Dariusz Ucinski | University of Zielona Gora (original) (raw)
Uploads
Papers by Dariusz Ucinski
1997 European Control Conference (ECC), 1997
A computational procedure is presented for designing moving sensor trajectories in parameter iden... more A computational procedure is presented for designing moving sensor trajectories in parameter identification of two-dimensional distributed systems. Two widely used minimax criteria, namely those of MV-optimality and E-optimality, are considered here as the measures of the estimation accuracy. The approach converts the problem to an optimal control one in which both the control forces of the sensors and the initial sensor positions are optimized. A gradient algorithm is developed based on the negative formulation of the Potryagin Maximum Principle which handles various constraints imposed on the sensors' motions. A summary of numerical experiments with the techniques proposed is given.
IFAC Proceedings Volumes, 1999
This paper deals with the optimal parameter estimation of a distributed-parameter process, for wh... more This paper deals with the optimal parameter estimation of a distributed-parameter process, for which the observation subject to additive noise is realized by poinrwise sensors which are allowed to move in the spatial domain and are driven by some control inputs. The global design criterion is the expectation of a general local design criterion defined on the Fisher information matrix, given a priori distribution of the parameters to be identified. A stochastic-gradient algorithm is used for its Inaximization, which makes it possible to reduce significantly the required computational burden. A technique to tackle minimax-optinlality criteria is also indicated.
IFAC Proceedings Volumes, 1994
This paper deals with a computer diagnostic system for a power plant simulator. The system is des... more This paper deals with a computer diagnostic system for a power plant simulator. The system is designed to help the operator in fault detection and isolation during operation of the power plant. A two-part knowledge base was created to increase the efficiency and flexibility of knowledge-based diagnostic system. The base consists of heuristic knowledge (set of rules and principles of system behavior) and analytical knowledge (set of mathematical models , Kalman filter algorithms and tests of random sequences). The design methodology is a hierarchical knowledge structure with compiled knowledge at higher levels of abstraction and analytical redundancy at lower ones. Such an integrated approach reduces the computational complexity associated with functionally-redundant schemes and increases the effectiveness of the knowledge-based approach .
Proceedings of the First Workshop on Robot Motion and Control. RoMoCo'99 (Cat. No.99EX353), 1999
ABSTRACT We develop an effective numerical procedure for optimizing trajectories of moving sensor... more ABSTRACT We develop an effective numerical procedure for optimizing trajectories of moving sensors which take measurements in a given spatial in order to find parameter estimates of a given distributed system. The global design criterion is the Frobenius condition number for the Hessian of the least-squares criterion. The approach converts the problem to an optimal control one in which both the control forces of the sensors and the initial sensor positions are optimized. Its solution is obtained by the use of a gradient algorithm which handles various constraints imposed on sensor motions. Among other things, the method copes efficiently with problems involving state constraints induced by collision-avoidance conditions or admissible distances between the sensors. A simple test problem is presented to illustrate the presented ideas
Discrete Structural Optimization, 1994
This paper deals with the sensors allocation problem for the state estimation and parameter ident... more This paper deals with the sensors allocation problem for the state estimation and parameter identification in non-linear stochastic distributed parameter systems described by parabolic partial differential equations. In order to pose the sensors location problem, a mathematical model of distributed systems is briefly considered. Then, a concise general review of several methods and approaches considered in the current literature for the state and parameter estimation is discussed. Some typical illustrative numerical example is presented in the final part of this survey type paper.
jiip, 2001
Some fundamental results of the modern theory of optimum experimental design are extended here to... more Some fundamental results of the modern theory of optimum experimental design are extended here to address the problem of determining the optimal measurement scheduling, encountered while estimating unknown parameters in mathematical models described by partial differential equations from observations of the underlying physical phenomenon being modelled. Special emphasis is put on measurements realized by optimal motion of spatially-movable sensors for which we generalize the approach advanced by Rafaj lowicz in his seminal paper [16] to the case of minimizing a general performance index defined on the Fisher information matrix related to the parameters to be identified. Since only the measurability of the resulting trajectories can be guaranteed, we also show how to ease this inconvenience by introducing a suitable parametrization of the set of admissible solutions. In the latter case, we also detail how to adapt standard sequential numerical algorithms of optimum experimental design so that they could be employed for computation of trajectories in particular situations.
Although we witness an extremely fast development of methods of Fault Detection and Isolation (FD... more Although we witness an extremely fast development of methods of Fault Detection and Isolation (FDI) for dynamical systems in the last decade (1), (2), (3), (4), there is a grave lack of the corresponding effective techniques dedicated to distributed parameter systems (DPSs). Furthermore, within the framework of FDI systems, the optimization of data acquisition process which increases the reliability of the diagnosis is most often neglected and the contributions are very scarce. Within the framework of diagnostics, the crucial difficulty is the definition of a suitable criterion describing the relations between the quality of the system diagnosis and the observation strategy. One of the most prospective approaches in this context is to make use of techniques originating in parameter estimation, see the works (5) and (6) where the appropriate performance measure, the so-called Ds-optimality criterion, defined on the Fisher Information Matrix (FIM) associated with the unknown system parameters, was used as a measure of the ‘goodness’ of experimental conditions. Nevertheless, more efforts are needed in order to adapt this approach in the context of modern measurement systems encountered in applications.
International Journal of Systems Science, 1990
... Good surveys on this subject can be found in Polis and Goodson (1976), Rajbman (1976), Kubrus... more ... Good surveys on this subject can be found in Polis and Goodson (1976), Rajbman (1976), Kubrusly (1977), Chavent (1987) and Kunisch (1988). ... For the node with coordinates (mAz,,nAz,) the six triangles {TA)z_, are shown in Fig. 2. Direct calculations prove that ...
Contributions to Statistics, 2013
Proceedings of the First Workshop on Robot Motion and Control. RoMoCo'99 (Cat. No.99EX353), 1999
ABSTRACT We develop an effective numerical procedure for optimizing trajectories of moving sensor... more ABSTRACT We develop an effective numerical procedure for optimizing trajectories of moving sensors which take measurements in a given spatial in order to find parameter estimates of a given distributed system. The global design criterion is the Frobenius condition number for the Hessian of the least-squares criterion. The approach converts the problem to an optimal control one in which both the control forces of the sensors and the initial sensor positions are optimized. Its solution is obtained by the use of a gradient algorithm which handles various constraints imposed on sensor motions. Among other things, the method copes efficiently with problems involving state constraints induced by collision-avoidance conditions or admissible distances between the sensors. A simple test problem is presented to illustrate the presented ideas
1997 European Control Conference (ECC), 1997
A computational procedure is presented for designing moving sensor trajectories in parameter iden... more A computational procedure is presented for designing moving sensor trajectories in parameter identification of two-dimensional distributed systems. Two widely used minimax criteria, namely those of MV-optimality and E-optimality, are considered here as the measures of the estimation accuracy. The approach converts the problem to an optimal control one in which both the control forces of the sensors and the initial sensor positions are optimized. A gradient algorithm is developed based on the negative formulation of the Potryagin Maximum Principle which handles various constraints imposed on the sensors' motions. A summary of numerical experiments with the techniques proposed is given.
IFAC Proceedings Volumes, 1999
This paper deals with the optimal parameter estimation of a distributed-parameter process, for wh... more This paper deals with the optimal parameter estimation of a distributed-parameter process, for which the observation subject to additive noise is realized by poinrwise sensors which are allowed to move in the spatial domain and are driven by some control inputs. The global design criterion is the expectation of a general local design criterion defined on the Fisher information matrix, given a priori distribution of the parameters to be identified. A stochastic-gradient algorithm is used for its Inaximization, which makes it possible to reduce significantly the required computational burden. A technique to tackle minimax-optinlality criteria is also indicated.
IFAC Proceedings Volumes, 1994
This paper deals with a computer diagnostic system for a power plant simulator. The system is des... more This paper deals with a computer diagnostic system for a power plant simulator. The system is designed to help the operator in fault detection and isolation during operation of the power plant. A two-part knowledge base was created to increase the efficiency and flexibility of knowledge-based diagnostic system. The base consists of heuristic knowledge (set of rules and principles of system behavior) and analytical knowledge (set of mathematical models , Kalman filter algorithms and tests of random sequences). The design methodology is a hierarchical knowledge structure with compiled knowledge at higher levels of abstraction and analytical redundancy at lower ones. Such an integrated approach reduces the computational complexity associated with functionally-redundant schemes and increases the effectiveness of the knowledge-based approach .
Proceedings of the First Workshop on Robot Motion and Control. RoMoCo'99 (Cat. No.99EX353), 1999
ABSTRACT We develop an effective numerical procedure for optimizing trajectories of moving sensor... more ABSTRACT We develop an effective numerical procedure for optimizing trajectories of moving sensors which take measurements in a given spatial in order to find parameter estimates of a given distributed system. The global design criterion is the Frobenius condition number for the Hessian of the least-squares criterion. The approach converts the problem to an optimal control one in which both the control forces of the sensors and the initial sensor positions are optimized. Its solution is obtained by the use of a gradient algorithm which handles various constraints imposed on sensor motions. Among other things, the method copes efficiently with problems involving state constraints induced by collision-avoidance conditions or admissible distances between the sensors. A simple test problem is presented to illustrate the presented ideas
Discrete Structural Optimization, 1994
This paper deals with the sensors allocation problem for the state estimation and parameter ident... more This paper deals with the sensors allocation problem for the state estimation and parameter identification in non-linear stochastic distributed parameter systems described by parabolic partial differential equations. In order to pose the sensors location problem, a mathematical model of distributed systems is briefly considered. Then, a concise general review of several methods and approaches considered in the current literature for the state and parameter estimation is discussed. Some typical illustrative numerical example is presented in the final part of this survey type paper.
jiip, 2001
Some fundamental results of the modern theory of optimum experimental design are extended here to... more Some fundamental results of the modern theory of optimum experimental design are extended here to address the problem of determining the optimal measurement scheduling, encountered while estimating unknown parameters in mathematical models described by partial differential equations from observations of the underlying physical phenomenon being modelled. Special emphasis is put on measurements realized by optimal motion of spatially-movable sensors for which we generalize the approach advanced by Rafaj lowicz in his seminal paper [16] to the case of minimizing a general performance index defined on the Fisher information matrix related to the parameters to be identified. Since only the measurability of the resulting trajectories can be guaranteed, we also show how to ease this inconvenience by introducing a suitable parametrization of the set of admissible solutions. In the latter case, we also detail how to adapt standard sequential numerical algorithms of optimum experimental design so that they could be employed for computation of trajectories in particular situations.
Although we witness an extremely fast development of methods of Fault Detection and Isolation (FD... more Although we witness an extremely fast development of methods of Fault Detection and Isolation (FDI) for dynamical systems in the last decade (1), (2), (3), (4), there is a grave lack of the corresponding effective techniques dedicated to distributed parameter systems (DPSs). Furthermore, within the framework of FDI systems, the optimization of data acquisition process which increases the reliability of the diagnosis is most often neglected and the contributions are very scarce. Within the framework of diagnostics, the crucial difficulty is the definition of a suitable criterion describing the relations between the quality of the system diagnosis and the observation strategy. One of the most prospective approaches in this context is to make use of techniques originating in parameter estimation, see the works (5) and (6) where the appropriate performance measure, the so-called Ds-optimality criterion, defined on the Fisher Information Matrix (FIM) associated with the unknown system parameters, was used as a measure of the ‘goodness’ of experimental conditions. Nevertheless, more efforts are needed in order to adapt this approach in the context of modern measurement systems encountered in applications.
International Journal of Systems Science, 1990
... Good surveys on this subject can be found in Polis and Goodson (1976), Rajbman (1976), Kubrus... more ... Good surveys on this subject can be found in Polis and Goodson (1976), Rajbman (1976), Kubrusly (1977), Chavent (1987) and Kunisch (1988). ... For the node with coordinates (mAz,,nAz,) the six triangles {TA)z_, are shown in Fig. 2. Direct calculations prove that ...
Contributions to Statistics, 2013
Proceedings of the First Workshop on Robot Motion and Control. RoMoCo'99 (Cat. No.99EX353), 1999
ABSTRACT We develop an effective numerical procedure for optimizing trajectories of moving sensor... more ABSTRACT We develop an effective numerical procedure for optimizing trajectories of moving sensors which take measurements in a given spatial in order to find parameter estimates of a given distributed system. The global design criterion is the Frobenius condition number for the Hessian of the least-squares criterion. The approach converts the problem to an optimal control one in which both the control forces of the sensors and the initial sensor positions are optimized. Its solution is obtained by the use of a gradient algorithm which handles various constraints imposed on sensor motions. Among other things, the method copes efficiently with problems involving state constraints induced by collision-avoidance conditions or admissible distances between the sensors. A simple test problem is presented to illustrate the presented ideas