The problem of constructing nonasymptotic estimates of the rate of convergence of robust identification algorithms is considered. Estimates are constructed for the class of one-dimensional algorithms that are valid at...
详细信息
The problem of constructing nonasymptotic estimates of the rate of convergence of robust identification algorithms is considered. Estimates are constructed for the class of one-dimensional algorithms that are valid at every step of the algorithm with arbitrary, preassigned probability. Examples of these types of estimates are presented.
Robot calibration techniques provide a practical approach to improve the accuracy of industrial robot manipulators. A problem associated with the calibrated results is that the inverse kinematic solution to the calibr...
详细信息
Robot calibration techniques provide a practical approach to improve the accuracy of industrial robot manipulators. A problem associated with the calibrated results is that the inverse kinematic solution to the calibrated kinematic model becomes difficult to resolve. This paper presents a method for solving the inverse kinematics problem of an S-model calibrated Puma 560 robot. It is a numerical iterative approach based on the closed-form inverse kinematic solution to the nominal Puma kinematic model. The reported method is accurate, efficient and suitable for real-time applications.
A recursive LU decomposition scheme extends the capabilities of nonrecursive algorithms for the reduction of computation time when geometrical modifications are made to a precomputed scatterer. Significant savings are...
详细信息
A recursive LU decomposition scheme extends the capabilities of nonrecursive algorithms for the reduction of computation time when geometrical modifications are made to a precomputed scatterer. Significant savings are achieved for cases of many different attachments, or when the initial scatterer is amenable to a particular efficient solution. (C) 1994 John Wiley & Sons, Inc.
In this paper, we present simple recursive algorithms for computing call and time congestion in the classical Engset model with M sources and N servers. The first recursion has the complexity of O(MN) and gives the bl...
详细信息
In this paper, we present simple recursive algorithms for computing call and time congestion in the classical Engset model with M sources and N servers. The first recursion has the complexity of O(MN) and gives the blocking probabilities for all intermediate values of M and N. The second recursion assumes a particular value of M and has the complexity of O(N). It gives the blocking probabilities for all intermediate values of N. Both recursions are similar to the well-known recurrence for computing the Erlang loss function.
A model for developmental systems consisting of elements subjected to operations grouped in a generating word was described in two previous Automatica articles. In this paper operating systems with multilevel and para...
详细信息
A model for developmental systems consisting of elements subjected to operations grouped in a generating word was described in two previous Automatica articles. In this paper operating systems with multilevel and parallel development are compared and illustrated by the maple leaf.
The problem of recursive robust identification of linear discrete-time dynamic stochastic systems, when the a priori disturbance statistics are incomplete, is discussed. Min-max robust identification algorithms of sto...
详细信息
The problem of recursive robust identification of linear discrete-time dynamic stochastic systems, when the a priori disturbance statistics are incomplete, is discussed. Min-max robust identification algorithms of stochastic gradient type are derived, making use of a priori data, such as the class of distributions to which the unknown disturbance distribution belongs. Making use of prior statistical information on the estimated parameters, the rate of estimates convergence at initial steps is improved. The convergence of the developed algorithms is established theoretically, using the martingale theory. The results of simulation demonstrating the robustness of the proposed algorithms are also included.
A new method for identification of nonlinear systems using the Hammerstein model is presented, This is developed along the lines of the basic Kalman filter and has an important property for on-line identification that...
详细信息
A new method for identification of nonlinear systems using the Hammerstein model is presented, This is developed along the lines of the basic Kalman filter and has an important property for on-line identification that parameters of the nonlinear static polynomial and those of the linear dynamic transfer function are estimated recursively and separately;thus, the number of coefficients to be estimated is minimal, and computational requirements are considerably reduced. This procedure is extended to nonlinear multi-input single-output (MISO) systems. Two recursive methods are derived. The first one consists of estimating parameters of an equivalent realization of the nonlinear MISO representation. The second recursive algorithm estimates recursively and separately parameters of each submodel of the system, using a new formulation of the input-output difference equation. Both procedures are based on the algorithm developed in the nonlinear single-input single-output (SISO) case. To illustrate the efficiency of these algorithms, numerical examples are provided.
A new on-line bias-compensating least-squares method is presented for the parameter estimation of linear, single-input single-output, discrete-time systems where the output measurement is corrupted by an additive colo...
详细信息
A new on-line bias-compensating least-squares method is presented for the parameter estimation of linear, single-input single-output, discrete-time systems where the output measurement is corrupted by an additive coloured noise. The principle of the bias-compensating method used here, is to compensate the bias of the least-squares estimate by introducing artificially a stable pre-filter on the system. To avoid the heuristic choice of the pre-filter encountered in some previous bias-compensating methods, the proposed method uses the filter provided by the recursive generalised least-squares algorithm. By using the roots of this filter, the bias of the conventional least-squares method may be estimated and then removed. Numerical examples are included to illustrate the superiority of the on-line implementation technique of the proposed method over the recursive generalised least-squares method.
This paper presents a new identification algorithm that is particular suitable for the parameter estimation of instationary processes. It estimates the rate of change of an instationary model along with the model para...
详细信息
This paper presents a new identification algorithm that is particular suitable for the parameter estimation of instationary processes. It estimates the rate of change of an instationary model along with the model parameters. This approach allows the prediction of future model parameters which results in a faster adaptation to instationary processes with a smaller prediction error. Based on a Bayesian probability concept the paper derives the structure of the identification algorithm which is then developed into a set of recursive update equations. A simulation example shows the advantages of the new algorithm over standard RLS estimation.
A second order recursive least squares algorithm is derived. It is shown that the algorithm encompasses both the RLS and the LMS algorithms as special cases. The computational complexity is the same as for the RLS alg...
详细信息
A second order recursive least squares algorithm is derived. It is shown that the algorithm encompasses both the RLS and the LMS algorithms as special cases. The computational complexity is the same as for the RLS algorithm, but requires some extra memory storage. The associated Ordinary Differential Equation (ODE) for the algorithm is proven to be globally exponentially stable. Further, it is demonstrated that the proposed algorithm has a higher ability to track time-varying signals than has the RLS-algorithm. The proposed algorithm especially handles those situations well where there is a simultaneous system change and decrease of signal power.
暂无评论