Stochastical real time finite state machine LPC for planar manipulator control system model estimation

This paper presents a new stochastical real-time LPC (Last Principal Component) algorithm to estimate single-input-single-output (SISO) and multiple-input-multiple-output (MIMO) varying time models from input output data clusters of non stationary black boxes. Each of data clusters is on a time window. An application to estimate the control system model of a planar manipulator is developed. In fact many mathematical models of physical systems are non stationary such as industrial manipulator model. A real time estimation algorithm via stochastical LPC algorithm and an appraiser called "finite state machine" is then described. For every data cluster the finite state machine updates the parameters of a Gaussian varying time model via an optimality design criterion that maximises the Likelihood function. The estimated steady-state parameters are constant values. By applying to two links planar manipulator, numerical tests of simulation in Matlab 6.5 demonstrate the effectiveness of this algorithm.

[1]  Bruno Siciliano,et al.  Modelling and Control of Robot Manipulators , 1997, Advanced Textbooks in Control and Signal Processing.

[2]  F. Girosi,et al.  Networks for approximation and learning , 1990, Proc. IEEE.

[3]  I. Jolliffe.  Principal Component Analysis , 2002 .

[4]  J. Colprim,et al.  MULTIVARIATE STATISTICAL PROCESS CONTROL TO SITUATION ASSESSMENT OF A SEQUENCING BATCH REACTOR , 2004 .

[5]  Sanjoy Dasgupta,et al.  A Generalization of Principal Components Analysis to the Exponential Family , 2001, NIPS.

[6]  Joaquim Melendez,et al.  Multivariable statistical process control to situation assessment of a sequencing batch reactor , 2004 .

[7]  P. D. Groen.  An Introduction to Total Least Squares , 1998, math/9805076.

[8]  B. Atal.  A model of LPC excitation in terms of eigenvectors of the autocorrelation matrix of the impulse response of the LPC filter , 1989, International Conference on Acoustics, Speech, and Signal Processing,.

[9]  Bruno Siciliano,et al.  Modelling and Control of Robot Manipulators , 1997, Advanced Textbooks in Control and Signal Processing.

[10]  Tommy W. S. Chow,et al.  An accelerated recurrent network training algorithm using IIR filter model and recursive least squares method , 1997 .

[11]  S. Van Huffel,et al.  A novel neural approach to inverse problems with discontinuities (the GMR neural network) , 2003, Proceedings of the International Joint Conference on Neural Networks, 2003..

[12]  Michael E. Tipping,et al.  Probabilistic Principal Component Analysis , 1999 .

[13]  L. Siciliano.  Modelling and Control of Robot Manipulators , 2000 .

[14]  M. Melluso,et al.  STOCHASTIC ESTIMATE PCA ALGORITHM FOR PLANAR INDUSTRIAL MANIPULATOR CONTROL , 2004 .