary and sufficient conditions for designing a Markovian jump linear filter that ensures a prescribed bound on the L 2 -induced gain from the noise signals to the estimation error. The main result is tailored via linear matrix inequalities.
83 citations
TL;DR: A novel particle filtering based approach to fault detection in non- linear stochastic systems is developed here and the effectiveness of this new method is demonstrated through Monte Carlo simulations and the detection performance is compared with that using the extended Kalman filter on a non-linear system.
Abstract: Much of the development in model-based fault detection techniques for dynamic stochastic systems has relied on the system model being linear and the noise and disturbances being Gaussian. Linearized approximations have been used in the non-linear systems case. However, linearization techniques, being approximate, tend to suffer from poor detection or high false alarm rates. A novel particle filtering based approach to fault detection in non-linear stochastic systems is developed here. One of the appealing advantages of the new approach is that the complete probability distribution information of the state estimates from particle filter is utilized for fault detection, whereas, only the mean and covariance of an approximate Gaussian distribution are used in a coventional extended Kalman filter-based approach. Another advantage of the new approach is its applicability to general non-linear system with non-Gaussian noise and disturbances. The effectiveness of this new method is demonstrated through Monte Car...
83 citations
TL;DR: By combining the parameterizations of the observer eigenvectors and an established condition for disturbance decoupling in descriptor linear systems, the effect of the disturbance to the residual signal is decoupled.
Abstract: A new parametric approach for robust fault detection in descriptor linear multivariable systems with unknown disturbances is proposed. The residual is generated using a fullorder generalized state observer. Based on a recently proposed parametric eigenstructure assignment approach, parameterizations of the observer gain and the eigenvectors of the observer system are presented. By combining the parameterizations of the observer eigenvectors and an established condition for disturbance decoupling in descriptor linear systems, the effect of the disturbance to the residual signal is decoupled. A simple algorithm is presented. An example shows the effect of the proposed approach.
74 citations
TL;DR: In this article, fault diagnosis for a class of linear systems based on adaptive observer is investigated, and two adaptive observers are designed for fault identification.
Abstract: In this article, fault diagnosis for a class of linear systems based on adaptive observer is investigated. Linear systems without model uncertainty are first considered, and two adaptive observers are designed for fault identification. The first one uses optimal design for minimizing the estimation error. The second one can achieve asymptotic fault estimation. The general situation where the system is subjected to either model errors or external disturbance is then discussed. Robust adaptive control techniques are applied to guarantee the convergence to a bounded set. Simulation of sensor fault diagnosis for an induction motor is presented to verify the effectiveness of the proposed method.
52 citations
TL;DR: A simple linear tracking-differentiator is proposed and the convergence proved for any differentiable signal with random perturbation to be tracked, enabling a relatively simple globally convergent online estimator of the frequency of a sinusoidal signal under small random perturgation.
Abstract: A simple linear tracking-differentiator is proposed and the convergence proved for any differentiable signal with random perturbation to be tracked This enables us to design a relatively simple globally convergent online estimator of the frequency of a sinusoidal signal under small random perturbation The polynomial convergent rate is obtained
52 citations
TL;DR: Under the existence of bounded deterministic disturbances, the adaptive stabilizer is constructed by the concept of high-gain non-linear output feedback and the estimation mechanism of the unknown parameters to guarantee the global asymptotic stability and convergence of the system state to zero.
Abstract: The paper is concerned with adaptive stabilization of a reaction-diffusion system governed by the Kuramoto-Sivashinsky equation (a non-linear partial differential equation). Under the existence of bounded deterministic disturbances, the adaptive stabilizer is constructed by the concept of high-gain non-linear output feedback and the estimation mechanism of the unknown parameters. In the control system, the global asymptotic stability and convergence of the system state to zero will be guaranteed. The problem of set point regulation is also considered.
49 citations
TL;DR: An operational matrix of integration P based on sine and cosine wavelets is presented and the matrix P is used to reduce a variational problem to the solution of algebraic equations.
Abstract: An operational matrix of integration P based on sine and cosine wavelets is presented. A general procedure for forming this matrix is given. The matrix P is then used to reduce a variational problem to the solution of algebraic equations. An illustrative example is included to demonstrate the validity and applicability of the technique.
48 citations
TL;DR: A varying deterioration rate, time-value of money and the condition of permissible delay in payments used in conjunction with the EOQ model are the focus of discussion.
Abstract: A varying deterioration rate, time-value of money and the condition of permissible delay in payments used in conjunction with the EOQ model are the focus of discussion. The replenishment number and fraction of each cycle in which there is no shortage are both determined to minimize the present value of inventory cost over a finite planning horizon. Two special cases and numerical examples are presented to illustrate the model.
TL;DR: Two new algorithms are proposed that combine the orthogonal least squares algorithm with support vector machines to give a parsimonious model with good prediction accuracy in the low signal-to-noise ratio case.
Abstract: Generalization properties of support vector machines, orthogonal least squares and zero-order regularized orthogonal least squares algorithms are studied using simulation. For high signal-to-noise ratios (40 dB), mixed results are obtained, but for a low signal-to-noise ratio, the prediction performance of support vector machines is better than the orthogonal least squares algorithm in the examples considered. However, the latter can usually give a parsimonious model with very fast training and testing time. Two new algorithms are therefore proposed that combine the orthogonal least squares algorithm with support vector machines to give a parsimonious model with good prediction accuracy in the low signal-to-noise ratio case.
TL;DR: New delay-dependent stability criteria are proposed by simplifying the derived LMIs and show that the results obtained by these new criteria significantly improve the estimate of stability limit over the existing results in the literature.
Abstract: The asymptotic stability problem for a class of linear systems with time-varying delays is studied using a generalized discretized Lyapunov functional approach. The kernel of the functional, which is a function of two variables, is chosen as piecewise linear. The conditions of the Lyapunov functional and its derivative are written in terms of linear matrix inequalities (LMIs). New delay-dependent stability criteria are proposed by simplifying the derived LMIs. Numerical examples show that the results obtained by these new criteria significantly improve the estimate of stability limit over the existing results in the literature.
TL;DR: An algorithm of finding the optimal solution to the lead time and set-up cost reductions problem on the modified lot size reorder point inventory model in which the production process is imperfect is developed.
Abstract: This paper deals with the lead time and set-up cost reductions problem on the modified lot size reorder point inventory model in which the production process is imperfect. We consider that the lead time can be shortened at an extra crashing cost, which depends on the length of lead time to be reduced and the ordering lot size. The option of investing in reducing set-up cost is also included. Two commonly used investment cost functional forms, logarithmic and power, are employed for set-up cost reduction. We assume that the stochastic demand during lead time follows a Normal distribution. The objective is simultaneously to optimize the lot size, reorder point, set-up cost and lead time. An algorithm of finding the optimal solution is developed, and two numerical examples are given to illustrate the results.
TL;DR: An EOQ inventory model that is depleted not only by time-varying demand but also by Weibull distribution deterioration, in which shortages are allowed and partially backordered and the optimal procedure was independent of the form of the demand rate.
Abstract: The paper presents an EOQ inventory model that is depleted not only by time-varying demand but also by Weibull distribution deterioration, in which shortages are allowed and partially backordered. The backlogging rate is variable and dependent on the waiting time for the next replenishment. Further, the optimal procedure was independent of the form of the demand rate. It is then illustrated with the help of four numerical examples. The sensitivity analysis is also studied.
TL;DR: Investigation of SGX-DT Nikkei 225 futures prices during the non-cash-trading (NCT) period using an artificial neural network model indicates that there is valuable information involved in futures prices that can be used to forecast the opening cash market price index.
Abstract: The study investigates the information content of SGX-DT Nikkei 225 futures prices during the non-cash-trading (NCT) period using an artificial neural network model. The cash market closing index, the futures prices from a period in the same trading day and on the following trading day are utilized to determine the appropriate input nodes of a back propagation neural network model in forecasting the opening cash price index. Sensitivity analysis is first employed to address and solve the issue of finding the appropriate network topology. Extensive studies are then performed on the robustness of the constructed network by using different training and testing sample sizes. The effectiveness of the method is demonstrated on data from a 6-month historical record (1998-99). Analytic results demonstrate that the proposed neural network model outperforms a neural network model with the previous day's closing index as the input node and the random walk model forecasts. It, therefore, indicates that there is valua...
TL;DR: The aim was to design a state feedback controller such that the plant remained stable for all admissible uncertainties as well as actuator faults among a prespecified subset of actuators or sector-type actuator non-linearity, independently of the delay time.
Abstract: This paper deals with the problem of robust reliable control for a class of uncertain neutral delay systems. The aim was to design a state feedback controller such that the plant remained stable fo...
TL;DR: A theorem and corollary was obtained in which the boundedness and differentiability of the signal functions in some papers are deleted and some sufficient conditions for the existence of global asymtotic stable equilibrium of the networks are better than the sufficient conditions in the quoted literature.
Abstract: Bidirectional associative memory (BAM) models are two-layer heteroassociative networks. This paper is devoted to the investigation of the global asymptotic stability for BAM neural networks with S-type distributed signal transmission delays along the axon of a neuron. A theorem and corollary was obtained in which the boundedness and differentiability of the signal functions in some papers are deleted. Some sufficient conditions for the existence of global asymtotic stable equilibrium of the networks in this paper are better than the sufficient conditions in the quoted literature.
TL;DR: The emphasis is put on an emerging methodology, relevant for intelligent product-support systems, to combine information about disparate evidences systematically based on Bayesian Belief Networks to show the link between basic information and the confidence one can have in a system.
Abstract: The objective of the research has been to investigate the possibility to transfer the requirements of a software safety standard into Bayesian belief networks (BBNs). The BBN methodology has mainly ...
TL;DR: By introducing the relationships between B-Spline neural networks and Mamdani (satisfying certain assumptions) and Takagi-Kang-Sugeno fuzzy models, training algorithms developed initially for neural networks can be adapted to fuzzy systems.
Abstract: Complete supervised training algorithms for B-Spline neural networks and fuzzy rule-based systems are discussed. By introducing the relationships between B-Spline neural networks and Mamdani (satisfying certain assumptions) and Takagi-Kang-Sugeno fuzzy models, training algorithms developed initially for neural networks can be adapted to fuzzy systems. The standard training criterion is reformulated, by separating its linear and nonlinear parameters. By employing this reformulated criterion with the Levenberg-Marquardt algorithm, a new training method, offering a fast rate of convergence is obtained. It is also shown that the standard Error-Back Propagation algorithm, the most common training method for this class of systems, exhibits a very poor and unreliable performance.
TL;DR: A novel approach to the identification of Coupled Map Lattice models of linear and nonlinear infinite-dimensional systems from discrete observations by exploiting the regularity of the CML model so that only a finite number of spatial measurements are required.
Abstract: This paper introduces a novel approach to the identification of Coupled Map Lattice (CML) models of linear and nonlinear infinite-dimensional systems from discrete observations. The method exploits the regularity of the CML model so that only a finite number of spatial measurements are required. The measurement system associated with a CML is discussed and some necessary conditions for the input/output equations to form a CML are presented. Numerical simulations illustrate the applicability of the proposed method.
TL;DR: Several ways in which new technologies can assist in the design and delivery of warnings are described, and a warning presentation can be modified to fit conditions and persons.
Abstract: This paper describes several ways in which new technologies can assist in the design and delivery of warnings. There are four discussion points: (1) current product information can be delivered via the Internet; (2) computer software and hardware are available to assist in the design, construction, and production of visual and auditory warnings; (3) various detection devices can be used to recognize instances in which warnings might be delivered; and (4) a warning presentation can be modified to fit conditions and persons. Implications, example applications and future prospects of these points are described.
TL;DR: Methods and procedures to predict software failure rates from a user perspective in system test phases and to reverse-engineer in order to estimate software release time for given availability targets are presented.
Abstract: It is essential to predict customer-perceived software availability during software development and determine when to release the software to maintain a balance among time-to-market, development cost and software quality. This paper presents methods and procedures to predict software failure rates from a user perspective in system test phases and to reverse-engineer in order to estimate software release time for given availability targets. Software reliability analysis is conducted based on non-homogenous Poisson process models. Software system test data of current release are used to estimate the number of residual faults by the end of system tests and data of previous releases or similar products (including system test data, post-system test data and field failure data) provide a means to predict a user-perceived average failure rate of a fault. Software system availability can be predicted from these estimates. Both execution and calendar times are considered. A software resource utilization model is d...
TL;DR: The adaptive stabilization of the generalized Hamiltonian control systems with dissipation, which has a linearly parameterized Hamiltonian function with respect to unknown constants, is considered here and the designed adaptive control law is very effective.
Abstract: The adaptive stabilization of the generalized Hamiltonian control systems with dissipation, which has a linearly parameterized Hamiltonian function with respect to unknown constants, is considered here. The theoretic result is then applied to power system that cannot be treated by backstepping introduced by Kokotovic et al. Simulations show that the designed adaptive control law is very effective.
TL;DR: The aim is to explore the concept of regional asymptotic observation for a class of parabolic-distributed parameter systems and considers the use of regional observers in regional closed-loop control systems.
Abstract: The aim is to explore the concept of regional asymptotic observation for a class of parabolic-distributed parameter systems. The approach derives from Luenberger observer type, as introduced by Gressang and Lamont (1975). We show the links with regional detectability and strategic sensors. We also show that there is a dynamical system that is not observer in the usual sense, but that may be regional observer. Furthermore, we consider the use of regional observers in regional closed-loop control systems.
TL;DR: The notions of regional remediability and regional efficient actuators are introduced and the set of regionally remediable disturbances is determined and the optimal control is given which ensures its regional compensation.
Abstract: In this paper, we introduce and characterize the notions of regional remediability and regional efficient actuators. We study their relationship with regional controllability and regional strategic actuators. We also determine the set of regionally remediable disturbances and, for each disturbance, we give the optimal control which ensures its regional compensation.
TL;DR: The process of conceptual modelling using the Inferential Modelling Technique as a basis for ontology construction is presented and the tool and processes are applied to build an expert system in the domain of monitoring of a petroleum-production facility.
Abstract: This paper presents the processes of knowledge acquisition and ontology development for structuring the knowledge base of an expert system Ontological engineering is a process that facilitates construction of the knowledge base of an intelligent system Ontology is the study of the organization and classification of knowledge Ontological engineering in artificial intelligence has the practical goal of constructing frameworks for knowledge that allow computational systems to tackle knowledgeintensive problems and it supports knowledge sharing and reuse To illustrate the process of conceptual modelling using the Inferential Modelling Technique as a basis for ontology construction, the tool and processes are applied to build an expert system in the domain of monitoring of a petroleum-production facility
TL;DR: A dynamic model of hypercompetition is developed through the specification of expansion paths along the cost frontier through such concepts as innovations and access efficiency, externalities and increasing returns to scale and intense rivalry between firms which differ in their dynamic efficiency.
Abstract: A dynamic model of hypercompetition is developed through the specification of expansion paths along the cost frontier. The divergence of hypercompetition from the traditional notion of a statically competitive market is emphasized here through such concepts as innovations and access efficiency, externalities and increasing returns to scale and intense rivalry between firms which differ in their dynamic efficiency.
TL;DR: This paper considers robust performance analysis and H X controller design for a class of systems with time-varying and nonlinear uncertainties and shows that in some cases, the constraints can be eliminated through simplifications and the output feedback controller design methods can be provided in terms of LMIs.
Abstract: This paper considers robust performance analysis and H X controller design for a class of systems with time-varying and nonlinear uncertainties. These uncertainties are allowed to exist not only in the state, but also in the control input, measurement output, exogenous input and derivative of state. A new sufficient condition based on LMI is first provided to analyse the robust H X performance problem of the free systems. For the general case, it is shown that a solvability condition for the output feedback control problem can be reduced to that of a set of LMIs with algebraic constraints. Then it is shown that in some cases, the constraints can be eliminated through simplifications and the output feedback controller design methods can be provided in terms of LMIs. In particular, two special cases of the systems with nonlinear uncertainties are discussed thoroughly and the design procedures of output feedback controllers are provided via typical LMIs. Furthermore, for a class of systems with both structur...
TL;DR: This paper focuses on the problem of a robust output-sliding control design for a class of nonlinear time-varying systems and application to a two-degree-of-freedom manipulator indicates that the proposed switching control law drives the system state trajectories onto the chosen sliding mode in finite time and the output tracking is guaranteed.
Abstract: Sliding mode control methods have been used widely because they provide robustness against parameter variations and disturbances. This paper focuses on the problem of a robust output-sliding control design for a class of nonlinear time-varying systems. Output signals are used for the switching function definition. The control law formulation is emphasized. Input and output linearization is used. Output tracking can be achieved against a class of time-varying parameter variations and external disturbances. An application to a two-degree-of-freedom manipulator indicates that the proposed switching control law drives the system state trajectories onto the chosen sliding mode in finite time and the output tracking is guaranteed.